Privacy leakage in Multimodal Large Language Models (MLLMs) has long been an intractable problem. Existing studies, though effectively obscure private information in MLLMs, often overlook the evaluation of authenticity and recovery quality of user privacy. To this end, this work uniquely focuses on the critical challenge of how to restore surrogate-driven protected data in diverse MLLM scenarios. We first bridge this research gap by contributing the SPPE (Surrogate Privacy Protected Editable) dataset, which includes a wide range of privacy categories and user instructions to simulate real MLLM applications. This dataset offers protected surrogates alongside their various MLLM-edited versions, thus enabling the direct assessment of privacy recovery quality. By formulating privacy recovery as a guided generation task conditioned on complementary multimodal signals, we further introduce a unified approach that reliably reconstructs private content while preserving the fidelity of MLLM-generated edits. The experiments on both SPPE and InstructPix2Pix further show that our approach generalizes well across diverse visual content and editing tasks, achieving a strong balance between privacy protection and MLLM usability.

Knowledge transfer (KT) plays an essential role in evolutionary multitask optimization (EMTO), whereas ”what to transfer” and ”how to transfer” are the key focuses that influence the KT performance. For the issue ”what to transfer”, many EMTO algorithms often transfer the top individuals directly during the KT process. However, the transferred individual information is not always effective, especially when the tasks own the low similarity. For the issue ”how to transfer”, many KT methods mainly focus on learning from all dimensions in a single individual, causing the lack of learning diversity. Therefore, in this paper, we propose a novel directional combination learning method for multitask optimization, termed as DCLMTO, tries to address these two issues effectively. Specifically, for the issue ”what to transfer”, a directional learning (DL) strategy is developed to deeply extract the useful directional knowledge, which is behind the individual information and shows the trend of moving toward better position, for KT preparation. For the issue ”how to transfer”, a combination learning (CL) strategy is designed to fully combine the superiorities of different individuals for enriching the learning diversity. Moreover, DCLMTO can be easily extended to many-task optimization problems (MaTOPs) and can directly avoid the difficulty of task selection, showing its convenience and scalability. Experimental results demonstrate that DCLMTO significantly outperforms other state-of-the-art EMTO and EMaTO algorithms on the multitask benchmarks CEC17 and CEC22, and the many-task benchmarks CEC19 and WCCI20. Finally, DCLMTO is applied to a real-world multitask planar kinematic arm control application, further demonstrating its applicability.

The rapid growth of video-based social applications has intensified the demand for efficient transmission and personalized cartoon-style customization. Existing solutions typically apply talking face video and text codecs, followed by cartoon-style control algorithms, which often result in unsatisfactory compression performance and high inference latency. In this paper, we propose CartoonCodec, an efficient generative framework that unifies face video coding and cartoon-style control into an end-to-end process. Our framework encodes facial video sequences into compact motion feature representations, which are transmitted together with compressed text prompts. To integrate control into the coding process while ensuring efficient compression, a text-guided adaptive layer selection mechanism relying on the compact representations is introduced to dynamically select and optimize the most influential layers in the generators. Furthermore, to facilitate stylization over the decoupled spaces, we propose a self-supervised domain stylization training strategy that constructs both multimodal and unimodal data pairs, enabling the use of diverse loss functions. Extensive experiments demonstrate that CartoonCodec outperforms baselines in compression efficiency for video reconstruction and cartoon-style control tasks while maintaining competitive inference efficiency. CartoonCodec provides key insights for advancing face video communication with cartoon-style customization. The project page can be found at https://github.com/xiaonae/CartoonCodec/tree/main .

Salient Object Detection (SOD) aims to identify and segment the most prominent objects in an image. In real open environments, intelligent systems often encounter complex and challenging scenes, such as low-light, rain, snow, etc., which we call constrained conditions. These real situations pose more severe challenges to existing SOD models. However, there is no comprehensive and in-depth exploration of this field at both the data and model levels, and most of them focus on ideal situations or a single condition. To bridge this gap, we launch a new task, Condition-Constrained Salient Object Detection (CSOD), aimed at robustly and accurately locating salient objects in constrained environments. On the one hand, to compensate for the lack of datasets, we construct the first large-scale condition-constrained salient object detection dataset CSOD10 K, comprising 10,000 pixel-level annotated images and over 100 categories of salient objects. This dataset is oriented towards the real environment and includes 8 real-world constrained scenes under 3 main constraint types, making it extremely challenging. On the other hand, we abandon the paradigm of "restoration before detection" and instead introduce a unified end-to-end framework CSSAM that fully explores scene attributes, eliminating the need for additional ground-truth restored images and reducing computational overhead. Specifically, we design a Scene Prior-Guided Adapter (SPGA), which injects scene priors to enable the foundation model to better adapt to downstream constrained scenes. To automatically decode salient objects, we propose a Hybrid Prompt Decoding Strategy (HPDS), which can effectively integrate multiple types of prompts to achieve adaptation to the SOD task. Extensive experiments show that our model significantly outperforms state-of-the-art methods on both the CSOD10 K dataset and existing standard SOD benchmarks.

Machine vision systems, which can efficiently manage extensive visual perception tasks, are becoming increasingly popular in industrial production and daily life. Due to the challenge of simultaneously obtaining accurate depth and texture information with a single sensor, multimodal data captured by cameras and LiDAR is commonly used to enhance performance. Additionally, cloud-edge cooperation has emerged as a novel computing approach to improve user experience and ensure data security in machine vision systems. This paper proposes a pioneering solution to address the feature compression problem in multimodal 3D object detection. Given a sparse tensor-based object detection network at the edge device, we introduce two modes to accommodate different application requirements: Transmission-Friendly Feature Compression (T-FFC) and Accuracy-Friendly Feature Compression (A-FFC). In T-FFC mode, only the output of the last layer of the network's backbone is transmitted from the edge device. The received feature is processed at the cloud device through a channel expansion module and two spatial upsampling modules to generate multi-scale features. In A-FFC mode, we expand upon the T-FFC mode by transmitting two additional types of features. These added features enable the cloud device to generate more accurate multi-scale features. Experimental results on the KITTI dataset using the VirConv-L detection network showed that T-FFC was able to compress the features by a factor of 4933 with less than a 3% reduction in detection performance. On the other hand, A-FFC compressed the features by a factor of about 733 with almost no degradation in detection performance. We also designed optional residual extraction and 3D object reconstruction modules to facilitate the reconstruction of detected objects. The reconstructed objects effectively reflected the shape, occlusion, and details of the original objects.

Traditional video compression methods perform well at high bitrates but struggle to preserve fine-grained semantic information at low bitrates. Recently, with the blossoming of Multimodal Large Language Models (MLLMs), Cross-modal compression techniques offer prospective solutions for improving video compression under low-bitrate conditions. In this paper, we propose a unified Cross-Modality Video Compression (CMVC) framework that integrates multimodal representations and video generative models. The encoder disentangles video into spatial and temporal components, which are mapped to compact cross modal representations using MLLMs. During decoding, different encoding-decoding modes are employed to acquire various video reconstruction qualities, including Text-Text-to-Video (TT2V) for semantic preservation and Image-Text-to-Video (IT2V) for perceptual consistency. Additionally, we elaborate on an efficient frame interpolation model using Low-Rank Adaptation (LoRA) to improve the perceptual quality. Experimental results demon strate that TT2V achieves effective semantic reconstruction, while IT2V ensures competitive perceptual consistency. These findings suggest the potential of leveraging multimodal priors to improve video compression, offering promising future research directions.

Due to inadequate monitoring, key pollutants (e.g., PM2.5, VOCs, etc) very possibly leak into atmosphere, thus to endanger the long-term and short-term life safety of people that work and live in the environment. Therefore, it is imperative to effectively and efficiently detect the leakage of industrial waste gas, for the purpose of timely lowering the risk of pollution and explosions. To solve such a problem, we in this paper propose a new lightweight deep and wide network (LdwNet) for detecting the leakage of industrial waste gas from an image, which brings about the two main merits: 1) Compensating for the deficiencies of sensor-based detection methods, which can accurately detect the leakage of waste gas and even measure its concentrations but require to seek leakage sources beforehand; 2) Overcoming the shortcomings of image-based detection methods, which leverage DNN-based recognition technologies and usually suffer from low efficacy, low efficiency and high energy consumption during the model training and inference. To specify, the proposed LdwNet is developed by simulating human perception, motivated by the method which detects the leakage of industrial waste gas from surveillance images with the human observation and judgement. First, based on the inspiration that the human eyes are highly sensitive to horizontal and vertical stimuli, we construct a novel lightweight parallel-series-stripe (PS2) module to validly extract features with very few parameters. Second, to fully exploit deep and shallow features for fusing the global and local information, we extend the PS2 module as a backbone along both the deep and wide directions to build the multi-channel network. Third, to achieve effective, efficient and low-carbon detection in model running, we constraint the extended PS2 modules with parameter sharing to prodigiously reduce the model parameters and thus to make the proposed model ultra-lightweight. Experiments on the datasets of carbon particulate matters and ethylene leakage prove that our LdwNet with ten thousand parameters outperforms the state-of-the-art models with millions of parameters in detection accuracy and implementation cost, and this renders our proposed LdwNet more suitable for real industrial applications.

Remote sensing images captured from aerial perspectives often exhibit significant scale variations and complex backgrounds, posing challenges for salient object detection (SOD). Existing methods typically extract multi-level features at a single scale using uniform attention mechanisms, leading to suboptimal representations and incomplete detection results. To address these issues, we propose a GeoGran-Aware Hierarchical Feature Fusion Network (G2HFNet) that fully exploits geometric and granular cues in optical remote sensing images. Specifically, G2HFNet adopts Swin Transformer as the backbone to extract multi-level features and integrates three key modules: the multi-scale detail enhancement (MDE) module to handle object scale variations and enrich fine details, the dual-branch geo-gran complementary (DGC) module to jointly capture fine-grained details and positional information in mid-level features, and the deep semantic perception (DSP) module to refine high-level positional cues via self-attention. Additionally, a local-global guidance fusion (LGF) module is introduced to replace traditional convolutions for effective multi-level feature integration. Extensive experiments demonstrate that G2HFNet achieves high-quality saliency maps and significantly improves detection performance in challenging remote sensing scenarios.

This paper focuses on the inconsistency in salient regions between RGB and thermal images. To address this issue, we propose the Region-guided Selective Optimization Network for RGB-T Salient Object Detection, which consists of the region guidance stage and saliency generation stage. In the region guidance stage, three parallel branches with same encoder-decoder structure equipped with the context interaction (CI) module and spatial-aware fusion (SF) module are designed to generate the guidance maps which are leveraged to calculate similarity scores. Then, in the saliency generation stage, the selective optimization (SO) module fuses RGB and thermal features based on the previously obtained similarity values to mitigate the impact of inconsistent distribution of salient targets between the two modalities. After that, to generate high-quality detection result, the dense detail enhancement (DDE) module which adopts the multiple dense connections and visual state space blocks is applied to low-level features for optimizing the detail information. In addition, the mutual interaction semantic (MIS) module is placed in the high-level features to dig the location cues by the mutual fusion strategy. We conduct extensive experiments on the RGB-T dataset, and the results demonstrate that the proposed RSONet achieves competitive performance against 27 state-of-the-art SOD methods.

The conditional coding paradigm is widely used in learned video compression, which shows superior performance in capturing redundancies within a large context space. However, existing Conditional coding-based Learned Video Compression (C-LVC) methods ignore that the predicted motion vectors usually contain large uncertainty due to complex motions, occlusions, etc., which consequently decrease the accuracy of the generated temporal contexts. In addition, existing C-LVC methods have a weak ability to mine diverse dependencies within the context space, which are closely related to the coding efficiency. To address these issues, an efficient temporal redundancy mining method is proposed to improve the coding efficiency of C-LVC in this paper. To generate accurate temporal contexts, a Long Short-Term Motion Aggregation (LSTMA) model is proposed, in which an LSTMA-based motion estimation module is developed to capture both current and aggregated long short-term motion information to reduce the uncertainty of predicted motion vectors. Based on the dual motion information, an LSTMA-based temporal context mining module is developed to exploit the aggregated long short-term motion information and increase the accuracy of the generated temporal contexts. In order to fully eliminate spatial-temporal redundancies in a video, a Global-Local Information Decorrelation Module (GLIDM)-based context codec is proposed, in which the GLIDM is designed based on the visual state space block (namely vmamba), the residual block, and the squeeze-and-excitation block to effectively capture long-range, short-range spatial-temporal dependencies and channel-wise dependencies. Experimental results demonstrate that our proposed method can effectively improve the coding performance of C-LVC, and outperforms other state-of-the-art LVC methods.

Large-scale optimization problem (LSOP) is an essential research topic in the field of evolutionary computation community. Many large-scale optimization algorithms often maintain a large population for diversity enhancement. However, updating such a large population consumes a significant number of fitness evaluations (FEs), which may lead to the insufficient evolution of the population. In light of this, this article proposes a small-scale learning particle swarm optimization (SSLPSO) for solving LSOPs. In the small-scale learning mechanism, only up to two representative individuals are updated in every generation to effectively save FEs and prolong the evolutionary generations, so as to refine the solution accuracy. Specifically, we first design a representative individual selection (RIS) strategy to select the convergence representative individual and the diversity representative individual for updating. Then, we develop a representative individual learning (RIL) strategy, which includes a convergence learning method and a diversity learning method for the convergence representative individual and the diversity representative individual, respectively. Meanwhile, we further propose an adaptive strategy adjustment (ASA) method based on evolutionary state assessment to determine whether the representative individuals should be updated, further achieving the adaptive adjustment of the evolutionary behavior in the population. Experimental results on the commonly used large-scale test suites, IEEE CEC2010 and IEEE CEC2013, show that the performance of SSLPSO is significantly better than, or at least comparable to other state-of-the-art large-scale optimization algorithms, including the winners of large-scale competitions. Finally, the application of SSLPSO to a large-scale constrained water distribution network optimization problem further demonstrates its real-world applicability.

Set meal design (SMD) for online-to-offline (O2O) restaurant services presents a complex optimization problem, requiring the simultaneous satisfaction of diverse customer preferences, operational constraints, and profit maximization objective. To address this challenge, this article proposes a comprehensive mathematical formulation for the O2O-SMD problem. This formulation integrates complex operational requirements, such as dish variety, pricing, nutritional balance, and profitability, into a unified optimization problem with well-defined objective and constraints. To efficiently solve the O2O-SMD problem, we propose a tensor-based ant colony optimization (TACO) algorithm. Distinct from traditional ant colony optimization (ACO) variants, the core of TACO lies in reformulating the fundamental ACO operations into a tensor computational structure, enabling parallel optimization over O2O-SMD tasks at the algorithmic level. Furthermore, a dedicated local search strategy is integrated to refine solutions and accelerate convergence of the algorithm. The performance of TACO is evaluated on real-world restaurant data and benchmark instances. The experimental results show that TACO significantly outperforms a wide range of comparison algorithms in terms of solution quality, scalability, and computational efficiency, confirming its effectiveness and practical value for real-world O2O-SMD problems.

evolutionary multitask optimization (EMTO) aims to optimize multiple tasks simultaneously. In recent years, various EMTO algorithms based on knowledge transfer (KT) have been developed to utilize the information from other tasks and promote the optimization of the current task. However, most of them often use the fixed KT probability (ktp) and a single evolutionary search operator (ESO) during the evolution process, which lacks an adaption mechanism and cannot meet the different searching requirements among multiple tasks. Fuzzy system can effectively express the qualitative knowledge with unclear boundaries, which has good adaptability to nonindependent EMTO. Therefore, this article proposes a fuzzy adaptive multitask optimization (FAMTO), which employs a fuzzy adaptive transfer (FAT) strategy for intertask KT to achieve the adaptive adjustment of the ktp by designing a comprehensive evaluation in KT performance from two aspects, including the survival rate and the quality of transferred offspring. In FAT strategy, the fuzzy logical is employed to handle the interdependent relationships among multiple indicators, further achieving the more robust and adaptive ktp adjustment. In addition, an individual-based random selection (IRS) strategy is developed for each individual to choose the suitable ESO for intratask self-evolution in fuzzy adaptive multitasking optimization (FAMTO). Experimental results show that FAMTO achieves significantly better performance than other state-of-the-art EMTO algorithms on two well-known multitask benchmarks, CEC17 and CEC22. Furthermore, FAMTO is applied to a real-world multitask planar kinematic arm control application, demonstrating its applicability. Finally, the extended experiments on many-task optimization problems (MaTOPs) illustrate the scalability of FAMTO.

In recent years, the task of detecting salient objects in optical remote-sensing images has posed a significant and formidable challenge. The existing approaches heavily rely on a limited amount of label saliency masks and usually utilize convolutional neural networks (CNNs) for feature decoding. In this article, we introduce the conditional diffusion transformer network (CDTNet), a novel architecture meticulously designed to learn contextualized and diffusion-guided features for optical remote sensing image salient object detection (ORSI SOD). Our work presents a Transformer-based progressive cross-stage fusion (PCSF) module. This module serves as the decoding unit for saliency prediction, enabling the seamless integration of multiscale features from different stages of the network. Through this fusion, the model can better understand the inner structure of the image and enhance the accuracy of saliency prediction. Moreover, we develop a patch strategy (PS). This strategy is dedicated to fine-grained feature aggregation, allowing the network to focus on detailed information within individual feature patches and thus making better use of transformer layers. In addition, the encoder feature enhancement (EFE) module is applied to enhance the extracted features from the backbone network by utilizing spatial and channel attention. We conduct comprehensive experiments on various benchmark datasets and evaluation metrics. The experimental results unequivocally demonstrate the superiority of the proposed CDTNet over the comparison SOTA methods.

How to simultaneously locate multiple global peaks and achieve certain accuracy on the found peaks are two key challenges in solving multimodal optimization problems (MMOPs). In this article, a landscape-aware differential evolution (LADE) algorithm is proposed for MMOPs, which utilizes landscape knowledge to maintain sufficient diversity and provide efficient search guidance. In detail, the landscape knowledge is efficiently utilized in the following three aspects. First, a landscape-aware peak exploration helps each individual evolve adaptively to locate a peak and simulates the regions of the found peaks according to search history to avoid an individual re-locating an already found peak. Second, a landscape-aware peak distinction distinguishes whether an individual locates a new global peak, a new local peak, or an already found peak. Accuracy refinement can thus only be conducted on the global peaks to enhance the search efficiency. Third, a landscape-aware reinitialization specifies the initial position of an individual adaptively according to the distribution and distinction of the found peaks, which helps explore more peaks. The experiments are conducted on the widely-used benchmark MMOPs and multimodal nonlinear equation system problems. Experimental results show that LADE obtains generally better or competitive performance compared with seven well-performing recent algorithms and four winner algorithms in the IEEE CEC competitions for multimodal optimization.

Localized feature selection (LFS) methods divide the whole sample space to determine region-specific subsets for classification which outperform traditional feature selection with a global feature subset for the entire sample space. However, existing LFS algorithms decompose the local regions by impurity level of samples, which can misplace critical samples and impair feature selection results. To tackle this issue, this paper proposes a novel Fuzzy Localized Feature Selection (Fuzzy-LFS) algorithm, which divides local regions around each sample based on Gaussian fuzzy membership to enhance the coherence of region-specific information. Besides, to handle data fuzziness and uncertainty, Fuzzy-LFS establishes a Local Neighborhood Rough Set Model with forward greedy optimization to search the feature subsets. A novel local classifier is subsequently developed, overcoming the limitations of global classifiers unsuited for LFS while mitigating the excessive dependency on impurity level in traditional local classifiers. Specifically, for high-dimensional datasets, we introduce a Localized Feature Relevance Pre-Selection strategy, assigning sample-specific feature subsets according to local relevance to assist in dividing local regions and enhance classification performance. Through comprehensive experiments on 11 low-dimensional and 13 high-dimensional datasets, Fuzzy-LFS achieves superior classification accuracy to state-of-the-art LFS methods, demonstrating its effectiveness.

Facial image acquisition under constrained illumination and with limited-resolution imaging devices often results in coupled photometric and geometric degradations, manifesting as low-light and low-resolution (LLR) conditions. Prevailing research predominantly follows fragmented optimization paradigms that address low-light image enhancement (LLIE) and face super-resolution (FSR) as isolated tasks. This approach overlooks the compound nature of the degradations, thereby significantly limiting their applicability in practical scenarios. To bridge this gap, we present DiffLLFace, a unified framework that harnesses diffusive generative capabilities with illumination-aware trajectories to achieve robust FSR from LLR observations. The core of our method lies in its alternate illumination-diffusion adaptation, which operates throughout the generation process. This mechanism not only captures degradation patterns in both brightness and structure to harmonize latent representations but also dynamically calibrates the illumination prior with the generative knowledge inherent to diffusion models. As such, DiffLLFace attains precise control over conditional adaptation and illumination rectification. We further devise a simple yet effective non-parametric Fourier enhancement strategy, which provides structural appearance clues that work in concert with the alternate adaptation to ensure texture and color consistency. Extensive experiments demonstrate the superiority of DiffLLFace over existing methods and remarkable generalizability on complex natural scenes. Code is available at https://github.com/KaishengPang/DiffLLFace.

Vision Transformer (ViT) and its variants have witnessed a significant success in computer vision. However, their performance may degrade in underwater dense prediction tasks due to challenges like complex underwater environments, quality degradation, and light scattering in underwater images. To solve this problem, we propose the Vision Transformer Underwater-Adapter (ViT-UWA), the first detail-focused and adapted ViT backbone for underwater dense prediction tasks, without requiring task-specific pretraining. In ViT-UWA, we first introduce High-frequency Components Prior (HFCP) to add high-frequency information of underwater images to the plain ViT, which can help recover and capture lost high-frequency information of underwater images. Then, we propose a Detail Aware Module (DAM) to obtain a detail-focused multi-scale convolutional feature pyramid, which can be used in kinds of dense prediction tasks. Through the ViT-DAM Cross Fusion (VDCF), we achieve bidirectional feature cross fusion between ViT and DAM. We evaluate ViT-UWA on multiple underwater dense prediction tasks, including semantic segmentation, instance segmentation, and object detection. With only ImageNet-22K pretraining, our ViT-UWA-B yields state-of-the-art 46.4 box AP and 44.2 mask AP on USIS10K dataset, which demonstrates the superiority of our method. Our code is available at https://github.com/Linqirui/ViT-UWA.

Efficient talking face video coding and control are crucial in modern video communication, reshaping how individuals connect, collaborate, and interact. Coding seeks to reduce transmission costs, while control enables the realization of user-customizable facial expressions and head poses in the transmitted videos. However, the compression efficiency of the common par-adigm of applying control algorithms before video coding is not satisfactory. In this paper, we propose an efficient, Controllable Generative Talking Face Video Coding (CoFaCo) framework, wh-ich seamlessly integrates control into the coding process. Specific-ally, CoFaCo projects talking face videos into ultra-compact and semantic feature representations that can be customized by users before compression. To enable independent controls of pose and expression, we design a set of sophisticated losses to accurately de-couple the pose and expression direction codes. Once the decoupled direction codes and the semantic face representations are obtained, the pose and expression control modules can be effectively learned to generate decoupled, controlled pose and expression direction codes. The controlled direction codes are subsequently smoothed to enhance temporal consistency in the controlled video output by the generators. Experimental results demonstrate that CoFaCo achieves competitive compression efficiency in ultra-low bit rate video reconstruction and control tasks, providing valuab-le insights for advancing face video communication with diverse control capabilities.

The geometry-based point cloud compression algorithm achieves efficient compression and transmission for LiDAR point clouds with high sparsity. However, the low-bitrate mode results in severe geometry compression artifacts, which involve both point reduction and coordinate offset. To the best of our knowledge, this is the first attempt to directly enhance the geometry quality for compressed LiDAR point cloud (CLGE) in a post-processing manner. Our proposed method consists of two branches: cylindrical densification and adaptive refinement. The former adopts a multi-scale sparse convolution framework to effectively extract spatial features in the cylindrical coordinate system and generate dense candidate points quickly. Large asymmetric sparse convolution kernels are also designed to capture the shapes of different regions and objects. The latter branch refines the candidate points through several MLP layers, which takes the neighborhood features between the candidate points and the input points into account. Finally, the designed ring-based farthest point resampling serves as an effective alternative for achieving the target number while maintaining the geometry distribution. Extensive experiments conducted on several datasets verify the effectiveness of our approach under different compression artifact levels. Furthermore, our method is easily extended to upsampling and is robust to noise. In addition to the geometry signal quality improvement, the point cloud enhanced by our proposed method alleviates the performance degradation in object detection task due to compression distortion.

With the development of underwater exploration and marine protection, underwater vision tasks are widespread. Due to the degraded underwater environment, characterized by color distortion, low contrast, and blurring, camouflaged instance segmentation (CIS) faces greater challenges in accurately segmenting objects that blend closely with their surroundings. Traditional camouflaged instance segmentation methods, trained on terrestrial-dominated datasets with limited underwater samples, may exhibit inadequate performance in underwater scenes. To address these issues, we introduce the first underwater camouflaged instance segmentation (UCIS) dataset, abbreviated as UCIS4K, which comprises 3,953 images of camouflaged marine organisms with instance-level annotations. In addition, we propose an Underwater Camouflaged Instance Segmentation network based on Segment Anything Model (UCIS-SAM). Our UCIS-SAM includes three key modules. First, the Channel Balance Optimization Module (CBOM) enhances channel characteristics to improve underwater feature learning, effectively addressing the model's limited understanding of underwater environments. Second, the Frequency Domain True Integration Module (FDTIM) is proposed to emphasize intrinsic object features and reduce interference from camouflage patterns, enhancing the segmentation performance of camouflaged objects blending with their surroundings. Finally, the Multi-scale Feature Frequency Aggregation Module (MFFAM) is designed to strengthen the boundaries of low-contrast camouflaged instances across multiple frequency bands, improving the model's ability to achieve more precise segmentation of camouflaged objects. Extensive experiments on the proposed UCIS4K and public benchmarks show that our UCIS-SAM outperforms state-of-the-art approaches. The code and dataset are released at https://github.com/wchchw/UCIS4K.

Colored point cloud comprising geometry and attribute components is one of the mainstream representations enabling realistic and immersive 3D applications. To generate large-scale and denser colored point clouds, we propose a deep learning-based Joint Geometry and Attribute Up-sampling (JGAU) method, which learns to model both geometry and attribute patterns and leverages the spatial attribute correlation. Firstly, we establish and release a large-scale dataset for colored point cloud up-sampling, named SYSU-PCUD, which has 121 large-scale colored point clouds with diverse geometry and attribute complexities in six categories and four sampling rates. Secondly, to improve the quality of up-sampled point clouds, we propose a deep learning-based JGAU framework to up-sample the geometry and attribute jointly. It consists of a geometry up-sampling network and an attribute up-sampling network, where the latter leverages the up-sampled auxiliary geometry to model neighborhood correlations of the attributes. Thirdly, we propose two coarse attribute up-sampling methods, Geometric Distance Weighted Attribute Interpolation (GDWAI) and Deep Learning-based Attribute Interpolation (DLAI), to generate coarsely up-sampled attributes for each point. Then, we propose an attribute enhancement module to refine the up-sampled attributes and generate high quality point clouds by further exploiting intrinsic attribute and geometry patterns. Extensive experiments show that Peak Signal-to-Noise Ratio (PSNR) achieved by the proposed JGAU are 33.90 dB, 32.10 dB, 31.10 dB, and 30.39 dB when up-sampling rates are $4\times $ , $8\times $ , $12\times $ , and $16\times $ , respectively. Compared to the state-of-the-art schemes, the JGAU achieves an average of 2.32 dB, 2.47 dB, 2.28 dB and 2.11 dB PSNR gains at four up-sampling rates, respectively, which are significant. The code is released with https://github.com/SYSU-Video/JGAU.

Conventional end-to-end learning-based point cloud compression requires training multiple models to adapt to different target bit rates. Moreover, the rate difference between geometry and attribute components of point clouds is not well-considered. In this paper, we propose an end-to-end Rate-Reconfigurable Deep Point Cloud Compression (RR-DPCC) with on/off-line Perceptual Bit Allocation Optimization (PBAO-ON/OFF), which achieves arbitrary bit rate control with one trained deep model and high efficiency joint geometry and attribute coding. First, we propose the framework of the RR-DPCC using PBAO-ON/OFF, which includes Point Cloud Quality Assessment (PCQA) for perceptual quality measurement, PBAO-ON/OFF modules for bit allocation and RR-DPCC for high efficiency point cloud coding. Second, we propose a one-stream network of the RR-DPCC to encode the attribute and geometry of point clouds jointly. Moreover, in RR-DPCC, a bitrate reconfigurable module is proposed to encode multiple fine-grained bitrate points with one trained model and a rate allocation module is proposed to allocate bits between geometry and attribute. Third, we propose on/off-line PBAO algorithms to maximize the perceptual quality of the reconstructed point cloud, where the bits are properly allocated based on the importance of geometry and attribute. Meanwhile, rate-distortion models (R- $\alpha $ / $\beta $ and D- $\alpha $ / $\beta $ ) are derived for high accuracy rate control and bit allocation. Experimental results show that the proposed RR-DPCC achieves fine-grained bitrate control and allocation through a single trained model. When combined the proposed RR-DPCC with PBAO-ON, it reduces -6.56% and -18.68% bit rate on average as comparing with the state-of-the-art V-PCC and Deep Joint Geometry and Attribute Compression (Deep-JGAC), respectively. When combined with the PBAO-OFF, it achieves -4.90% and -15.34% bit rate reductions on average, and reduces 98.38%/22.05% and 53.75%/10.04% encoding/decoding time on average with respect to V-PCC and Deep-JGAC.

Collaborative Perception (CP) has been shown to be a promising technique for multi-agent autonomous driving and multi-agent robotic systems, where multiple agents share their perception information to enhance the overall perception performance and expand the perception range. However, in CP, an ego agent needs to receive messages from its collaborators, which makes it vulnerable to attacks from malicious agents. To address this critical issue, we propose a unified, probability-agnostic, and adaptive framework, namely, CP-uniGuard, which is a tailored defense mechanism for CP deployed by each agent to accurately detect and eliminate malicious agents in its collaboration network. Our key idea is to enable CP to reach a consensus rather than a conflict against an ego agent's perception results. Based on this idea, we first develop a probability-agnostic sample consensus (PASAC) method to effectively sample a subset of the collaborators and verify the consensus without prior probabilities of malicious agents. Furthermore, we define collaborative consistency loss (CCLoss) for object detection task and bird's eye view (BEV) segmentation task to capture the discrepancy between an ego agent and its collaborators, which is used as a verification criterion for consensus. In addition, we propose online adaptive threshold via dual sliding windows to dynamically adjust the threshold for consensus verification and ensure the reliability of the systems in dynamic environments. Finally, we conduct extensive experiments and demonstrate the effectiveness of our framework.

High-quality fundus images are critical for clinical diagnosis, yet real-world acquisition challenges often introduce multi-component degradations. Current deep learning methods typically address single degradations, lacking a unified handling of complex scenarios. In this paper, we propose the Multi-degradation Fundus Image Restoration Network (MFR-Net), an all-in-one restoration framework integrating frequency-aware prompt learning. MFR-Net comprehensively extracts the frequency domain features of different degradation components, and injects them into the backbone network through designed prompt generation and interaction modules. Furthermore, to enhance the model's domain generalization capability, the unsupervised domain adaptation is incorporated into a more reliable perceptual and image quality-oriented space for domain alignment. Extensive experimental results demonstrate that the proposed method outperforms several state-of-the-art models in the restoration of degraded retinal images, especially in the restoration of complex degradations in real images, where the quantitative indicators have been improved by up to 5.42% compared with SOTA algorithms.

With the rapid growth of cloud services, the storage of images in cloud environments requires secure and effective data encryption methods. Many thumbnail-preserving encryption (TPE) methods have thus been proposed to balance privacy and usability of image data. However, the exposure of thumbnail information in TPE methods may introduce privacy leakage risk, and a systematic evaluation of their security has not yet been conducted. In this paper, we propose a new Mamba-Transformer cooperation Network (MTNet) to recover the original images from the limited exposed thumbnail information, highlighting the information disclosure problem in TPE. Specifically, the core model component integrates a Mamba block and a Transformer block, which employ the powerful capabilities of the Mamba for wide field dependency modeling and the Transformer for effective channel interaction. Besides, the cascade architecture incorporates an intermediate output that provides supplementary information and achieves multilevel supervision, thereby improving the quality of the final output. Finally, to better utilize the subtle details in different levels, we propose a multi-scale fusion module that adaptively integrates features from various stages of the encoding process. The experimental results achieved by our proposed MTNet reveal that the privacy risk associated with TPE is significantly underestimated and more robust defense mechanisms are required. Source code is available athttps://github.com/HITLiXincodes/MTNet.

Just Recognizable Difference (JRD) represents the minimum visual difference that is detectable by machine vision, which can be exploited to promote machine vision-oriented visual signal processing. In this paper, we propose a Deep Transformer-based JRD (DT-JRD) prediction model for Video Coding for Machines (VCM), where the accurately predicted JRD can be used to reduce the coding bit rate while maintaining the accuracy of machine tasks. Firstly, we model the JRD prediction as a multi-class classification and propose a DT-JRD prediction model that integrates an improved embedding, a content and distortion feature extraction, a multi-class classification, and a novel learning strategy. Secondly, inspired by the perception property that machine vision exhibits a similar response to distortions near JRD, we propose an asymptotic JRD loss by using Gaussian Distribution-based Soft Labels (GDSL), which significantly extends the number of training labels and relaxes classification boundaries. Finally, we propose a DT-JRD-based VCM to reduce the coding bits while maintaining the accuracy of object detection. Extensive experimental results demonstrate that the mean absolute error of the predicted JRD by the DT-JRD is 5.574, outperforming the state-of-the-art JRD prediction model by 13.1%. Coding experiments show that compared with the VVC, the DT-JRD-based VCM achieves an average of 29.58% bit rate reduction while maintaining the object detection accuracy.

Multi-scale feature compression is essential in machine vision tasks for reducing storage and transmission costs while maintaining task performance. However, existing multi-scale feature compression methods fail to effectively extract and aggregate the local and global correlations of multi-scale features, resulting in incomplete elimination of feature redundancies. Moreover, these multi-scale feature compression methods mainly rely on mean square error-based loss functions to optimize signal fidelity, but they fail to adequately preserve semantic information critical to machine vision tasks. To address these issues, a Multi-receptive-field Convolutional Neural Network (MCNN)-based multi-scale feature compression method is proposed in this paper, which not only achieves compact fusion of multi-scale features but also enhances the semantic fidelity of reconstructed features. To effectively eliminate feature redundancies, a multi-receptive-field-based feature fusion module is designed for capturing both local and global correlations in multi-scale features. To enhance the quality of the reconstructed features, a cosine similarity-based multi-fidelity loss function is developed by considering both signal and semantic fidelity. Extensive experiments on the object detection and instance segmentation tasks show that the proposed MCNN outperforms the state-of-the-art multi-scale feature compression methods in terms of compression efficiency. The source code of our proposed MCNN is publicly available athttps://github.com/NUIST-Videocoding/MCNN.git.

The eye-tracking video saliency prediction (VSP) task and video salient object detection (VSOD) task both focus on the most attractive objects in video and show the result in the form of predictive heatmaps and pixel-level saliency masks, respectively. In practical applications, eye tracker annotations are more readily obtainable and align closely with the authentic visual patterns of human eyes. Therefore, this paper aims to introduce fixation information to assist the detection of video salient objects under weak supervision. On the one hand, we ponder how to better explore and utilize the information provided by fixation, and then propose a Position and Semantic Embedding (PSE) module to provide location and semantic guidance during the feature learning process. On the other hand, we achieve spatiotemporal feature modeling under weak supervision from the aspects of feature selection and feature contrast. A Semantics and Locality Query (SLQ) Competitor with semantic and locality constraints is designed to effectively select the most matching and accurate object query for spatiotemporal modeling. In addition, an Intra-Inter Mixed Contrastive (IIMC) model improves the spatiotemporal modeling capabilities under weak supervision by forming an intra-video and inter-video contrastive learning paradigm. Experimental results on five popular VSOD benchmarks indicate that our model outperforms other competitors on various evaluation metrics.

Video deinterlacing remains a significant challenge due to structural artifacts and information loss. When displayed on modern digital devices, early interlaced videos often suffer from complex interlacing and compression artifacts, which severely degrade visual quality. Existing deinterlacing methods typically struggle to handle such diverse artifacts while preserving fine-grained details. To address these issues, we propose a novel Spatiotemporal Synchronization for Video Deinterlacing (SSVD). First, we design a Multi-Directional Shuffling Module (MDSM) to enhance the model's ability to capture spatial dependencies, thereby guiding the prediction of missing fields. Second, a Dynamic Cross-frame Interaction Module (DCIM) is incorporated to implicitly model inter-frame correspondences, effectively leveraging cross-frame information to alleviate the blurring and artifacts. Third, we develop a Gated Refinement Module (GRM) to achieve fine-grained reconstruction. Experimental results demonstrate SSVD is superior to the state-of-the-art algorithms in video deinterlacing tasks, achieving superior visual quality and detail reconstruction. Source code will be made public after the review is completed.

Small models, despite their computational efficiency for real-time and edge applications, remain vulnerable to adversarial attacks. Adversarial Distillation (AD) has proven effective in enhancing model robustness, yet current approaches predominantly rely on single-strategy adversarial samples with either fixed or adaptive teacher supervision. Fixed supervision often leads to over-smoothing due to static guidance, while adaptive supervision incurs higher computational costs and convergence instability. To address these limitations, we propose Dual Adversarial Distillation (DAD), a novel framework that synergistically combines fixed and adaptive supervision through multi-intensity adversarial samples, with customized distillation strategies designed to enhance knowledge diversity and feature transfer. For fixed supervision, a Mixup-based strategy is employed to diversify teacher knowledge, ensuring robust feature representations by aligning the student model with the teacher's rich representations through cross-strength feature consistency. For adaptive supervision, learning diversity is augmented by integrating transformed features from multiple projection modules, effectively minimizing the feature distribution gap between teacher and student models. Computational efficiency is optimized through variable iteration strategies. Extensive experiments demonstrate the effectiveness of our method in improving the robustness of small models, achieving state-of-the-art baselines.

Dynamic point clouds, widely used in virtual reality and autonomous driving systems, often suffer from distortions due to quantization in the process of compression. These distortions significantly degrade the visual quality of dynamic point clouds, especially temporal inconsistency. To address this issue, a temporal consistency-aware dynamic point clouds color attribute enhancement method is proposed in this work. Specifically, a 3D Spatial-Temporal Search (STS) module is designed to adaptively search point cloud patches in the temporal domain for feature alignment. These matched patches are then individually fed into Single Frame Feature Extraction (SFFE) module that comprises of multi-head attention and graph convolution to exploit latent features of point cloud color attribute. In addition, to further capture both the spatial and temporal dependencies, a Convolutional Point cloud Long Short-Term Memory (Conv-PointLSTM) network is applied, which integrates convolution and max pooling with LSTM mechanism to facilitate the color attribute correspondents across the spatial-temporal latent features. Experimental results demonstrate that the proposed method can achieve 0.44 dB gains on average in terms of Peak Signal-to-Noise Ratio (PSNR) and 1.50%/5.31%bit rate reductions at the low/high bit rate, which outperforms the state-of-the-art works. The source code and trained models are available athttps://github.com/xu-coder-666/DPC.

With the advancement of machine vision technology, automated vision inspection systems are needed in broad quality control scenarios. This article proposes a neighborhood attention-based feature reconstruction method for image anomaly detection and localization (NAFRAD). To address the challenges of data scarcity, low visibility, and irregular defect shapes in unsupervised anomaly detection, we introduce a feature reconstruction framework that preserves high-level abstract features rather than focusing on pixel-level reconstruction. This approach enhances model robustness and generalizability by leveraging neighborhood attention (NA) mechanisms, which simultaneously capture local details and the global context through a sliding window strategy. The NA-based autoencoder reconstructs normal features by aggregating local inductive biases with translational equivariance, enabling precise anomaly localization. Extensive experiments on the MVTec Anomaly Detection (MVTec AD) dataset—comprising 15 categories with 5,354 images—demonstrate the superiority of NAFRAD. It achieves state-of-the-art performance with AUROC \({}_{I}\) = 99.02, AUROC \({}_{P}\) = 98.99, and AP = 79.40, outperforming existing methods by 3.6% in AP and 0.89% in AUROC \({}_{P}\) . The framework’s effectiveness is validated through ablation studies, visualization of feature reconstruction, and comparisons with eight leading unsupervised methods. The code is made public at https://github.com/Math-Computer/NAFRAD .

Underwater imaging plays a pivotal role in marine exploration and ecological monitoring. However, it faces significant challenges of limited transmission bandwidth and severe distortion in the aquatic environment. In this work, to achieve the target of both underwater image compression and enhancement simultaneously, an enhanced quality-aware scalable underwater image compression framework is presented, which comprises a Base Layer (BL) and an Enhancement Layer (EL). In the BL, the underwater image is represented by a controllable number of non-zero sparse coefficients for coding bits saving. Furthermore, the underwater image enhancement dictionary is derived with shared sparse coefficients to make reconstruction close to the enhanced version. In the EL, a dual-branch filter comprising rough filtering and detail refinement branches is designed to produce a pseudo-enhanced version for residual redundancy removal and to improve the quality of final reconstruction. Extensive experimental results demonstrate that the proposed scheme outperforms the state-of-the-art works under five large-scale underwater image datasets in terms of Underwater Image Quality Measure (UIQM).

Crowdsourcing contests have become an important approach for organizations to tackle complex problems by gathering innovative solutions from globally distributed participants. However, as platforms always host an increasing number of concurrent contests, the voluntary and selective nature of participants usually leads to coordination difficulties and unpredictable outcomes, which present a critical challenge to guide multicontest settings toward success. To address this issue, this article proposes a novel and effective dynamic link prediction-based recommendation algorithm tailored for crowdsourcing platforms named the heterogeneous temporal graph generative adversarial network (HTGGAN). The HTGGAN leverages participants’ historical interaction data to predict the optimal set of participants for each future task. This ensures that participants’ skills and interests align with the contest requirements, thereby improving the success of crowdsourcing contests. Specifically, the HTGGAN contains four modules. First, the metapath-relation aggregation (MRA) module integrates information from multiple metapaths of the heterogeneous temporal graph (HTG) into a unified spatial embedding. Second, the group-relation aggregation (GRA) module incorporates learnable group-level features into node-level representation learning to enhance the expressiveness of the target node. Third, the across-time aggregation (ATA) module captures interactions between the target node and its temporal neighbors, enabling the learning of an initial spatiotemporal embedding. Finally, the optimized recommendation (OR) module incorporates a generative adversarial network and performs link prediction to recommend appropriate users for competitions or posts. Using a large real-world dataset constructed from the Kaggle platform, we demonstrate that HTGGAN outperforms several state-of-the-art algorithms across multiple metrics and delivers clear practical value.

Collaborative Perception (CP) has shown a promising technique for autonomous driving, where multiple connected and autonomous vehicles (CAVs) share their perception information to enhance the overall perception performance and expand the perception range. However, in CP, ego CAV needs to receive messages from the collaborators, which makes it easy to be attacked by malicious agents. For example, a malicious agent can send harmful information to the ego CAV to mislead it. To address this critical issue, we propose a novel method, **CP-Guard**, a tailored defense mechanism for CP that can be deployed by each agent to accurately detect and eliminate malicious agents in its collaboration network. Our key idea is that CP will lead to a consensus rather than a conflict against the ego CAV's perception results. Based on this idea, we first develop a probability-agnostic sample consensus (PASAC) method that can effectively sample a subset of the collaborators and verify the consensus without prior probabilities of malicious agents. Furthermore, we design a collaborative consistency loss (CCLoss) to calculate the discrepancy between the ego CAV and the collaborators, which is used as a verification criterion for consensus. Finally, we conduct extensive experiments in collaborative bird's eye view (BEV) tasks and the results demonstrate the effectiveness of our CP-Guard.

Assessing the quality of artificial intelligence-generated images (AIGIs) plays a crucial role in their application in real-world scenarios. However, traditional image quality assessment (IQA) algorithms primarily focus on low-level visual perception, while existing IQA works on AIGIs overemphasize the generated content itself, neglecting its effectiveness in real-world applications. To bridge this gap, we propose AIGI-VC, a quality assessment database for AI-Generated Images in Visual Communication, which studies the communicability of AIGIs in the advertising field from the perspectives of information clarity and emotional interaction. The dataset consists of 2,500 images spanning 14 advertisement topics and 8 emotion types. It provides coarse-grained human preference annotations and fine-grained preference descriptions, benchmarking the abilities of IQA methods in preference prediction, interpretation, and reasoning. We conduct an empirical study of existing representative IQA methods and large multi-modal models on the AIGI-VC dataset, uncovering their strengths and weaknesses.

Motion expression video segmentation aims to segment objects based on input motion descriptions. Compared with traditional referring video object segmentation, it focuses on motion and multi-object expressions and is more challenging. Previous works achieved it by simply injecting text information into the video instance segmentation (VIS) model. However, this requires retraining the entire model and optimization is difficult. In this work, we propose DMVS, a simple framework constructed on the existing query-based VIS model, emphasizing decoupling the task into video instance segmentation and motion expression understanding. Firstly, we use a frozen video instance segmenter to extract object-specific contexts and convert them into frame-level and video-level queries. Secondly, we interact two levels of queries with static and motion cues, respectively, to further encode visually enhanced motion expressions. Furthermore, we propose a novel query initialization strategy that uses video queries guided by classification priors to initialize motion queries, greatly reducing the difficulty of optimization. Without bells and whistles, DMVS achieves state-of-the-art performance on the MeViS dataset at a lower training cost. Extensive experiments verify the effectiveness and efficiency of our framework.

Large language models (LLMs) have achieved remarkable success in various tasks, such as decision-making, reasoning, and question answering. They have been widely used in edge devices. However, fine-tuning LLMs to specific tasks at the edge is challenging due to the high computational cost and the limited storage and energy resources at the edge. To address this issue, we propose TaskEdge, a task-aware parameter-efficient fine-tuning framework at the edge, which allocates the most effective parameters to the target task and only updates the task-specific parameters. Specifically, we first design a parameter importance calculation criterion that incorporates both weights and input activations into the computation of weight importance. Then, we propose a model-agnostic task-specific parameter allocation algorithm to ensure that task-specific parameters are distributed evenly across the model, rather than being concentrated in specific regions. In doing so, TaskEdge can significantly reduce the computational cost and memory usage while maintaining performance on the target downstream tasks by updating less than 0.1% of the parameters. In addition, TaskEdge can be easily integrated with structured sparsity to enable acceleration by NVIDIA’s specialized sparse tensor cores, and it can be seamlessly integrated with LoRA to enable efficient sparse low-rank adaptation. Extensive experiments on various tasks demonstrate the effectiveness of TaskEdge.

Deep learning has achieved success across many domains when sufficient training samples are available. However, the commonly used mini-batch stochastic gradient descent (SGD) training paradigm treats each sample equally, resulting in massive computational waste on samples that are easily identifiable. In contrast, low-quality samples, such as those with erroneous labels, can negatively impact the training process. To address these issues, we propose a training sample utilization method based on sample uncertainty. Once the model has acquired preliminary decision-making abilities, the class uncertainty for each sample can be evaluated within a training epoch. Subsequently, the samples are probabilistically selected based on their uncertainty for the next epoch. Experiments conducted on the GSC v2 and CIFAR-10 datasets demonstrate that the proposed method can reduce training time by over 32% and 58%, respectively, with only a loss of 1% performance. Additionally, the method has the capability to mitigate the adverse effects of samples with erroneous labels.

Multimodal Continual Instruction Tuning (MCIT) aims to enable Multimodal Large Language Models (MLLMs) to incrementally learn new tasks without catastrophic forgetting, thus adapting to evolving requirements. In this paper, we explore the forgetting caused by such incremental training, categorizing it into superficial forgetting and essential forgetting. Superficial forgetting refers to cases where the model’s knowledge may not be genuinely lost, but its responses to previous tasks deviate from expected formats due to the influence of subsequent tasks’ answer styles, making the results unusable. On the other hand, essential forgetting refers to situations where the model provides correctly formatted but factually inaccurate answers, indicating a true loss of knowledge. Assessing essential forgetting necessitates addressing superficial forgetting first, as severe superficial forgetting can conceal the model’s knowledge state. Hence, we first introduce the Answer Style Diversification (ASD) paradigm, which defines a standardized process for data style transformations across different tasks, unifying their training sets into similarly diversified styles to prevent superficial forgetting caused by style shifts. Building on this, we propose RegLoRA to mitigate essential forgetting. RegLoRA stabilizes key parameters where prior knowledge is primarily stored by applying regularization to LoRA’s weight update matrices, enabling the model to retain existing competencies while remaining adaptable to new tasks. Experimental results demonstrate that our overall method, SEFE, achieves state-of-the-art performance.

Due to the frequent occurrence of missing views in real-world multi-view data, incomplete multi-view clustering (IMVC) has attracted significant attention. However, most existing IMVC methods overlook the fact that incomplete data in practical applications often exhibits varying missing rates across different views, rendering their mechanisms ineffective under such conditions. Although several works based on conventional learning methods have been proposed to solve unbalanced incomplete multi-view clustering (UIMVC), their performance is limited by their shallow feature representation and over-sophisticated optimization procedure. In this paper, we propose Deep Unbalanced Incomplete Multi-view Clustering via Graph Constrained Imputation and Contrastive Learning (DUIMC) to address UIMVC with deep learning paradigm. Specifically, DUIMC introduces a novel differentiable imputation layer for dynamically handling unbalanced incompleteness and integrates it with multi-view contrastive clustering into a unified deep representation learning framework. Furthermore, bi-level graph constraints are imposed on imputation and representation learning to preserve local consistency at both the feature and instance levels. In addition, we develop adaptive fusion mechanisms to adaptively restrain the impact aroused by information unbalance among views. Extensive experimental results on five benchmark datasets demonstrate DUIMC's superior clustering performance over several traditional state-of-the-art approaches.

Point cloud processing and 3D vision have emerged as very hot topics in the multimedia community. Point clouds can give an immersive visual experience and provide accurate structural information of 3D objects and scenes in the applications including virtual reality/augmented reality (VR/AR), autonomous driving, robot navigation, and geo-information systems (GIS). Moreover, 3D Gaussian splatting has become a very powerful and popular tool for 3D reconstruction, generation and rendering, as well as compression, representation and understanding. 3D Gaussian splatting technology can also be deemed as an extension of point cloud processing technology. 3D vision technologies empower the developments of immersive media, embodied artificial intelligence (AI) and unmanned systems. Their challenges in processing, analysis, and applications have attracted significant interest from industry, academia, and standardization bodies. This workshop invites innovative contributions in point cloud processing and 3D Gaussian splatting to propel the advancements of 3D vision technologies.

Salient object detection (SOD) plays a crucial role in image understanding and visual guidance. However, due to the complexity of underwater environments, the accuracy of underwater salient object detection is often low. To improve the accuracy and robustness of underwater salient object detection, different from the existing spatial domain aware RGB-D methods that rely on pixel-level probabilities, we propose a novel Fourier-Spatial Entangled Conditional Diffusion model (FSCDiff) for underwater salient object detection. The FSCDiff aims to address the insufficient representation and boundary shift issues in underwater salient object detection by leveraging Fourier-domain information and the powerful multi-step iterative generation capability of diffusion models. The FSCDiff framework consists of two key components: the Dual-Domain Entanglement Enhancement Block (DTEB) and the Stable Time-step Mask Prediction Module (STMP). DTEB utilizes Fourier-spatial entanglement learning to fully exploit the Fourier and spatial domain information of RGB images and depth maps, thereby optimizing feature representation. STMP takes advantage of the excellent multi-step iterative mechanism of diffusion models to enhance the accuracy and robustness of the segmentation results. Comprehensive experimental results indicate that our FSCDiff method outperforms the state-of-the-art approaches on the USOD10K and USOD datasets. The source code is available at: https://github.com/lgwplay/FSCDiff.

Despite the effectiveness of Segment Anything Model (SAM) based methods in Few-Shot Segmentation (FSS) tasks, our closer examination of their prompt encoding mechanism reveals that these methods rely solely on visual information to generate a single type of prompt. Consequently, they suffer from semantic granularity representation bias and a loss of spatial information. To address these limitations, this paper introduces an innovative multi-modal prompt encoder, enabling SAM to leverage both annotated reference images and textual descriptions of class names as segmentation prompts. This approach generates text prompts, dense visual prompts, and sparse visual prompts, spanning multiple modalities and granularities. These prompts provide enhanced representations of the target class, capturing both abstract semantics and specific details, while ensuring granularity appropriateness. When our multi-modal prompt encoder is integrated with SAM's image encoder and mask decoder, the overall model is referred to as MM-Prompt. To validate its effectiveness, we conducted extensive empirical studies on the PASCAL-5^i and COCO-20^i datasets. The experimental results demonstrate that MM-Prompt achieves state-of-the-art performance in FSS tasks, highlighting its substantial potential and value in this domain.

Adapting billion-parameter language models to a downstream task is still costly, even with parameter-efficient fine-tuning (PEFT). We re-cast task adaptation as output-distribution alignment: the objective is to steer the output distribution toward the task distribution directly during decoding rather than indirectly through weight updates. Building on this view, we introduce Steering Vector Decoding (SVDecode), a lightweight, PEFT-compatible, and theoretically grounded method. We start with a short warm-start fine-tune and extract a task-aware steering vector from the Kullback-Leibler (KL) divergence gradient between the output distribution of the warm-started and pre-trained models. This steering vector is then used to guide the decoding process to steer the model's output distribution towards the task distribution. We theoretically prove that SVDecode is first-order equivalent to the gradient step of full fine-tuning and derive a globally optimal solution for the strength of the steering vector. Across three tasks and nine benchmarks, SVDecode paired with four standard PEFT methods improves multiple-choice accuracy by up to 5 percentage points and open-ended truthfulness by 2 percentage points, with similar gains (1-2 percentage points) on commonsense datasets without adding trainable parameters beyond the PEFT adapter. SVDecode thus offers a lightweight, theoretically grounded path to stronger task adaptation for large language models.

Prompt engineering has become an effective tool for numerous large language models (LLMs)-based tasks. However, it is still a challenge to adaptively optimize the prompt for the target task, where gradients are inaccessible via APIs and the search space is highly complex. Due to the ability to robustly handle complex and multimodal landscapes, and to adaptively explore complex search spaces without explicit gradient information, evolutionary computation (EC) algorithms have garnered significant attention in black-box optimization. However, the performance of different EC algorithms for prompt optimization remains uncertain, which cannot provide guidance for algorithm selection and design in prompt optimization. To alleviate this, a series of investigative experiments are conducted in this paper to evaluate the efficiency of EC algorithms in prompt optimization, which results in three novel findings. First, different EC algorithms, including XNES, CMA-ES, DE, and PSO, are compared on various few-shot learning tasks. The findings indicate that XNES can outperform other algorithms, achieving faster or smoother convergence and higher final accuracy under high-dimensional settings. Second, the role of truncation strategies is also investigated. Results show that moderate bounds effectively help the algorithm balance exploration and exploitation, whereas overly small or large bounds diminish performance. Third, the influence of different k-shot values is examined on the optimization performance for few-shot tasks, which shows that k=32 consistently provides the best trade-off between convergence speed and final model accuracy. In conclusion, these investigations validate the efficacy of the investigated EC algorithms and highlight the advantages of XNES for complex prompt optimization. They further underscore the importance offering valuable guidance for future black-box prompt tuning scenarios. These insights pave the way for future work on more diverse and complex tasks with larger LLMs.

The research of class-incremental semantic segmentation (CISS) seeks to enhance semantic segmentation methods by enabling the progressive learning of new classes while preserving knowledge of previously learned ones. A significant yet often neglected challenge in this domain is class imbalance. In CISS, each task focuses on different foreground classes, with the training set for each task exclusively comprising images that contain these currently focused classes. This results in an overrepresentation of these classes within the single-task training set, leading to a classification bias towards them. To address this issue, we propose a novel CISS method named STAR, whose core principle is to reintegrate the missing proportions of previous classes into current single-task training samples by replaying their prototypes. Moreover, we develop a prototype deviation technique that enables the deduction of past-class prototypes, integrating the recognition patterns of the classifiers and the extraction patterns of the feature extractor. With this technique, replay can be accomplished without using any storage to save prototypes. Complementing our method, we devise two loss functions to enforce cross-task feature constraints: the Old-Class Features Maintaining (OCFM) loss and the Similarity-Aware Discriminative (SAD) loss. The OCFM loss is designed to stabilize the feature space of old classes, thus preserving previously acquired knowledge without compromising the ability to learn new classes. The SAD loss aims to enhance feature distinctions between similar old and new class pairs, minimizing potential confusion. Our experiments on two public datasets, Pascal VOC 2012 and ADE20 K, demonstrate that our STAR achieves state-of-the-art performance.

Typically, deep network-based full-reference image quality assessment (FR-IQA) models compare deep features from reference and distorted images pairwise, overlooking correlations among features from the same source. We propose a dual-branch framework to capture the joint degradation effect among deep network features. The first branch uses kernel representation similarity analysis (KRSA), which compares feature self-similarity matrices via the mean absolute error (MAE). The second branch conducts pairwise comparisons via the MAE, and a training-free logarithmic summation of both branches derives the final score. Our approach contributes in three ways. First, integrating the KRSA with pairwise comparisons enhances the model's perceptual awareness. Second, our approach is adaptable to diverse network architectures. Third, our approach can guide perceptual image enhancement. Extensive experiments on 10 datasets validate our method's efficacy, demonstrating that perceptual deformation widely exists in diverse IQA scenarios and that measuring the joint degradation effect can discern appealing content deformations.

Existing Continual Semantic Segmentation (CSS) methods effectively address the issue of background shift in regular training samples. However, this issue persists in exemplars, i.e. , replay samples, which is often overlooked. Each exemplar is annotated only with the classes from its originating task, while other past classes and the current classes during replay are labeled as background . This partial annotation can erase the network’s knowledge of previous classes and impede the learning of new classes. To resolve this, we introduce a new method named Trace Back and Go Ahead (TAGA), which utilizes a backward annotator model and a forward annotator model to generate pseudo-labels for both regular training samples and exemplars, aiming at reducing the adverse effects of incomplete annotations. This approach effectively mitigates the risk of incorrect guidance from both sample types, offering a comprehensive solution to background shift . Additionally, due to a significantly smaller number of exemplars compared to regular training samples, the class distribution in the sample pool of each incremental task exhibits a long-tailed pattern, potentially biasing classification towards incremental classes. Consequently, TAGA incorporates a class-equilibrium sampling strategy that adaptively adjusts the sampling frequencies based on the ratios of exemplars to regular samples and past to new classes, counteracting the skewed distribution. Extensive experiments on two public datasets, Pascal VOC 2012 and ADE20K, demonstrate that our method surpasses state-of-the-art methods. • Proposes a method to address background shift problems in all training samples. • Utilizes annotators to complete missing annotations for past and new classes. • Implements a class-equilibrium sampling strategy to long-tail challenges. • Demonstrates superior performance of TAGA over the state-of-the-art CSS methods.

In underwater environments, the absorption and scattering of light often result in various types of degradation in captured images, including color cast, low contrast, low brightness, and blurriness. These undesirable effects pose significant challenges for both underwater photography and downstream tasks such as object detection, recognition, and navigation. To address these challenges, we propose a novel end-to-end underwater image enhancement (UIE) network via the multistage and mixed attention mechanism and a residual-based feature refinement module, called ERD. Specifically, our network includes an encoder stage for extracting features from input underwater images with channel, spatial, and patch attention modules to emphasize degraded channels and regions for restoration; a residual stage for further purification of informative features through sufficient feature learning; and a decoder stage for effective image reconstruction. Inspired by visual perception mechanism, we design the frequency domain loss and edge details loss to retain more high-frequency information and object details while ensuring that the enhanced image approximates the reference image in terms of color tone while preserving content and structure. To comprehensively evaluate our proposed UIE model, we also curated three additional underwater image datasets through online collection and generation using Cycle-GAN. Rigorous experiments conducted on a total of eight underwater image datasets demonstrate that the proposed ERD model outperforms state-of-the-art methods in enhancing both real-world and generated underwater images. Our code and datasets are available athttps://github.com/fansuregrin/ERD.

Image enhancement plays a crucial role in computer vision by improving visual quality while minimizing distortion. Traditional methods enhance images through pixel value transformations, yet they often introduce new distortions. Recent advancements in deep learning-based techniques promise better results but challenge the preservation of image fidelity. Therefore, it is essential to evaluate the visual quality of enhanced images. However, existing quality assessment methods frequently encounter difficulties due to the unique distortions introduced by these enhancements, thereby restricting their effectiveness. To address these challenges, this paper proposes a novel blind image quality assessment (BIQA) method for enhanced natural images, termed multi-scale local feature fusion and global feature representation-based quality assessment (MLGQA). This model integrates three key components: a multi-scale Feature Attention Mechanism (FAM) for local feature extraction, a Local Feature Fusion (LFF) module for cross-scale feature synthesis, and a Global Feature Representation (GFR) module using Vision Transformers to capture global perceptual attributes. This synergistic framework effectively captures both fine-grained local distortions and broader global features that collectively define the visual quality of enhanced images. Furthermore, in the absence of a dedicated benchmark for enhanced natural images, we design the Natural Image Enhancement Database (NIED), a large-scale dataset consisting of 8,581 original images and 102,972 enhanced natural images generated through a wide array of traditional and deep learning-based enhancement techniques. Extensive experiments on NIED demonstrate that the proposed MLGQA model significantly outperforms current state-of-the-art BIQA methods in terms of both prediction accuracy and robustness.

Co-salient object detection (CoSOD) is to find the salient and recurring objects from a series of relevant images, where modeling inter-image relationships plays a crucial role. Different from the commonly used direct learning structure that inputs all the intra-image features into some well-designed modules to represent the inter-image relationship, we resort to adopting a recursive structure for inter-image modeling, and propose a two-tier recursion network (TRNet) to achieve CoSOD in this paper. The two-tier recursive structure of the proposed TRNet is embodied in two stages of inter-image extraction and distribution. On the one hand, considering the task adaptability and inter-image correlation, we design an inter-image exploration with recursive reinforcement module to learn the local and global inter-image correspondences, guaranteeing the validity and discriminativeness of the information in the step-by-step propagation. On the other hand, we design a dynamic recursion distribution module to fully exploit the role of inter-image correspondences in a recursive structure, adaptively assigning common attributes to each individual image through an improved semi-dynamic convolution. Experimental results on five prevailing CoSOD benchmarks demonstrate that our TRNet outperforms other competitors in terms of various evaluation metrics. The code and results of our method are available athttps://github.com/rmcong/TRNet_TCSVT2025.

By now, many works have been done on shadow removal for image manipulation. As a result, detecting shadow removal has become a critical part to reveal the traces of image manipulation. However, there are only a few works conducted on shadow removal detection, and these works cannot accurately localize the image regions where the shadows have been removed. In this paper, we present a novel model called Multi-level Feature Fusion Network (MFF-Net) for shadow removal detection. MFF-Net consists of two parts: a dual-branch feature extraction encoder and a dense prediction decoder. The encoder anchors the approximate position of the manipulated regions, while the decoder progressively fills in the details of the estimated shadow masks by integrating multi-level information. In the encoder part, a global modeling branch is constructed to capture long-range dependencies, while a local feature extraction branch is designed to extract local structural information. The features extracted by these two branches are integrated using a feature fusion module. In the decoder part, a multi-scale feature upsampling module is proposed to upsample the input features and integrate them with the low-level features obtained from the encoder part. Meanwhile, the cross attention mechanism is introduced to guide the multi-level feature fusion process. Finally, the features of different resolutions are employed to estimate the shadow masks in a coarse-to-fine manner. Extensive experiments on shadow removal detection demonstrate the superiority of MFF-Net over the state-of-the-art methods. The source code of MFF-Net is publicly available athttps://github.com/HITFuxiwen/MFF-Net.

Fine-grained visual classification (FGVC) is a challenging task characterized by interclass similarity and intraclass diversity and has broad application prospects. Recently, several methods have adopted the vision Transformer (ViT) in FGVC tasks since the data specificity of the multihead self-attention (MSA) mechanism in ViT is beneficial for extracting discriminative feature representations. However, these works focus on integrating feature dependencies at a high level, which leads to the model being easily disturbed by low-level background information. To address this issue, we propose a fine-grained attention-locating vision Transformer (FAL-ViT) and an attention selection module (ASM). First, FAL-ViT contains a two-stage framework to identify crucial regions effectively within images and enhance features by strategically reusing parameters. Second, the ASM accurately locates important target regions via the natural scores of the MSA, extracting finer low-level features to offer more comprehensive information through position mapping. Extensive experiments on public datasets demonstrate that FAL-ViT outperforms the other methods in terms of performance, confirming the effectiveness of our proposed methods. The source code is available athttps://github.com/Yueting-Huang/FAL-ViT.

In the field of no-reference image quality assessment (NR-IQA), the visual masking effect has long been a challenging issue. Although existing methods attempt to alleviate the interference caused by masking by generating pseudoreference images, the quality of these images is often constrained by the accuracy and reconstruction capabilities of image restoration algorithms. This can introduce additional biases, thereby affecting the reliability of the evaluation results. To address this problem, we propose a novel generative “noise” estimation framework (GNE-Vim) that eliminates the need for pseudoreference images. Instead, it deeply decouples the distortion components from degraded images and performs quality-aware modelling of these components. During the training phase, the model leverages both reference images and distortion components to guide the learning of the true distortion distribution. In the inference phase, quality prediction is conducted directly on the basis of the decoupled distortion components, making the evaluation results more aligned with human subjective perception. The experimental results demonstrate that the proposed method achieves strong performance across datasets containing various types of distortions. The source code is publicly available at the following website: https://github.com/opencodelxt/GNE-Vim.

Few-shot segmentation (FSS) methods aim to segment objects using only a few pixel-level annotated samples. Current approaches either derive a generalized class representation from support samples to guide the segmentation of query samples, which often discards crucial spatial contextual information, or rely heavily on spatial affinity between support and query samples, without adequately summarizing and utilizing the core information of the target class. Consequently, the former struggles with fine detail accuracy, while the latter tends to produce errors in overall localization. To address these issues, we propose a novel FSS framework, CCFormer, which balances the transmission of core semantic concepts with the modeling of spatial context, improving both macro and micro-level segmentation accuracy. Our approach introduces three key modules: 1) the Concept Perception Generation (CPG) module, which leverages pre-trained category perception capabilities to capture high-quality core representations of the target class; 2) the Concept-Feature Integration (CFI) module, which injects the core class information into both support and query features during feature extraction; and 3) the Contextual Distribution Mining (CDM) module, which utilizes a Brownian Distance Covariance matrix to model the spatial-channel distribution between support and query samples, preserving the fine-grained integrity of the target. Experimental results on the PASCAL-$5^{i}$and COCO-$20^{i}$datasets demonstrate that CCFormer achieves state-of-the-art performance, with visualizations further validating its effectiveness. Our code is available at github.com/lourise/ccformer.

Digital images in real world applications typically undergo a wide variety of quality degradations before compression or re-compression. Existing learning based codecs are typically data-driven, relying on the predefined compression pipeline with pristine or high quality images as the input. However, the images in the wild may exhibit the substantially different characteristics compared to the high quality images, casting major challenges to the learning based image coding. In this paper, we propose a robust noisy image compression framework with the blind assumption on the specific noise type and level. The specifically designed encoder decomposes the representation of visual content into two types of features, including the Features that represent the Intrinsic Content (FIC) and the Features that account for Additive Degradation (FAD). As such, beyond the philosophy of faithfully reconstructing the given image with high fidelity, only FIC needs to be compactly represented and conveyed. The principled disentanglement strategy facilitates the removal of the redundancy from multiple perspectives (e.g., spatial, channel and content), ensuring the handling of a wide variety of noisy images in the wild. Extensive experimental results show that our model can achieve superior performance in terms of the ultimate quality and exhibit the strong generalizability across images degraded by a variety of means. The proposed scheme also points out a new research avenue on learning based compression for images in the wild, which is technically challenging but desirable in practice.

The family of regularization by denoising (RED) methods introduce denoising operator as the regularization term to perform compressed sensing (CS) reconstruction, which shows higher flexibility and scalability. However, traditional RED framework has strict requirements on several properties of denoiser, making it hard to design the specific denoiser and limits the quality of reconstructed images. Although some relaxation for denoisers can be made by incorporating the fixed point projection during the iteration process, the involved parameters have great impact on the effectiveness and efficiency of the algorithm, which is non-trivial to set them properly. In this paper, we propose an innovative Deep Unfolding Network framework termed FP-DUN based on the iterative process of Regularization by Denoising via Fixed-Point Projection (RED-PRO). In FP-DUN, fix-point projection module is implemented with learnable weights of neural networks, where an effective denoiser based on dual attention mechanism (DAM) is developed to capture the details of the reconstructed image. Additionally, we propose a new loss function based on fixed point constraints, which is able to overcome the over-smoothness caused by multi-stage denoising and maintain the structural details to progressively improve the reconstruction quality. By training the DUN model, the parameters for the process of fix point projection and denoiser are learned automatically. Extensive experimental results comparing with state-of-the-art CS algorithms and traditional RED-PRO approach validate the effectiveness of FP-DUN, especially on some images with complex details.

The self-expressive coefficient plays a crucial role in the self-expressiveness-based subspace clustering method. To enhance the precision of the self-expressive coefficient, we propose a novel deep subspace clustering method, named grouping belief-based deep contrastive subspace clustering (GRESS), which integrates the clustering information and higher-order relationship into the coefficient matrix. Specifically, we develop a deep contrastive subspace clustering module to enhance the learning of both self-expressive coefficients and cluster representations simultaneously. This approach enables the derivation of relatively noiseless self-expressive similarities and cluster-based similarities. To enable interaction between these two types of similarities, we propose a unique grouping belief-based affinity refinement module. This module leverages grouping belief to uncover the higher-order relationships within the similarity matrix, and integrates the well-designed noisy similarity suppression and similarity increment regularization to eliminate redundant connections while complete absent information. Extensive experimental results on four benchmark datasets validate the superiority of our proposed method GRESS over several state-of-the-art methods.

Electroencephalography (EEG) is widely utilized for train driver state detection due to its high accuracy and low latency. However, existing methods for driver status detection rarely use the rich physiological information in EEG to improve detection performance. Moreover, there is currently a lack of EEG datasets for abnormal states of train drivers. To address these gaps, we propose a novel transfer learning model based on a hybrid attention mechanism, named hybrid attention-based transfer learning network (HATNet). We first segment the EEG signals into patches and utilize the hybrid attention module to capture local and global temporal patterns. Then, a channel-wise attention module is introduced to establish spatial representations among EEG channels. Finally, during the training process, we employ a calibration-based transfer learning strategy, which allows for adaptation to the EEG data distribution of new subjects using minimal data. To validate the effectiveness of our proposed model, we conduct a multistimulus oddball experiment to establish a EEG dataset of abnormal states for train drivers. Experimental results on this dataset indicate that: 1) Compared to the state-of-the-art end-to-end models, HATNet achieves the highest classification accuracy in both subject-dependent and subject-independent tasks at 94.26% and 87.03%, respectively, and 2) The proposed hybrid attention module effectively captures the temporal semantic information of EEG data.

Feature selection (FS) is a significant research topic in machine learning and artificial intelligence, but it becomes complicated in the high dimensional search space due to the vast number of features. Evolutionary computation (EC) has been widely used in solving FS by modeling it as an expensive wrapper-form optimization task, where a classifier is used to obtain classification accuracy for fitness evaluation (FE). In this article, we propose that the FS problem can be also modeled as a cheap filter-form optimization task, where the FE is based on the relevance and redundancy of the selected features. The wrapper-form optimization task is beneficial for classification accuracy while the filter-form optimization task has the strength of a lighter computational cost. Therefore, different from existing multitask-based FS that uses various wrapper-form optimization tasks, this article uses a multiform optimization technique to model the FS problem as a wrapper-form optimization task and a filter-form optimization task simultaneously. An evolutionary multitask FS (EMTFS) algorithm for parallel tacking these two tasks is proposed followed by, in which a two-channel knowledge transfer strategy is proposed to transfer positive knowledge across the two tasks. Experiments on widely used public datasets show that EMTFS can select as few features as possible on the premise of superior classification accuracy than the compared state-of-the-art FS algorithms.

As a challenging research topic in evolutionary multitask optimization (EMTO), evolutionary many-task optimization (EMaTO) aims at solving more than three tasks simultaneously. The design of the EMaTO algorithm generally needs to consider two major open issues, which are how to obtain useful knowledge from similar source tasks and how to effectively transfer knowledge to the target task. In this paper, we discover that knowledge structure plays a significant role in dealing with these two issues and propose a novel knowledge structure preserving-based evolutionary algorithm (KSP-EA) to efficiently solve many-task optimization problems. KSP-EA aims to achieve two goals, which are firstly to obtain useful structure-preserved knowledge from similar source tasks and secondly to effectively transfer both direct and indirect knowledge to the target task. To achieve the first goal, we propose a local-structure-preserved knowledge acquisition strategy that projects the knowledge of similar source tasks into a unified subspace without loss of the knowledge structure, thus enhancing the quality of the obtained knowledge. To achieve the second goal, we propose a tree-based knowledge propagation strategy that constructs a knowledge propagating tree to connect all the tasks and propagates knowledge along the edges of this tree. This way, the target task can obtain both direct and indirect knowledge, improving the effectiveness of knowledge transfer. We conduct extensive experiments on CEC19 and WCCI22 many-task optimization test suites and a real-world application scenario to evaluate the performance of KSP-EA. The experimental results show that our KSP-EA generally outperforms state-of-the-art algorithms.

Knowledge transfer (KT) has been regarded as an efficient method in evolutionary multitask optimization (EMTO) by utilizing the information of other tasks to promote the optimization of the current task. Most KT methods achieve information communication across index-aligned dimensions. However, the index-aligned dimensions are not always similar or related, which is not always suitable for communication and causes the low efficiency in KT. Moreover, when the KT occurs in the heterogeneous tasks with different dimensions, the task with lower dimensions often pads the extra dimensions to make their dimensions equal. However, the dimension-padding often involves the redundant or useless information, which may mislead the KT process. In this article, a novel multilevel and multisegment learning multitask optimization (MMLMTO) algorithm based on niching technique is proposed to achieve high-quality KT. First, a multilevel learning strategy is proposed to divide the population into three levels according to fitness values for better selecting the individuals for KT. Second, a multisegment learning strategy is proposed to split some top individuals in each level into several segments, and each segment will find its closest segment to form a niche, where the KT is executed. This ensures that KT occurs in the similar or related dimensions and avoids the dimension-padding to eliminate the influence of the redundant information. Experimental results on IEEE CEC2017 and IEEE CEC2022 multitask benchmarks fully demonstrate the effectiveness of MMLMTO, which can significantly outperform other state-of-the-art multitask algorithms. Finally, MMLMTO is applied to a real-world multitask rover navigation application problem to further demonstrate its applicability.

Flocking control, as an essential approach for survivable navigation of multirobot systems, has been widely applied in fields, such as logistics, service delivery, and search and rescue. However, realistic environments are typically complex, dynamic, and even aggressive, posing considerable threats to the safety of flocking robots. In this article, based on deep reinforcement learning, anAsymmetricSelf-play-empoweredFlockingControl framework is proposed to address this concern. Specifically, the flocking robots are trained concurrently with learnable adversarial interferers to stimulate the intelligence of the flocking strategy. A two-stage self-play training paradigm is developed to improve the robustness and generalization of the model. Furthermore, an auxiliary training module regarding the learning of transition dynamics is designed, dramatically enhancing the adaptability to environmental uncertainties. Feature-level and agent-level attention are implemented for action and value generation, respectively. Both extensive comparative experiments and real-world deployment demonstrate the superiority and practicality of the proposed framework.

Multirobot flocking is crucial for safe and cooperative navigation, with wide applications in logistics, service delivery, and mobile surveillance. Despite significant progress, developing effective flocking strategies under complex conditions remains challenging. Communication is a vital technique for multirobot coordination. In this article, we propose refinement and enhancement of communication information (REIN), a novel deep reinforcement learning-based framework designed to improve communication effectiveness in leader–follower flocking systems through the REIN. First, regarding information refinement, a graph-based information refiner, integrating directed graph-structured communication with an innovative edge filter, is developed for selective multirobot interaction. It helps robots adaptively focus on relevant neighbors, considerably alleviating information overload. Second, for information enhancement, a cognition-aligned information enhancer is designed that boosts information expressiveness by encouraging team consensus. It utilizes two cascaded leader-related objectives to optimize information towards cognitive alignment among decentralized followers. Extensive comparisons with state-of-the-art approaches and ablation versions demonstrate the superiority of our framework. Physical experiments are also conducted to validate its practicality.

Stereo Image Super-Resolution (SSR) holds great promise in improving the quality of stereo images by exploiting the complementary information between left and right views. Most SSR methods primarily focus on the inter-view correspondences in low-resolution (LR) space. The potential of referencing a high-quality SR image of one view benefits the SR for the other is often overlooked, while those with abundant textures contribute to accurate correspondences. Therefore, we propose Reference-based Iterative Interaction (RIISSR), which utilizes reference-based iterative pixel-wise and patch-wise matching, dubbed $P^{2}$ -Matching, to establish cross-view and cross-resolution correspondences for SSR. Specifically, we first design the information perception block (IPB) cascaded in parallel to extract hierarchical contextualized features for different views. Pixel-wise matching is embedded between two parallel IPBs to exploit cross-view interaction in LR space. Iterative patch-wise matching is then executed by utilizing the SR stereo pair as another mutual reference, capitalizing on the cross-scale patch recurrence property to learn high-resolution (HR) correspondences for SSR performance. Moreover, we introduce the supervised side-out modulator (SSOM) to re-weight local intra-view features and produce intermediate SR images, which seamlessly bridge two matching mechanisms. Experimental results demonstrate the superiority of RIISSR against existing state-of-the-art methods.

Point cloud compression significantly reduces data volume but sacrifices reconstruction quality, highlighting the need for advanced quality enhancement techniques. Most existing approaches focus primarily on point-to-point fidelity, often neglecting the importance of perceptual quality as interpreted by the human visual system. To address this issue, we propose a generative adversarial network for point cloud quality enhancement (PCE-GAN), grounded in optimal transport theory, with the goal of simultaneously optimizing both data fidelity and perceptual quality. The generator consists of a local feature extraction (LFE) unit, a global spatial correlation (GSC) unit and a feature squeeze unit. The LFE unit uses dynamic graph construction and a graph attention mechanism to efficiently extract local features, placing greater emphasis on points with severe distortion. The GSC unit uses the geometry information of neighboring patches to construct an extended local neighborhood and introduces a transformer-style structure to capture long-range global correlations. The discriminator computes the deviation between the probability distributions of the enhanced point cloud and the original point cloud, guiding the generator to achieve high quality reconstruction. Experimental results show that the proposed method achieves state-of-the-art performance. Specifically, when applying PCE-GAN to the latest geometry-based point cloud compression (G-PCC) test model, it achieves an average BD-rate of -19.2% compared with the PredLift coding configuration and -18.3% compared with the RAHT coding configuration. Subjective comparisons show a significant improvement in texture clarity and color transitions, revealing finer details and more natural color gradients.

Robust analysis of 3D point cloud data is essential for high-precision applications such as autonomous driving and industrial automation, where models need to consistently perform under complex and unpredictable real-world conditions. Current strategies, including data augmentation techniques and robust network designs, often struggle to effectively capture dynamic disturbances or accommodate the spatial variations of point clouds, thus lacking the required flexibility across diverse environments. To overcome these limitations, we propose a novel methodology to improve the robustness of 3D point cloud processing systems. Our approach simulates generalized corrupted input samples during training, using Radial Basis Functions (RBF) to model smooth deformations based on the control points. These deformations are applied selectively to different regions of the point cloud, adapting to spatial heterogeneity based on local density and geometric complexity. While generating these samples, we employ a combined adversarial loss that simultaneously induces model errors and maximizes the difference in internal feature distributions between the original and perturbed data. Additionally, we introduce a sub-network for distortion-guided feature augmentation to enhance important features while suppressing unreliable ones. This sub-network estimates distortion levels by compressing features and identifying discrepancies, then adjusts feature extraction process accordingly. Experimental results demonstrate that our method outperforms existing approaches on both Computer-Aided Design (CAD) models and real-world LiDAR datasets, enhancing model resilience and accuracy in handling diverse 3D scenarios.

Artifact remains a long-standing challenge in High Dynamic Range (HDR) reconstruction. Existing methods focus on model designs for artifact mitigation but ignore explicit detection and suppression strategies. Because artifact lacks clear boundaries, distinct shapes, and semantic consistency, and there is no existing dedicated dataset for HDR artifact, progress in direct artifact detection and recovery is impeded. To bridge the gap, we propose a unified HDR reconstruction framework that integrates artifact detection and model optimization. Firstly, we build the first HDR artifact dataset (HADataset), comprising 1,213 diverse multi-exposure Low Dynamic Range (LDR) image sets and 1,765 HDR image pairs with per-pixel artifact annotations. Secondly, we develop an effective HDR artifact detector (HADetector), a robust artifact detection model capable of accurately localizing HDR reconstruction artifact. HADetector plays two pivotal roles: (1) enhancing existing HDR reconstruction models through fine-tuning, and (2) serving as a non-reference image quality assessment (NR-IQA) metric, the Artifact Score (AS), which aligns closely with human visual perception for reliable quality evaluation. Extensive experiments validate the effectiveness and generalizability of our framework, including the HADataset, HADetector, fine-tuning paradigm, and AS metric. The code and datasets are available at: https://github.com/xinyueliii/hdr-artifact-detect-optimize.

We propose an end-to-end attribute compression method for dense point clouds. The proposed method combines a frequency sampling module, an adaptive scale feature extraction module with geometry assistance, and a global hyperprior entropy model. The frequency sampling module uses a Hamming window and the Fast Fourier Transform to extract high-frequency components of the point cloud. The difference between the original point cloud and the sampled point cloud is divided into multiple sub-point clouds. These sub-point clouds are then partitioned using an octree, providing a structured input for feature extraction. The feature extraction module integrates adaptive convolutional layers and uses offset-attention to capture both local and global features. Then, a geometry-assisted attribute feature refinement module is used to refine the extracted attribute features. Finally, a global hyperprior model is introduced for entropy encoding. This model propagates hyperprior parameters from the deepest (base) layer to the other layers, further enhancing the encoding efficiency. At the decoder, a mirrored network is used to progressively restore features and reconstruct the color attribute through transposed convolutional layers. The proposed method encodes base layer information at a low bitrate and progressively adds enhancement layer information to improve reconstruction accuracy. Compared to the best anchor of the latest geometry-based point cloud compression (G-PCC) standard that was proposed by the Moving Picture Experts Group (MPEG), the proposed method can achieve an average Bjøntegaard delta bitrate of -24.58% for the Y component (resp. -21.23% for YUV components) on the MPEG Category Solid dataset and -22.48% for the Y component (resp. -17.19% for YUV components) on the MPEG Category Dense dataset. This is the first instance that a learning-based attribute codec outperforms the G-PCC standard on these datasets by following the common test conditions specified by MPEG. Our source code will be made publicly available on https://github.com/sduxlmao/SPAC.

Major efforts in data-driven image super-resolution (SR) primarily focus on expanding the receptive field of the model to better capture contextual information. However, these methods are typically implemented by stacking deeper networks or leveraging transformer-based attention mechanisms, which consequently increases model complexity. In contrast, model-driven methods based on the unfolding paradigm show promise in improving performance while effectively maintaining model compactness through sophisticated module design. Based on these insights, we propose a Structural Similarity-Inspired Unfolding (SSIU) method for efficient image SR. This method is designed through unfolding an SR optimization function constrained by structural similarity, aiming to combine the strengths of both data-driven and model-driven approaches. Our model operates progressively following the unfolding paradigm. Each iteration consists of multiple Mixed-Scale Gating Modules (MSGM) and an Efficient Sparse Attention Module (ESAM). The former implements comprehensive constraints on features, including a structural similarity constraint, while the latter aims to achieve sparse activation. In addition, we design a Mixture-of-Experts-based Feature Selector (MoE-FS) that fully utilizes multi-level feature information by combining features from different steps. Extensive experiments validate the efficacy and efficiency of our unfolding-inspired network. Our model outperforms current state-of-the-art models, boasting lower parameter counts and reduced memory consumption. Our code will be available at: https://github.com/eezkni/SSIU.

High Dynamic Range (HDR) images present unique challenges for Learned Image Compression (LIC) due to their complex domain distribution compared to Low Dynamic Range (LDR) images. In coding practice, HDR-oriented LIC typically adopts preprocessing steps (e.g., perceptual quantization and tone mapping operation) to align the distributions between LDR and HDR images, which inevitably comes at the expense of perceptual quality. To address this challenge, we rethink the HDR imaging process which involves fusing multiple exposure LDR images to create an HDR image and propose a novel HDR image compression paradigm, Unifying Imaging and Compression (HDR-UIC). The key innovation lies in establishing a seamless pipeline from image capture to delivery and enabling end-to-end training and optimization. Specifically, a Mixture-ATtention (MAT)-based compression backbone merges LDR features while simultaneously generating a compact representation. Meanwhile, the Reference-guided Misalignment-aware feature Enhancement (RME) module mitigates ghosting artifacts caused by misalignment in the LDR branches, maintaining fidelity without introducing additional information. Furthermore, we introduce an Appearance Redundancy Removal (ARR) module to optimize coding resource allocation among LDR features, thereby enhancing the final HDR compression performance. Extensive experimental results demonstrate the efficacy of our approach, showing significant improvements over existing state-of-the-art HDR compression schemes. Our code is available at: https://github.com/plf1999/HDR-UIC.

In this paper, we address the challenge of significant memory consumption and redundant components in large-scale voxel-based model, which are commonly encountered in real-world 3D reconstruction scenarios. We propose a novel method called Shell-guided compression of Voxel Radiance Fields (SVRF), aimed at optimizing voxel-based model into a shell-like structure to reduce storage costs while maintaining rendering accuracy. Specifically, we first introduce a Shell-like Constraint, operating in two main aspects: 1) enhancing the influence of voxels neighboring the surface in determining the rendering outcomes, and 2) expediting the elimination of redundant voxels both inside and outside the surface. Additionally, we introduce an Adaptive Thresholds to ensure appropriate pruning criteria for different scenes. To prevent the erroneous removal of essential object parts, we further employ a Dynamic Pruning Strategy to conduct smooth and precise model pruning during training. The compression method we propose does not necessitate the use of additional labels. It merely requires the guidance of self-supervised learning based on predicted depth. Furthermore, it can be seamlessly integrated into any voxel-grid-based method. Extensive experimental results demonstrate that our method achieves comparable rendering quality while compressing the original number of voxel grids by more than 70%. Our code will be available at: https://github.com/eezkni/SVRF.

Uncrewed aerial vehicles (UAVs) are increasingly employed for data collection in wireless sensor networks (WSNs) owing to their flexibility and real-time operational capabilities. However, effective UAV path planning remains a critical research challenge, requiring the design of optimal routes to efficiently complete data collection in WSNs. This paper introduces a novel constrained UAV data collection model tailored to address real-world challenges in this domain. Traditional mathematical optimization methods often face significant difficulties in derivation and computational complexity. Similarly, classical evolutionary computation (EC) algorithms are limited by their dependence on serial computations, resulting in substantial time costs. To address these issues, we propose a matrix-based differential evolution algorithm (MDE), leveraging matrix index operations to facilitate parallel computation and solve the problem efficiently. Given that existing matrix-based evolutionary computation (MEC) algorithms have limited applications in constrained optimization problems, we further introduce a constraint-guided optimization (CGO) method, enabling the MDE algorithm to inherently support constrained optimization. Experimental results demonstrate that the proposed MDE-CGO outperforms other representative EC methods in optimizing the model of constrained UAV data collection from WSNs. Only our proposed approach successfully optimizes the model to generate feasible UAV paths in all the experiments. Moreover, a computational speed comparison highlights that the MDE-CGO not only delivers superior optimization performance but also achieves high computational efficiency.

Collaborative perception has recently gained significant attention in autonomous driving, improving perception quality by enabling the exchange of additional information among vehicles. However, deploying collaborative perception systems can lead to domain shifts due to diverse environmental conditions and data heterogeneity among connected and autonomous vehicles (CAVs). To address these challenges, we propose a unified domain generalization framework to be utilized during the training and inference stages of collaborative perception. In the training phase, we introduce an Amplitude Augmentation (AmpAug) method to augment low-frequency image variations, broadening the model’s ability to learn across multiple domains. We also employ a meta-consistency training scheme to simulate domain shifts, optimizing the model with a carefully designed consistency loss to acquire domain-invariant representations. In the inference phase, we introduce an intra-system domain alignment mechanism to reduce or potentially eliminate the domain discrepancy among CAVs prior to inference. Extensive experiments substantiate the effectiveness of our method in comparison with the existing state-of-the-art works.

Ramp merging is one of the bottlenecks in traffic systems, which commonly cause traffic congestion, accidents, and severe carbon emissions. In order to address this essential issue and enhance the safety and efficiency of connected and autonomous vehicles (CAVs) at multi-lane merging zones, we propose a novel collaborative decision-making framework, namedAgentsCoMerge, to leverage large language models (LLMs). Specifically, we first design a scene observation and understanding module to allow an agent to capture the traffic environment. Then we propose a hierarchical planning module to enable the agent to make decisions and plan trajectories based on the observation and the agent's own state. In addition, in order to facilitate collaboration among multiple agents, we introduce a communication module to enable the surrounding agents to exchange necessary information and coordinate their actions. Finally, we develop a reinforcement reflection guided training paradigm to further enhance the decision-making capability of the framework. Extensive experiments are conducted to evaluate the performance of our proposed method, demonstrating its superior efficiency and effectiveness for multi-agent collaborative decision-making under various ramp merging scenarios.

When transmission medium and compression degradation are intertwined, new challenges emerge. This study addresses the problem of raindrop removal from compressed images, where raindrops obscure large areas of the background and compression leads to the loss of high-frequency (HF) information. The restoration of the former requires global contextual information, while the latter necessitates guidance for high-frequency details, resulting in a conflict in utilizing these two types of information when designing existing methods. To address this issue, we propose a novel transformer architecture that leverages the advantages of attention mechanism and HF-friendly design to effectively restore the compressed raindrop images at the framework, component, and module levels. Specifically, at the framework level, we integrate relative position multi-head self-attention and convolutional layers into the proposed low-high-frequency transformer (LHFT), where the former captures global contextual information and the latter focuses on high-frequency information. Their combination effectively resolves the issue of mixed degradation. At the component level, we utilize high-frequency depth-wise convolution (HFDC) with zero-mean kernels to improve the capability to extract high-frequency features, drawing inspiration from typical high-frequency filters like Prewitt and Sobel operators. Finally, at the module level, we introduce a low-high-attention module (LHAM) to adaptively allocate the importance of low and high frequencies along channels for effective fusion. We establish the JPEG-compressed raindrop image dataset and conduct extensive experiments on different compression rates. Experimental results demonstrate that the proposed method outperforms state-of-the-art methods without increasing computational costs.

Chroma intra prediction aims to reduce chroma redundancies within a frame, which plays an important role in improving the coding efficiency of intra coding. Existing chroma intra prediction methods typically utilize the spatial relationship between the current luma block and its neighboring reference luma blocks to predict its chroma samples. However, the spatial properties of luma components differ from those of chroma components, which limits the accuracy of chroma intra prediction. To tackle this issue, an efficient Exemplar Colorization Network (ECNet)-based chroma intra prediction method is proposed in this paper, in which the colorization relationship between reference luma and chroma components is exploited to predict the chroma components for the current luma component. Inspired by the principle that semantic information in an image exhibits short-range continuity, a Spatial-consistency-based Colorization Transfer Network (SCTNet) is proposed, which builds and transfers colorization representations of neighboring reference blocks for chroma prediction. To improve the chroma prediction capability of SCTNet, a colorization learning module is developed to learn the robust mapping relationship from the luma component to the chroma component in a region-to-pixel manner, and a weight-adaptive reconstruction module is designed to adaptively utilize reference information from neighboring blocks to generate an initial prediction result. In addition, to further improve the accuracy of chroma intra prediction, a multi-reference-based chroma refinement network is proposed, which simultaneously uses the spatial information of neighboring reference chroma blocks and the current luma block to eliminate blocking and color-bleeding artifacts in the initial prediction result. Experimental results demonstrate that our proposed ECNet outperforms the state-of-the-art chroma intra prediction methods in terms of coding performance.

Theperception-distortion- tradeoffreveals the limitation of current low-level deep learning paradigms,i.e., minimizing reconstruction distortion does not guarantee improved perceptual quality. Acknowledging the lack of a reliableperception-oriented optimization function, we are motivated to explore a flexible approach for enhancing perceptual quality by steering thetradeoffto prioritizeperception. To this end, we reconsider theperception-distortionfunction by incorporating the Just-Noticeable-Distortion (JND) mechanism. We mathematically demonstrate that in the common image restoration process, altering the optimization target from natural images to distorted images—where the distortion intensity is constrained by the JND threshold and the distortion type aligns with that arising from the restorer itself—effectively obtained improvedperceptionindices without any changes to the restorer or optimization function. Accordingly, to facilitate various low-level learning models, we are motivated to construct the first large-scale CNN-oriented JND image dataset. Our dataset comprises 500 natural images and 4,500 degraded versions generated by a series of autoencoders, as well as the actual JND judgment results collected through rigorous subjective testing from twenty volunteers. Finally, a learning-based JND inference model is established on the proposed dataset and employed in the proposed JND-based adaptation scheme, where the inferred JND images serve as pseudo-ground truth for the training or fine-tuning processes of low-level vision models. Extensive experiments on image super-resolution and end-to-end image compression across multiple models have shown encouraging improvements in perceptual quality, demonstrating the effectiveness of the proposed scheme. Our dataset is available at:https://github.com/ohq17/CNN-Oriented-JND-Dataset.

Action Quality Assessment (AQA) aims to evaluate and score human actions in videos accurately. Existing approaches involve extracting features from the input video and implementing regression based on those features. However, representations derived from a single branch often lack the necessary diversity and flexibility to capture the complexity of human actions effectively. This work addresses these limitations by introducing a multi-branch architecture designed to capture a broad spectrum of video dynamics at varying levels of granularity. Specifically, we enhance video representation in the flow-guided branch by integrating optical flow with video features. This combination of multimodal features offers a more comprehensive context of global motion. Meanwhile, the moment-focused branch is tailored to extract frame-specific features, constructing two distinct quality-based representations with different focuses on moments, which achieves adaptive clues aggregation. Furthermore, the detail-aware branch leverages multiscale deep embeddings from a hierarchy convolutional neural network to capture fine-grained spatial information, which is useful when objects have complex spatial changes. Finally, a post-fusion strategy is employed to merge outputs from all branches, contributing to the comprehensive action quality assessment. Experimental evaluations on three benchmark datasets, FineDiving, MTL-AQA, and AQA-7, demonstrate the superiority of our model in providing reliable assessments of action quality.

Image set compression (ISC) refers to compressing the sets of semantically similar images. Traditional ISC methods typically aim to eliminate redundancy among images at either signal or frequency domain, but often struggle to handle complex geometric deformations across different images effectively. Here, we propose a new Hybrid Neural Representation for ISC (HNR-ISC), including an implicit neural representation for Semantically Common content Compression (SCC) and an explicit neural representation for Semantically Unique content Compression (SUC). Specifically, SCC enables the conversion of semantically common contents into a small-and-sweet neural representation, along with embeddings that can be conveyed as a bitstream. SUC is composed of invertible modules for removing intra-image redundancies. The feature level combination from SCC and SUC naturally forms the final image set. Experimental results demonstrate the robustness and generalization capability of HNR-ISC in terms of signal and perceptual quality for reconstruction and accuracy for the downstream analysis task.

DeepFake, an AI technology that can automatically synthesize facial forgeries, has recently attracted worldwide attention. While DeepFakes can be entertaining, they can also be used to spread falsified information or be weaponized as cognition warfare. Forensic researchers have been dedicated to designing defensive algorithms to combat such disinformation. However, attacking technologies have been developed to make DeepFake products more aggressive. For example, by launching anti-forensics and adversarial attacks, DeepFakes can be disguised as authentic media to evade forensic detectors. However, such manipulations often sacrifice image quality for satisfactory undetectability. To address this issue, we propose a method to generate a novel adversarial sharpening mask for launching black-box anti-forensics attacks. Unlike many existing methods, our approach injects perturbations that allow DeepFakes to achieve high anti-forensics performance while maintaining pleasant sharpening visual effects. Experimental evaluations demonstrate that our method successfully disrupts state-of-the-art DeepFake detectors. Moreover, compared to images processed by existing DeepFake anti-forensics methods, our method’s quality of anti-forensics DeepFakes rendered is significantly improved. Our code is available at https://github.com/fb-reps/HQ-AF_GAN .

Reconstructing high dynamic range (HDR) images from standard dynamic range (SDR) ones has received growing attention in recent years. A predominant problem of this task lies in the absence of texture and structural information in under/over-exposed regions. In this article, we propose an efficient and stable single-image HDR reconstruction method, namely exposure-induced network (EIN). More specifically, a dynamic range expansion branch (DB) is designed to expand the global dynamic range of the input SDR image. Moreover, two exposure-gated detail recovering branches for local over- (OB) and under- (UB) exposed regions are proposed to interact with the DB to progressively infer the texture and structural details with the learned confidence maps to resolve challenging ambiguities in such regions. The features from these three interactional branches are adaptively fused in the joint global–local decoder to reconstruct the final HDR image. The proposed network is trained based upon a large-scale dataset constructed with diverse content. Extensive experimental results demonstrate that the proposed model achieves consistent visual quality improvement for input SDR images with different exposures compared with state-of-the-art methods. The source code is available at: https://github.com/Yliu724/EIN .

Crowdsourcing contests have become an important method for individuals and organizations to solve complex problems by obtaining innovative solutions from external participants. As the number of participants continues to grow, the likelihood of undesirable outcomes increases, posing a great requirement for effective community detection algorithms. To provide platform owners with actionable and timely management strategies, this article proposes a multimodule-based dynamic community detection (MDCD) algorithm to facilitate the achievement of efficient, high-quality, and sustainable innovation. The MDCD algorithm uses a multimodule task learning framework containing four different modules, including heterogeneous temporal aggregation (HTA), representation reconstruction (RR), link prediction (LP), and node clustering (NC) modules, to gradually detect the community structure accurately. First, the HTA module obtains the initial node representation by capturing both spatial heterogeneity and temporal dependencies. Second, the RR module considers reconstructed topology and node attribute information to update the node representation via an encoder–decoder collaboration mechanism. Third, the LP module further optimizes the node representation by exploiting the predicted graph links, which helps increase the accuracy of community detection. Finally, the NC module leverages two metric learning methods to optimize a learnable clustering process based on the predicted node presentations, which helps platform owners achieve comprehensive results across multiple dimensions of innovation performance. The experimental results from real-world crowdsourcing platforms indicate that MDCD shows effectiveness in simultaneously improving the multidimensional innovation performance of crowdsourcing platforms and increasing solver engagement.

Neural Radiance Fields (NeRF) have demonstrated impressive potential in synthesizing novel views from dense input, however, their effectiveness is challenged when dealing with sparse input. Existing approaches that incorporate additional depth or semantic supervision can alleviate this issue to an extent. However, the process of supervision collection is not only costly but also potentially inaccurate. In our work, we introduce a novel model: the Collaborative Neural Radiance Fields (ColNeRF) designed to work with sparse input. The collaboration in ColNeRF includes the cooperation among sparse input source images and the cooperation among the output of the NeRF. Through this, we construct a novel collaborative module that aligns information from various views and meanwhile imposes self-supervised constraints to ensure multi-view consistency in both geometry and appearance. A Collaborative Cross-View Volume Integration module (CCVI) is proposed to capture complex occlusions and implicitly infer the spatial location of objects. Moreover, we introduce self-supervision of target rays projected in multiple directions to ensure geometric and color consistency in adjacent regions. Benefiting from the collaboration at the input and output ends, ColNeRF is capable of capturing richer and more generalized scene representation, thereby facilitating higher-quality results of the novel view synthesis. Our extensive experimental results demonstrate that ColNeRF outperforms state-of-the-art sparse input generalizable NeRF methods. Furthermore, our approach exhibits superiority in fine-tuning towards adapting to new scenes, achieving competitive performance compared to per-scene optimized NeRF-based methods while significantly reducing computational costs. Our code is available at: https://github.com/eezkni/ColNeRF.

Evolutionary transfer optimization (ETO), which combines evolutionary algorithms with knowledge transfer across related tasks to enhance search performance, has gained widespread attention from researchers in recent years. Multiform transfer optimization (MFTO) stands out as a representative transfer paradigm of ETO, aiming to exploit alternative formulations of the target task of interest. By leveraging useful knowledge acquired from alternative formulations to assist in solving the target task, MFTO has proven effective in tackling complex optimization problems, contributing to the growth of MFTO research. This paper provides a review of existing research progress in MFTO. Firstly, we introduce the fundamental aspects of MFTO, including the general framework and core components. Subsequently, we summarize the advances in MFTO from the perspectives of problems to be solved and the way of constructing alternative formulations. Lastly, we discuss promising future research directions. It is hoped that this survey can provide a thorough understanding of the MFTO framework and facilitate the development of more advanced MFTO algorithms and applications.

Modern fault diagnosis faces an imbalance issue at both the sample and feature levels. A common approach is to combine balancing strategies with feature selection algorithms to address this problem. However, this may result in feature subsets that cannot accurately represent the true data distribution. This paper proposes an imbalanced fault diagnosis method called RPLFS-MOBPSO, which combines region purity (RP) with local feature selection to achieve class balance implicitly by partitioning local regions. RP is used as a new objective in the optimization process to achieve accurate fault detection. The adaptive reference point method from Non-Dominated Sorting Genetic Algorithm III is employed to maintain a diverse and evenly distributed external archive. On both the simulated Tennessee Eastma (TE) benchmark datasets and the real bearing experimental bench datasets, the proposed method achieves the best results compared to two LFS methods and four imbalanced ensemble algorithms based on different balancing strategies. Our source codes are available at: https://github.com/EMRGSZU/papers-code/tree/main/RPLFS-MOBPSO.

Recently, gradient-based repair methods have been commonly introduced into constraint-handling techniques to handle linear and non-linear constraints. These gradient-based repair methods are only designed to reduce constraint violations, and they do not act on the objective function in the repairing process. Nevertheless, the gradient descent optimization method is originally proposed to optimize the objective function without constraints. Motivated by this consideration, this study develops an improved gradient-based repair method that incorporates the objective function to handle the constraints and optimize the objective function simultaneously. The proposed repair method is integrated into a multiobjective differential evolution framework to investigate its effectiveness. Experiments have been conducted on 57 real-world constrained benchmark test functions. The empirical result shows that, compared to the selected state-of-the-art algorithms, our proposed gradient-based repair method can assist the adopted constrained optimization approach to obtain high-quality feasible solutions.

Many real-world optimization problems are inherently constrained, presenting significant challenges to the application of evolutionary algorithms. Successfully managing these constraints while simultaneously optimizing the objective function requires a considerable degree of population diversity. To address this, we have developed a methodology that effectively combines an$\varepsilon$-constraint-handling method with a niching technique. The$\varepsilon$-constraint- handling method is specifically designed to manage constraints, while the niching technique aims to preserve pop-ulation diversity. In our approach, a constrained optimization problem is transformed into a tri-objective optimization challenge, introducing two additional objectives: the density objective and the overall constraint objective. The density objective is a particularly innovative aspect of our method, as it prolongs the survival of promising yet infeasible solutions. This prolongation aids the evolutionary search in converging towards the feasible region from various directions, thereby increasing the chances of identifying optimal solutions. Moreover, an improved gradient repair mutation strategy, based on a successful information reuse approach, is implemented to further refine promising solutions. To evaluate the effectiveness of our method, we tested it on 30 real-world constrained optimization problems from the CEC 2020 benchmark test suite. The results demonstrate that our approach either exceeds or is equivalent to the performance of current state-of-the-art constrained optimization algorithms.

Face Image Quality Assessment (FIQA) is pivotal for guaranteeing the accuracy of face recognition in unconstrained environments. Recent progress in deep quality-fitting-based methods that train models to align with quality anchors, has shown promise in FIQA. However, these methods heavily depend on a recognition model to yield quality anchors and indiscriminately treat the confidence of inaccurate anchors as equivalent to that of accurate ones during the FIQA model training, leading to a fitting bottleneck issue. This paper seeks a solution by putting forward the Confidence-Calibrated Face Image Quality Assessment (CLIB-FIQA) approach, underpinned by the synergistic interplay between the quality anchors and objective quality factors such as blur, pose, expression, occlusion, and illumination. Specifically, we devise a joint learning framework built upon the vision-language alignment model, which leverages the joint distribution with multiple quality factors to facilitate the quality fitting of the FIQA model. Furthermore, to alleviate the issue of the model placing excessive trust in inaccurate quality anchors, we propose a confidence calibration method to correct the quality distribution by exploiting to the fullest extent of these objective quality factors characterized as the merged-factor distribution during training. Experimental results on eight datasets reveal the superior performance of the proposed method.

With the breakthrough of large models, Segment Anything Model (SAM) and its extensions have been attempted to apply in diverse tasks of computer vision. Underwater salient instance segmentation is a foundational and vital step for various underwater vision tasks, which often suffer from low segmentation accuracy due to the complex underwater circumstances and the adaptive ability of models. Moreover, the lack of large-scale datasets with pixel-level salient instance annotations has impeded the development of machine learning techniques in this field. To address these issues, we construct the first large-scale underwater salient instance segmentation dataset (USIS10K), which contains 10,632 underwater images with pixel-level annotations in 7 categories from various underwater scenes. Then, we propose an Underwater Salient Instance Segmentation architecture based on Segment Anything Model (USIS-SAM) specifically for the underwater domain. We devise an Underwater Adaptive Visual Transformer (UA-ViT) encoder to incorporate underwater domain visual prompts into the segmentation network. We further design an out-of-the-box underwater Salient Feature Prompter Generator (SFPG) to automatically generate salient prompters instead of explicitly providing foreground points or boxes as prompts in SAM. Comprehensive experimental results show that our USIS-SAM method can achieve superior performance on USIS10K datasets compared to the state-of-the-art methods. Datasets and codes are released on https://github.com/LiamLian0727/USIS10K.

Gaussian splatting, renowned for its exceptional rendering quality and efficiency, has emerged as a prominent technique in 3D scene representation. However, the substantial data volume of Gaussian splatting impedes its practical utility in real-world applications. Herein, we propose an efficient 3D scene representation, named Compressed Gaussian Splatting (CompGS), which harnesses compact Gaussian primitives for faithful 3D scene modeling with a remarkably reduced data size. To ensure the compactness of Gaussian primitives, we devise a hybrid primitive structure that captures predictive relationships between each other. Then, we exploit a small set of anchor primitives for prediction, allowing the majority of primitives to be encapsulated into highly compact residual forms. Moreover, we develop a rate-constrained optimization scheme to eliminate redundancies within such hybrid primitives, steering our CompGS towards an optimal trade-off between bitrate consumption and representation efficacy. Experimental results show that the proposed CompGS significantly outperforms existing methods, achieving superior compactness in 3D scene representation without compromising model accuracy and rendering quality. Our code will be released on GitHub for further research.

Assessing the quality of a player's performance, such as in diving events, requires precise measurement of subtle action details and overall fluidity. Existing methods primarily utilize appearance information from RGB frames, often neglecting crucial motion information that could contribute to a more comprehensive assessment. In response to this limitation, this paper introduces a novel Multi-Modality Network for Action Quality Assessment (AQA). The proposed method first employs a self-attention based module to foster interaction between optical flow and appearance clues, facilitating the extraction of discriminative features from each modality. Subsequently, a pairwise cross-attention mechanism is designed to comprehensively capture subtle differences via both intra-modality and inter-modality relationships between the query and exemplar video. Finally, to enhance the robustness and achieve accurate score prediction, an adaptive clip aggregation module is introduced to weigh the reliability of each patch based on multi-modal difference features. Experimental results on two benchmarks, FineDiving and MTL-AQA, validate the effectiveness of the proposed model.

In recent years, surrogate-assisted evolutionary algorithms have gained considerable success in addressing expensive constrained optimization problems. While significant focus has been directed toward optimization challenges with inequality constraints, the domain of expensive equality-constrained optimization also necessitates attention, as equality constraints are frequently encountered in traditional constrained optimization problems. Recognizing this gap, this study introduces an innovative approach that integrates a multilayer perceptron regression-based surrogate with a gradient descent-based repair method and differential evolution to address these challenges effectively. Our contributions are threefold: 1) We develop a multilayer perceptron-based surrogate model that concurrently approximates the objective function and equality constraints, 2) We employ a gradient descent-based repair method to adeptly manage the challenging equality constraints, and 3) We propose a hybrid local search scheme that enhances the solution refinement process. The combined use of the multilayer perceptron-based surrogate and gradient descent-based local search works in concert with differential evolution to guide the population toward the feasible region. This approach enables the evolutionary search, supported by the surrogate model, to extensively explore potential feasible regions. Our experimental results underscore the potential and efficacy of the proposed surrogate-assisted evolutionary algorithm in solving such complex optimization problems.

Ant colony system algorithm (ACS), as an important evolutionary computation (EC) algorithm, has demonstrated significant advantages in solving complex optimization problems. However, traditional EC algorithms and traditional ACS algorithm often face the challenge of slow computational speed when dealing with large-scale problems. In recent years, matrix-based EC approaches have been proposed to accelerate the computational speed, which has obtained promising results in dealing with large-scale problems. However, most existing matrix-based EC algorithms are designed for continuous optimization problems, while the matrix-based approach integrated with ACS has not attracted enough attention, which will be efficient for solving large-scale discrete optimization problems. Therefore, in this paper, we propose a matrix-based ACS (MACS) algorithm and apply it to solve the traveling salesman problem (TSP). MACS is an innovative improvement over the traditional ACS algorithm, utilizing matrix operations to parallelly let ants select city and update pheromone. Experimental results show that the MACS algorithm has significantly better efficiency in accelerating computational speed while maintaining the remarkable problem-solving ability in solving large-scale TSP.

The rapid growth of electric vehicles (EVs) has led to significant challenges in providing efficient and sustainable charging solutions. This paper addresses the battery swapping station (BSS) recommendation problem by proposing a novel conflict-free genetic algorithm (CFGA) integrated with a Nash equilibrium seeking (NES) approach to identify optimal Nash equilibrium (ONE) solutions to such a non-cooperative optimization problem. The CFGA employs specialized crossover and mutation operators to generate offspring that satisfy the constraints of the problem, ensuring that each EV decides a unique battery swap strategy without conflict. Firstly, an order crossover operator is proposed to preserve the order of genes in the chromosomes. Secondly, a replacement and exchange mutation operator is proposed to enhance mutation diversity. The resulting optimal solution is then used as the initial strategy for the NES, which iteratively converges to the ONE. The proposed CFGA with NES algorithm is evaluated under both small-scale and large-scale cases, demonstrating its effectiveness in achieving a balance between costs for EVs and utilization for BSSs. The study's findings have practical implications for the smart grid and EV integration, offering a robust method for optimizing EV infrastructure and operations.

The intra block copy (IBC) mode introduced can significantly improve the coding efficiency for screen content. However, with the mixed content, the coding performance improvement of IBC is limited and while also introducing the increases of the coding complexity. This paper proposes an early determination scheme for IBC prediction to reduce the encoding complexity over mixed content sequences containing captured content regions. Our method is based on a refined CTU-level screen content detection method, which can better distinguish screen content in mixed scenes. Experimental results show that the proposed method reduces encoding complexity with moderate coding performance loss on mixed content sequences.

Anomaly detection in the Industrial Internet of Things (IIoT) is a challenging task that relies heavily on the efficient learning of multivariate time series representations. We introduce Skip-patching and Spatial-Temporal discrepancy mechanisms to improve the efficiency of detecting anomalies. Traditional feature extraction is hindered by redundant information in limited datasets. The situation is that feature generation from stable operational processes results in low-quality representations. To address this challenge, we propose the Skip-Patching mechanism. This approach involves selectively extracting features from partial data patches, prompting the model to learn more meaningful knowledge through self-supervised learning. It also effectively doubles the training sample size by creating independent sub-groups of patches. Despite the complex spatial and temporal relationships in IIoT systems, existing methods mainly extracted features from a single domain, either temporal or spatial (sensor-wise), or simply cascaded two features, i.e., one after one, which limited anomaly detection capabilities. To address this, we introduce the Spatial-Temporal Association Discrepancy component, which leverages discrepancies between spatial and temporal features to enhance latent representation learning. Our Skip-Patching Spatial-Temporal Anomaly Detection (SSAD) framework combines these two components to provide a more diverse and comprehensive learning process. Tested across four multivariate time series anomaly detection benchmarks, SSAD demonstrates superior performance, confirming the efficacy of combining Skip-patching and Spatial-Temporal features to enhance anomaly detection in IIoT systems.

In this paper, we propose a Learning-based gEnome Codec (LEC), which is designed for high efficiency and enhanced flexibility. The LEC integrates several advanced technologies, including Group of Bases (GoB) compression, multi-stride coding and bidirectional prediction, all of which are aimed at optimizing the balance between coding complexity and performance in lossless compression. The model applied in our proposed codec is data-driven, based on deep neural networks to infer probabilities for each symbol, enabling fully parallel encoding and decoding with configured complexity for diverse applications. Based upon a set of configurations on compression ratios and inference speed, experimental results show that the proposed method is very efficient in terms of compression performance and provides improved flexibility in real-world applications.

Class-agnostic binary segmentation identifies objects that are similar or very different from the complex background, including salient object detection (SOD) and camouflage object detection (COD). Most existing models only focus on a specific type of foreground and background segmentation by employing the global modeling ability of transformers, without explicitly explaining or eliminating the discrepancy between these two different distributions. They also suffer from inefficient local feature learning and inadequate feature aggregation. To make binary segmentation research more accessible and trivially generalized, we introduce a novel unified uncertainty-aware paradigm, called uncertainty-aware feature reassembly (UAFer). Specifically, the Spatial Feature Reassembly (SFR) module is presented to formulate the uncertainty of binary segmentation map as the variance of generalized Bernoulli distribution and entropy from two perspectives. Our transformer-based model is then trained to prioritize regions of higher certainty, obtaining more confident and accurate predictions during the feature upsampling. Moreover, the Channel Feature Reassembly (CFR) with adjacent feature aggregation is designed to facilitate an iterative exploration of channel integrity. This iterative learning process enhances the interaction of neighboring channel features; thus, improving universal object information decoding efficiency. Extensive quantitative and qualitative evaluations demonstrate that our proposed UAFer consistently outperforms the state-of-the-art models across three challenging domains including SOD, COD, and polyp segmentation (POLYP). The implementation codes for our approach will be publicly available at https://github.com/zihaodong/UAFR.

The Versatile Video Coding (VVC) standard adopts a series of new coding tools in transform and quantization, including multiple transform selection, low-frequency non-separable transform, and trellis quantization. These new technologies, which bring significant coding gain, create daunting challenges to optimizing the VVC codec. In this work, we propose a new all-zero block (AZB) detection scheme tailored for VVC, with the collaboration of genuine all-zero block (GAZB) and pseudo all-zero block (PAZB) detection. First, to accommodate the multiple transform sizes in VVC, we develop a GAZB detection method that is apt for square and non-square residual blocks. Meanwhile, a theoretical upper bound is derived to locate the last significant coefficient and detect the potential frequency domain GAZB. Subsequently, a method tailored for trellis-coded quantization in VVC is devised for detecting PAZB. Finally, the GAZB and PAZB detection methods are collaboratively employed for AZB detection in VVC. The proposed method is implemented on the VVC codec Versatile Video Encoder (VVenC), and extensive experimental results show that the proposed method achieves promising time savings for test sequences of different resolutions with negligible rate-distortion performance loss.

Recent years have witnessed significant advancements in face image generation using generative adversarial networks (GANs), leading to a high demand for GAN-generated face image quality assessment (GFIQA). However, the intrinsic distortion caused by the generation brings a significant challenge for existing image quality assessment (IQA) models which are typically designed for natural images. In addition, the image distortion usually varies depending on different GAN models, resulting in a high generalization capability that a GFIQA model should possess. To account for this, we first establish a large GFIQA database by collecting various GFIs from existing popular GAN models. Subsequently, we further propose a causal representation learning (CRL) scheme for the generalized GFIQA model (CRL-GFIQA) with the assumption that the causal knowledge of human quality assessment is shareable in different scenarios. In particular, we disentangle the learned features into casual and non-causal components by an invertible neural network, facilitating the proposed CRL-GFIQA model with a high generalization on unseen domains. Extensive experimental results demonstrate the effectiveness of our CRL-GFIQA model. The codes and the constructed dataset will be publicly available.

Video coding is a video compression technique that compresses the original video sequence to produce a smaller archive file or reduce the transmission bandwidth under constraints on the visual quality loss. Rate control (RC) plays a critical role in video coding. It can achieve stable stream output in practical applications, especially real-time video applications such as video conferencing or game live streaming. Most RC algorithms either directly or indirectly characterise the relationship between the bit rate (R) and quantisation (Q) and then allocate bits to every coding unit so as to guarantee the global bit rate and video quality level. This paper comprehensively reviews the classic RC technologies used in international video standards of past generations, analyses the mathematical models and implementation mechanisms of various schemes, and compares the performance of recent state-of-the-art RC algorithms. Finally, we discuss future directions and new application areas for RC methods. We hope that this review can help support the development, implementation, and application of RC for new video coding standards.

The emergence of digital avatars has prompted an exponential increase in the demand for human point clouds with realistic and intricate details. The compression of such data becomes challenging due to massive amounts of data comprising millions of points. Herein, we leverage the human geometric prior in the geometry redundancy removal of point clouds to greatly promote compression performance. More specifically, the prior provides topological constraints as geometry initialization, allowing adaptive adjustments with a compact parameter set that can be represented with only a few bits. Therefore, we propose representing high-resolution human point clouds as a combination of a geometric prior and structural deviations. The prior is first derived with an aligned point cloud. Subsequently, the difference in features is compressed into a compact latent code. The proposed framework can operate in a plug-and-play fashion with existing learning-based point cloud compression methods. Extensive experimental results show that our approach significantly improves the compression performance without deteriorating the quality, demonstrating its promise in serving a variety of applications.

To further improve the performance of Versatile Video Coding (VVC), a neural network based multi-level in-loop filtering framework for luma and chroma is presented in this letter, which includes Reference pixel Level (RL), Coding tree unit Level (CL), and Frame Level (FL). The neural network based filters in these levels can be flexibly enabled. In RL, the coding performance upper bound is analyzed and asymmetric convolution is designed. In CL, the pixels located at the bottom and rightmost have been assigned greater weights for loss calculation during training. In addition, the co-located luma is adopted in CL and FL chroma filtering for guiding chroma enhancement due to the high correlation between them. For the architecture of neural network, two input channel fusion schemes are combined to enjoy both of their benefits. Extensive experimental results show that the proposed multi-level in-loop filtering method can achieve 6.87%, 32.8%, and 36.9% bit rate reductions on average for Y, U, and V components under all intra configuration, which outperforms the state-of-the-art works.

Salient instance segmentation (SIS) is an emerging field that evolves from salient object detection (SOD), aiming at identifying individual salient instances using segmentation maps. Inspired by the success of dynamic convolutions in segmentation tasks, this article introduces a keypoints-based SIS network (KepSalinst). It employs multiple keypoints, that is, the center and several peripheral points of an instance, as effective geometrical guidance for dynamic convolutions. The features at peripheral points can help roughly delineate the spatial extent of the instance and complement the information inside the central features. To fully exploit the complementary components within these features, we design a differentiated patterns fusion (DPF) module. This ensures that the resulting dynamic convolutional filters formed by these features are sufficiently comprehensive for precise segmentation. Furthermore, we introduce a high-level semantic guided saliency (HSGS) module. This module enhances the perception of saliency by predicting a map for the input image to estimate a saliency score for each segmented instance. On four SIS datasets (ILSO, SOC, SIS10K, and COME15K), our KepSalinst outperforms all previous models qualitatively and quantitatively.

Knowledge transfer (KT) is crucial for optimizing tasks in evolutionary multitask optimization (EMTO). However, most existing KT methods can only achieve superficial KT but lack the ability to deeply mine the similarities or relationships among different tasks. This limitation may result in negative transfer, thereby degrading the KT performance. As the KT efficiency strongly depends on the similarities of tasks, this article proposes a neural network (NN)-based KT (NNKT) method to analyze the similarities of tasks and obtain the transfer models for information prediction between different tasks for high-quality KT. First, NNKT collects and pairs the solutions of multiple tasks and trains the NNs to obtain the transfer models between tasks. Second, the obtained NNs transfer knowledge by predicting new promising solutions. Meanwhile, a simple adaptive strategy is developed to find the suitable population size to satisfy various search requirements during the evolution process. Comparison of the experimental results between the proposed NN-based multitask optimization (NNMTO) algorithm and some state-of-the-art multitask algorithms on the IEEE Congress on Evolutionary Computation (IEEE CEC) 2017 and IEEE CEC2022 benchmarks demonstrate the efficiency and effectiveness of the NNMTO. Moreover, NNKT can be seamlessly applied to other EMTO algorithms to further enhance their performances. Finally, the NNMTO is applied to a real-world multitask rover navigation application problem to further demonstrate its applicability.

The quality of videos is the primary concern of video service providers. Built upon deep neural networks, video quality assessment (VQA) has rapidly progressed. Although existing works have introduced the knowledge of the human visual system (HVS) into VQA, there are still some limitations that hinder the full exploitation of HVS, including incomplete modeling with few HVS characteristics and insufficient connection among these characteristics. In this article, we present a novel spatial-temporal VQA method termed HVS-5M, wherein we design five modules to simulate five characteristics of HVS and create a bioinspired connection among these modules in a cooperative manner. Specifically, on the side of the spatial domain, the visual saliency module first extracts a saliency map. Then, the content-dependency and the edge masking modules extract the content and edge features, respectively, which are both weighted by the saliency map to highlight those regions that human beings may be interested in. On the other side of the temporal domain, the motion perception module extracts the dynamic temporal features. Besides, the temporal hysteresis module simulates the memory mechanism of human beings and comprehensively evaluates the video quality according to the fusion features from the spatial and temporal domains. Extensive experiments show that our HVS-5M outperforms the state-of-the-art VQA methods. Ablation studies are further conducted to verify the effectiveness of each module toward the proposed method. The source code is available at https://github.com/GZHU-DVL/HVS-5M.

In this article, the problem of impulse noise image restoration is investigated. A typical way to eliminate impulse noise is to use an$L_{1}$norm data fitting term and a total variation (TV) regularization. However, a convex optimization method designed in this way always yields staircase artifacts. In addition, the$L_{1}$norm fitting term tends to penalize corrupted and noise-free data equally, and is not robust to impulse noise. In order to seek a solution of high recovery quality, we propose a new variational model that integrates the nonconvex data fitting term and the nonconvex TV regularization. The usage of the nonconvex TV regularizer helps to eliminate the staircase artifacts. Moreover, the nonconvex fidelity term can detect impulse noise effectively in the way that it is enforced when the observed data is slightly corrupted, while is less enforced for the severely corrupted pixels. A novel difference of convex functions algorithm is also developed to solve the variational model. Using the variational method, we prove that the sequence generated by the proposed algorithm converges to a stationary point of the nonconvex objective function. Experimental results show that our proposed algorithm is efficient and compares favorably with state-of-the-art methods.

The development of data sensing technology has generated a vast amount of high-dimensional data, posing great challenges for machine learning models. Over the past decades, despite demonstrating its effectiveness in data classification, genetic programming (GP) has still encountered three major challenges when dealing with high-dimensional data: 1) solution diversity; 2) multiclass imbalance; and 3) large feature space. In this article, we have developed a problem-specific multiobjective GP framework (PS-MOGP) for handling classification tasks with high-dimensional data. To reduce the large solution space caused by high dimensionality, we incorporate the recursive feature elimination strategy based on mining the archive of evolved GP solutions. A progressive domination Pareto archive evolution strategy (PD-PAES), which optimizes the objectives in a specific order according to their objectives, is proposed to evaluate the GP individuals and maintain a better diversity of solutions. Besides, to address the seriously imbalanced class issue caused by traditional binary decomposition (BD) one versus rest (OVR) for multiclass classification problems, we design a method named BD with a similar positive and negative class size (BD-SPNCS) to generate a set of auxiliary classifiers. Experimental results on benchmark and real-world datasets demonstrate that our proposed PS-MOGP outperforms state-of-the-art traditional and evolutionary classification methods in the context of high-dimensional data classification.

The extraction of spatiotemporal neuron activity from calcium imaging videos plays a crucial role in unraveling the coding properties of neurons. While existing neuron extraction approaches have shown promising results, disturbing and scattering background and unused depth still impede their performance. To address these limitations, we develop an automatic and accurate neuron extraction paradigm, dubbed as decomposition–estimation–reconstruction (DER), consisting of D-procedure, E-procedure, and R-procedure. Specifically, the D-procedure first decomposes the raw data into a low-rank background and a sparse neuron signal, and regularizes$L_{0}$-norm priors of intensity and gradient of the neuron signal to suppress blurring and artifact effects. Then, the E-procedure estimates the depth-dependent transmission of the neuron signal based on its bright and dark channel priors. The R-procedure finally integrates the depth estimation of the neuron signal as a content-importance weight into a constrained non-negative matrix decomposition framework, which facilitates accurate neuron locations to boost the quality of extracted neurons. These three procedures are coupled in a cascade manner, where the former copes with calcium imaging data to facilitate the subsequent one. Comprehensive experiments on neuron extraction from calcium imaging videos demonstrate the superiority of our DER paradigm in both qualitative results and quantitative assessments over state-of-the-art methods.

Many practical optimization problems in the fields of transportation, business, engineering, environmental economics, etc., involve more than one level of decision-making and can be modeled as a bi-level optimization problem with a nested structure of decision variables. Existing studies have made remarkable progress on bi-level single-objective problems. However, due to the increased complexities in terms of computation and decision-making, few efforts have been devoted to bi-level multi-objective optimization problems (BLMOPs). This paper proposes an evolutionary multi-form optimization paradigm that explores alternative formulations of the target task to assist in the search with the original formulation, namely BLMFO, for bi-level multi-objective optimization. Firstly, in the proposed framework, alternative formulations of the original problem are derived to facilitate the problem-solving and also alleviate computational overheads. Then, BLMFO performs the evolutionary search in the original problem space and the auxiliary task space simultaneously to combine searching for feasible solutions and exploring regions of promising solutions, thus ensuring the effectiveness of the proposed framework. Further, useful information is transferred across the original and auxiliary tasks via explicit knowledge transfer to enable complementary exploration for better optimization performance. To the best of our knowledge, this work serves as the first attempt to solve BLMOPs via multi-form evolutionary optimization in the literature. The framework is verified using four instantiation groups with different underlying baseline solvers on various benchmarks and practical problems. The experimental results show the effectiveness and superiority of the proposed framework in terms of performance indicators and the quality of final optimized solutions.

Cardiac image segmentation is essential when applying biomedical informatics to improve industrial healthcare applications. To extract context and detailed information more efficiently and further improve cardiac image segmentation accuracy, we present a novel deep dual-stream convolutional neural network (CNN) for cardiac image semantic segmentation in this article. We use a body stream and a shape stream, respectively, in this method. First, in the body stream we propose integrating a gated fully fusion module to fuse multilevel features in the encoder and decoder paths. In addition, we integrate a feature aggregation module to extract the multiscale context. Second, in the shape stream, we propose using a gated shape CNN exploiting multilevel context to extract detailed information, such as boundary and shape features. Finally, we apply a multitask loss function to align the predicted masks with the ground truth labels. Our experiments on the public cardiac magnetic resonance image dataset show significant performance in the left and right ventricular cavities and myocardium compared to the state-of-the-art algorithms.

The statistical regularities of natural images, referred to as natural scene statistics, play an important role in no-reference image quality assessment. However, it has been widely acknowledged that screen content images (SCIs), which are typically computer generated, do not hold such statistics. Here we make the first attempt to learn the statistics of SCIs, based upon which the quality of SCIs can be effectively determined. The underlying mechanism of the proposed approach is based upon the mild assumption that the SCIs, which are not physically acquired, still obey certain statistics that could be understood in a learning fashion. We empirically show that the statistics deviation could be effectively leveraged in quality assessment, and the proposed method is superior when evaluated in different settings. Extensive experimental results demonstrate the Deep Feature Statistics based SCI Quality Assessment (DFSS-IQA) model delivers promising performance compared with existing NR-IQA models and shows a high generalization capability in the cross-dataset settings. The implementation of our method is publicly available at https://github.com/Baoliang93/DFSS-IQA.

Deep CNNs have achieved impressive improvements for night-time self-supervised depth estimation form a monocular image. However, the performance degrades considerably compared to day-time depth estimation due to significant domain gaps, low visibility, and varying illuminations between day and night images. To address these challenges, we propose a novel night-time self-supervised monocular depth estimation framework with structure regularization, i.e., SRNSD, which incorporates three aspects of constraints for better performance, including feature and depth domain adaptation, image perspective constraint, and cropped multi-scale consistency loss. Specifically, we utilize adaptations of both feature and depth output spaces for better night-time feature extraction and depth map prediction, along with high- and low-frequency decoupling operations for better depth structure and texture recovery. Meanwhile, we employ an image perspective constraint to enhance the smoothness and obtain better depth maps in areas where the luminosity jumps change. Furthermore, we introduce a simple yet effective cropped multi-scale consistency loss that utilizes consistency among different scales of depth outputs for further optimization, refining the detailed textures and structures of predicted depth. Experimental results on different benchmarks with depth ranges of 40m and 60m, including Oxford RobotCar dataset, nuScenes dataset and CARLA-EPE dataset, demonstrate the superiority of our approach over state-of-the-art night-time self-supervised depth estimation approaches across multiple metrics, proving our effectiveness.

This study aims to develop advanced and training-free full-reference image quality assessment (FR-IQA) models based on deep neural networks. Specifically, we investigate measures that allow us to perceptually compare deep network features and reveal their underlying factors. We find that distribution measures enjoy advanced perceptual awareness and test the Wasserstein distance (WSD), Jensen-Shannon divergence (JSD), and symmetric Kullback-Leibler divergence (SKLD) measures when comparing deep features acquired from various pretrained deep networks, including the Visual Geometry Group (VGG) network, SqueezeNet, MobileNet, and EfficientNet. The proposed FR-IQA models exhibit superior alignment with subjective human evaluations across diverse image quality assessment (IQA) datasets without training, demonstrating the advanced perceptual relevance of distribution measures when comparing deep network features. Additionally, we explore the applicability of deep distribution measures in image super-resolution enhancement tasks, highlighting their potential for guiding perceptual enhancements. The code is available on website. (https://github.com/Buka-Xing/Deep-network-based-distribution-measures-for-full-reference-image-quality-assessment).

Residual coding has gained prevalence in lossless compression, where a lossy layer is initially employed and the reconstruction errors (i.e., residues) are then losslessly compressed. The underlying principle of the residual coding revolves around the exploration of priors based on context modeling. Herein, we propose a residual coding framework for 3D medical images, involving the off-the-shelf video codec as the lossy layer and a Bilateral Context Modeling based Network (BCM-Net) as the residual layer. The BCM-Net is proposed to achieve efficient lossless compression of residues through exploring intra-slice and inter-slice bilateral contexts. In particular, a symmetry-based intra-slice context extraction (SICE) module is proposed to mine bilateral intra-slice correlations rooted in the inherent anatomical symmetry of 3D medical images. Moreover, a bi-directional inter-slice context extraction (BICE) module is designed to explore bilateral inter-slice correlations from bi-directional references, thereby yielding representative inter-slice context. Experiments on popular 3D medical image datasets demonstrate that the proposed method can outperform existing state-of-the-art methods owing to efficient redundancy reduction. Our code will be available on GitHub for future research.

In this paper, we propose a graph-represented image distribution similarity (GRIDS) index for full-reference (FR) image quality assessment (IQA), which can measure the perceptual distance between distorted and reference images by assessing the disparities between their distribution patterns under a graph-based representation. First, we transform the input image into a graph-based representation, which is proven to be a versatile and effective choice for capturing visual perception features. This is achieved through the automatic generation of a vision graph from the given image content, leading to holistic perceptual associations for irregular image regions. Second, to reflect the perceived image distribution, we decompose the undirected graph into cliques and then calculate the product of the potential functions for the cliques to obtain the joint probability distribution of the undirected graph. Finally, we compare the distances between the graph feature distributions of the distorted and reference images at different stages; thus, we combine the distortion distribution measurements derived from different graph model depths to determine the perceived quality of the distorted images. The empirical results obtained from an extensive array of experiments underscore the competitive nature of our proposed method, which achieves performance on par with that of the state-of-the-art methods, demonstrating its exceptional predictive accuracy and ability to maintain consistent and monotonic behaviour in image quality prediction tasks. The source code is publicly available at the following website https://github.com/Land5cape/GRIDS.

Multi-robot cooperative navigation is an important task, which has been widely studied in many fields like logistics, transportation, and disaster rescue. However, most of the existing methods either require some strong assumptions or are validated in simple scenarios, which greatly hinders their implementation in the real world. In this paper, more complex environments are considered in which robots can only acquire local observations from their own sensors and have only limited communication capabilities for mapless collaborative navigation. To address this challenging task, we propose a hierarchical framework, by fusing bothSensor-wise andAgent-wise features forPerception-Improving (SAPI), which can adaptively integrate features from different information sources to improve perception capabilities. Specifically, to facilitate scene understanding, we assign prior knowledge to the visual coder to generate efficient embeddings. For effective feature representation, an attention-based sensor fusion network is designed to fuse sensor-level information of visual and LiDAR sensors, while graph convolution with multi-head attention mechanism is applied to aggregate agent-level information from an arbitrary number of neighbors. In addition, reinforcement learning is used to optimize the policy, where a novel compound reward function is introduced to guide training. Extensive experiments demonstrate that our method has excellent generalization ability in different scenarios and scalability for large-scale systems.

The Deep Contextual Video Compression framework (DCVC) utilizes a conditional coding paradigm, where the context is extracted and employed as a condition for the contextual encoder-decoder and entropy model. In this paper, we propose enhanced context mining and filtering to improve the compression efficiency of DCVC. Firstly, considering the context of DCVC is generated without supervision and redundancy may exist among context channels, an enhanced context mining model is proposed to mitigate redundancy across context channels to obtain superior context features. Then, we introduce a transformer-based enhancement network as a filtering module to capture long-distance dependencies and further enhance compression efficiency. The transformer-based enhancement adopts a full-resolution pipeline and calculates self-attention across channel dimensions. By combining the local modeling ability of the enhanced context mining model and the non-local modeling ability of the transformer-based enhancement network, our model outperforms LDP configurations of Versatile Video Coding (VVC), achieving an average bit savings of 6.7% in terms of MS-SSIM.

Text-to-image person re-identification (ReID) is a common subproblem in the field of person re-identification and image-text retrieval. Recent approaches generally follow the structure of a dual-stream network, extracting image and text features. There is no deep interaction between images and text in this approach, making it difficult for the network to learn a highly semantic feature representation. In addition, for both image data and text data, the feature extraction process is modeled in a regular way, such as using Transformer to extract sequence embeddings. However, this type of modeling disregards the inherent relationships among multimodal input embeddings. A more flexible approach to mining multimodal data, which uniformly treats the data as graphs, is proposed. In this way, the extraction and interaction of multimodal information are accomplished by means of messages passing between graph nodes. First, a unified multimodal feature extraction and fusion network is proposed based on the graph convolutional network, which enables the progression of multimodal information from ‘local’ to ‘global’. Second, an asymmetric multilevel alignment module, which focuses on more accurate ‘local’ information from a ‘global’ perspective, is proposed to progressively divide the multimodal information at each level. Last, a cross-modal representation matching strategy based on similarity distribution and mutual information is proposed to achieve cross-modal alignment. The proposed algorithm in this paper is simple and efficient, and the testing results on three public datasets (CUHK-PEDES, ICFG-PEDES and RSTPReID) show that it can achieve SOTA-level performance.

Stereo superpixel segmentation aims at grouping the discretizing pixels into perceptual regions through left and right views more collaboratively and efficiently. Existing superpixel segmentation algorithms mostly utilize color and spatial features as input, which may impose strong constraints on spatial information while utilizing the disparity information in terms of stereo image pairs. To alleviate this issue, we propose a stereo superpixel segmentation method with a decoupling mechanism of spatial information in this work. To decouple stereo disparity information and spatial information, the spatial information is temporarily removed before fusing the features of stereo image pairs, and a decoupled stereo fusion module (DSFM) is designed to handle the stereo features alignment as well as occlusion problems. Moreover, since the spatial information is vital to superpixel segmentation, we further design a dynamic spatiality embedding module (DSEM) to re-add spatial information, and the weights of spatial information will be adaptively adjusted through the dynamic fusion (DF) mechanism in DSEM for achieving a finer segmentation. Comprehensive experimental results demonstrate that our method can achieve the state-of-the-art performance on the KITTI2015 and Cityscapes datasets, and also verify the efficiency when applied in salient object detection on NJU2K dataset. The source code will be available publicly after paper is accepted.

Due to the light absorption and scattering in waterbodies, acquired underwater images frequently suffer from color cast, blur, low contrast, noise, etc., which seriously degrade the image quality and affect their subsequent applications. Therefore, it is necessary to propose a reliable and practical underwater image quality assessment (IQA) model that can faithfully evaluate underwater image quality. To this end, in this article, we establish a novel quality assessment model for underwater images by in-depth analysis and characterization of multiple image properties. Specifically, we propose characterizing the image luminance, color cast, sharpness, contrast, fog density and noise to comprehensively describe the image quality to evaluate the underwater image quality more accurately. Dedicated features are elaborately investigated to characterize those quality-aware image properties. After feature extraction, we employ support vector regression (SVR) to integrate all the quality-aware features and regress them onto the underwater image quality score. Extensive tests performed on standard underwater image quality databases demonstrate the superior prediction performance of the proposed underwater IQA model to state-of-the-art congeneric quality assessment models.

Existing continual image classification methods demonstrate that samples from all sequences of continual classification tasks contain common (task-invariant) features and class-specific (task-variant) features that can be decoupled for classification tasks. However, the existing feature decomposition strategies only focus on individual tasks while neglecting the essential cues that the relationship between different tasks can provide, thereby hindering the improvement of continual image classification results. To address this issue, we propose an Adversarial Contrastive Continual Learning (ACCL) method that decouples task-invariant and task-variant features by constructing all-round, multi-level contrasts on sample pairs within individual tasks or from different tasks. Specifically, three constraints on the distribution of task-invariant and task-variant features are included, i.e., task-invariant features across different tasks should remain consistent, task-variant features should exhibit differences, and task-invariant and task-variant features should differ from each other. At the same time, we also design an effective contrastive replay strategy to make full use of the replay samples to participate in the construction of sample pairs, further alleviating the forgetting problem, and modeling cross-task relationships. Through extensive experiments on continual image classification tasks on CIFAR100, MiniImageNet and TinyImageNet, we show the superiority of our proposed strategy, improving the accuracy and with better visualized outcomes.

Deep recognition models aim to recognize targets with various quality levels in uncontrolled application circumstances, and typically low-quality images usually retard the recognition performance dramatically. As such, a straightforward solution is to restore low-quality input images as pre-processing during deployment. However, this scheme cannot guarantee that deep recognition features of the processed images are conducive to recognition accuracy. How deep recognition features of low-quality images can be refined during training to optimize recognition models has largely escaped research attention in the field of metric learning. In this paper, we propose a quality-aware feature refinement framework based on the dedicated quality priors obtained according to the recognition performance, and a novel quality self-distillation algorithm to learn recognition models. We further show that the proposed scheme can significantly boost the performance of the recognition model with two popular deep recognition tasks, including face recognition and person re-identification. Extensive experimental results provide sufficient evidence on the effectiveness and impressive generalization capability of the proposed framework. Moreover, our framework can be essentially integrated with existing state-of-the-art classification loss functions and network architectures, without extra computation costs during deployment. The source code is available athttps://github.com/oufuzhao/QSD

Traditional full-reference image quality assessment (FR-IQA) methods predict the perceptual quality of a distorted image with a given pristine-quality image as the reference. However, the near-threshold visual perception suggests that there could be numerous pristine-quality representations that are indistinguishable in a scene, and the so-called pristine image used in FR-IQA for reference is just one of them. With numerous approaches proposed for FR-IQA by evaluating the perceptual similarity, much less work has been dedicated to locating the best reference for the deterministic perceptual This paper aims to answer the question that whether enabling the freedom in reference image selection could lead to better performance by designing a new FR-IQA paradigm FLexible REference (FLRE). The FLRE paradigm is developed in the feature space by attempting to obtain the feature-level reference of the distorted image via the selection of its corresponding best explanation within an equal-quality space. To this end, we devise the Perceptually Near-Threshold Estimation (PNTE) and the Pseudo-Reference Search (PRS) strategies. In particular, the PNTE module predicts the equal-quality map of a given pristine-quality feature, forming an equal-quality space. Subsequently, the PRS strategy is employed to locate the reference of the distorted feature within the equal-quality space in an element-wise minimum distance search manner. Due to the lack of the ground-truth reference (i.e., best explanation) of each distorted image, we optimize the pseudo-reference feature learning under three constraints, i.e., the quality regression loss, the disturbance maximization loss, and the content loss. We implement the FLRE as a plug-in module before the deterministic FR-IQA process, and experimental results have demonstrated that combining FLRE with the existing deep feature-based FR-IQA models can significantly improve the quality prediction performance, largely surpassing the state-of-the-art methods. The implementation of our method is publicly available onhttps://github.com/ytian73/FLRE.

Low-light images commonly exhibit issues such as reduced contrast, heightened noise, faded colors, and the absence of critical details. Enhancing these images is challenging due to the complex interplay of various factors. Existing methods primarily focus on learning the intricate mapping between low-light input and normal-light output through well-designed deep neural networks, potentially overlooking the valuable priors inherent in normal-light images. In this paper, we introduce a Code Bank-Guided Transformer (CodedBGT) for low-light image enhancement. Initially, we pre-train a VQGAN on an extensive collection of high-quality normal-light images to capture a high-quality prior. This prior is stored in a discrete codebook along with its corresponding decoded feature space, forming the code bank that guides the enhancement process. To effectively align low-light features with undistorted normal-light code bank features, we design a Code Bank-Guided Block (CBGB) within our enhancement network. The CBGB is integrated into the transformer to aggregate prior information into the enhancement network. Benefiting from the high-quality code bank, our method produces results with more satisfying visual quality. In comparison with the state-of-the-art methods, higher quantitative and qualitative experimental results on the paired dataset and unpaired datasets with various evaluation metrics show the superiority of our method.

Deep learning-based methods have achieved remarkable success with powerful modeling capabilities. However, the weights of these models are learned over the entire training dataset, which inevitably leads to the ignorance of sample specific properties in the learned enhancement mapping. This situation causes ineffective enhancement in the testing phase for the samples that differ significantly from the training distribution. In this paper, we introduce external memory to form an external memory-augmented network (EMNet) for low-light image enhancement. The external memory aims to capture the sample specific properties of the training dataset to guide the enhancement in the testing phase. Benefiting from the learned memory, more complex distributions of reference images in the entire dataset can be “remembered” to facilitate the adjustment of the testing samples more adaptively. To further augment the capacity of the model, we take the transformer as our baseline network, which specializes in capturing long-range spatial redundancy. Experimental results demonstrate that our proposed method has a promising performance and outperforms state-of-the-art methods. It is noted that, the proposed external memory is a plug-and-play mechanism that can be integrated with any existing method to further improve the enhancement quality. More practices of integrating external memory with other image enhancement methods are qualitatively and quantitatively analyzed. The results further confirm that the effectiveness of our proposed memory mechanism when combing with existing enhancement methods.

Just Recognizable Distortion (JRD) refers to the minimum distortion that notably affects the recognition performance of a machine vision model. If a distortion added to images or videos falls within this JRD threshold, the degradation of the recognition performance will be unnoticeable. Based on this JRD property, it will be useful to Video Coding for Machine (VCM) to minimize the bit rate while maintaining the recognition performance of compressed images. In this study, we propose a deep learning-based JRD prediction model for image and video compression. We first construct a large image dataset of Object-Wise JRD (OW-JRD) containing 29,218 original images with 80 object categories, and each image was compressed into 64 distorted versions using Versatile Video Coding (VVC). Secondly, we analyze of the distribution of the OW-JRD, formulate JRD prediction as binary classification problems and propose a deep learning-based OW-JRD prediction framework. Thirdly, we propose a deep learning based binary OW-JRD predictor to predict whether an image object is still detectable or not under different compression levels. Also, we propose an error-tolerance strategy that corrects misclassifications from the binary classifier. Finally, extensive experiments on large JRD image datasets demonstrate that the Mean Absolute Errors (MAEs) of the predicted OW-JRD are 4.90 and 5.92 on different numbers of the classes, which is significantly better than the state-of-the-art JRD prediction model. Moreover, ablation studies on deep network structures, object sizes, features, data padding strategies and image/video coding schemes are presented to validate the effectiveness of the proposed JRD model.

Enhancing low-light image visibility is a critical task in computer vision since it helps to improve input for high-level algorithms. High-quality images typically have clear structural information. In previous studies, due to the lack of proper structural guidance, restored images had some problems, such as unclear structural areas and overexposed or underexposed local areas. To address the above problems, in this paper, we introduce a coefficient of variation (COV) with excellent performance in maintaining structural information, and then we propose a low-light image enhancement method that utilizes the COV to extract structural information from images. First, we apply a traditional retinex model to estimate both reflectance and illumination. Second, we use the COV to indicate the degree of dispersion of the input sample, which enables us to obtain a robust structure-distinguishing weight map for low-light images. The weight map is adaptively divided to obtain a structural weight map, which is then used to enhance the gradient image. This process is applied before the reflectance layer of the retinex model. Finally, the result is obtained by using the block coordinate descent method. According to extensive experiments, outstanding results can be achieved by our proposed method in terms of both subjective and objective evaluation metrics in comparison with other state-of-the-art methods. The source code is available at our website.

Salient object detection (SOD) aims to determine the most visually attractive objects in an image. With the development of virtual reality (VR) technology, 360° omnidirectional image has been widely used, but the SOD task in 360° omnidirectional image is seldom studied due to its severe distortions and complex scenes. In this article, we propose a multi-projection fusion and refinement network (MPFR-Net) to detect the salient objects in 360° omnidirectional image. Different from the existing methods, the equirectangular projection (EP) image and four corresponding cube-unfolding (CU) images are embedded into the network simultaneously as inputs, where the CU images not only provide supplementary information for EP image but also ensure the object integrity of cube-map projection. In order to make full use of these two projection modes, a dynamic weighting fusion (DWF) module is designed to adaptively integrate the features of different projections in a complementary and dynamic manner from the perspective of inter and intrafeatures. Furthermore, in order to fully explore the way of interaction between encoder and decoder features, a filtration and refinement (FR) module is designed to suppress the redundant information of the feature itself and between the features. Experimental results on two omnidirectional datasets demonstrate that the proposed approach outperforms the state-of-the-art methods both qualitatively and quantitatively. The code and results can be found from the link of https://rmcong.github.io/proj_MPFRNet.html.

Traditional neural network compression (NNC) methods decrease the model size and floating-point operations (FLOPs) in the manner of screening out unimportant weight parameters; however, the intrinsic sparsity characteristics have not been fully exploited. In this article, from the perspective of signal processing and analysis for network parameters, we propose to use a compressive sensing (CS)-based method, namely NNCS, for performance improvements. Our proposed NNCS is inspired by the discovery that sparsity levels of weight parameters in the transform domain are greater than those in the original domain. First, to achieve sparse representations for parameters in the transform domain during training, we incorporate a constrained CS model into loss function. Second, the proposed effective training process consists of two steps, where the first step trains raw weight parameters and induces and reconstructs their sparse representations and the second step trains transform coefficients to improve network performances. Finally, we transform the entire neural network into another new domain-based representation, and a sparser parameter distribution can be obtained to facilitate inference acceleration. Experimental results demonstrate that NNCS can significantly outperform the other existing state-of-the-art methods in terms of parameter reductions and FLOPs. With VGGNet on CIFAR-10, we decrease 94.8% parameters and achieve a 76.8% reduction of FLOPs, with 0.13% drop in Top-1 accuracy. With ResNet-50 on ImageNet, we decrease 75.6% parameters and achieve a 78.9% reduction of FLOPs, with 1.24% drop in Top-1 accuracy.

Underwater image instance segmentation is a fundamental and critical step in underwater image analysis and understanding. However, the paucity of general multiclass instance segmentation datasets has impeded the development of instance segmentation studies for underwater images. In this paper, we propose the first underwater image instance segmentation dataset (UIIS), which provides 4628 images for 7 categories with pixel-level annotations. Meanwhile, we also design WaterMask for underwater image instance segmentation for the first time. In Water-Mask, we first devise Difference Similarity Graph Attention Module (DSGAT) to recover lost detailed information due to image quality degradation and downsampling to help the network prediction. Then, we propose Multi-level Feature Refinement Module (MFRM) to predict foreground masks and boundary masks separately by features at different scales, and guide the network through Boundary Mask Strategy (BMS) with boundary learning loss to provide finer prediction results. Extensive experimental results demonstrates that WaterMask can achieve significant gains of 2.9, 3.8 mAP over Mask R-CNN when using ResNet-50 and ResNet-101. Code and Dataset are available at https://github.com/LiamLian0727/WaterMask.

Face Image Quality Assessment (FIQA) lays the foundation for ensuring the stability and accuracy of face recognition systems. However, existing FIQA methods mainly formulate quality relationships within the training set to yield quality scores, ignoring the generalization problem caused by ethnic quality bias between the training and test sets. Domain adaptation presents a potential solution to mitigate the bias, but if FIQA is treated essentially as a regression task, it will be limited by the challenge of feature scaling in transfer learning. Additionally, how to guarantee source risk is also an issue due to the lack of ground-truth labels of the source domain for FIQA. This paper presents the first attempt in the field of FIQA to address these challenges with a novel Ethnic-Quality-Bias Mitigating (EQBM) framework. Specifically, to eliminate the restriction of scalar regression, we first compute the Likert-scale quality probability distributions as source domain annotations. Furthermore, we design an easy-to-hard training scheduler based on the inter-domain uncertainty and intra-domain quality margin as well as the ranking-based domain adversarial network to enhance the effectiveness of transfer learning and further reduce the source risk in domain adaptation. Extensive experiments demonstrate that the EQBM significantly mitigates the quality bias and improves the generalization capability of FIQA across races on different datasets.

Despite significant progress in shadow detection, current methods still struggle with the adverse impact of background color, which may lead to errors when shadows are present on complex backgrounds. Drawing inspiration from the human visual system, we treat the input shadow image as a composition of a background layer and a shadow layer, and design a Style-guided Dual-layer Disentanglement Network (SDDNet) to model these layers independently. To achieve this, we devise a Feature Separation and Recombination (FSR) module that decomposes multi-level features into shadow-related and background-related components by offering specialized supervision for each component, while preserving information integrity and avoiding redundancy through the reconstruction constraint. Moreover, we propose a Shadow Style Filter (SSF) module to guide the feature disentanglement by focusing on style differentiation and uniformization. With these two modules and our overall pipeline, our model effectively minimizes the detrimental effects of background color, yielding superior performance on three public datasets with a real-time inference speed of 32 FPS. Our code is publicly available at:https://github.com/rmcong/SDDNet_ACMMM23.

By integrating complementary information from RGB image and depth map, the ability of salient object detection (SOD) for complex and challenging scenes can be improved. In recent years, the important role of Convolutional Neural Networks (CNNs) in feature extraction and cross-modality interaction has been fully explored, but it is still insufficient in modeling global long-range dependencies of self-modality and cross-modality. To this end, we introduce CNNs-assisted Transformer architecture and propose a novel RGB-D SOD network with Point-aware Interaction and CNN-induced Refinement (PICR-Net). On the one hand, considering the prior correlation between RGB modality and depth modality, an attention-triggered cross-modality point-aware interaction (CmPI) module is designed to explore the feature interaction of different modalities with positional constraints. On the other hand, in order to alleviate the block effect and detail destruction problems brought by the Transformer naturally, we design a CNN-induced refinement (CNNR) unit for content refinement and supplementation. Extensive experiments on five RGB-D SOD datasets show that the proposed network achieves competitive results in both quantitative and qualitative comparisons. Our code is publicly available at: https://github.com/rmcong/PICR-Net_ACMMM23.

Existing class-incremental semantic segmentation (CISS) methods mainly tackle catastrophic forgetting and background shift, but often overlook another crucial issue. In CISS, each step focuses on different foreground classes, and the training set for a single step only includes images containing pixels of the current foreground classes, excluding images without them. This leads to an overrepresentation of these foreground classes in the single-step training set, causing the classification biased towards these classes. To address this issue, we present STAR, which preserves the main characteristics of each past class by storing a compact prototype and necessary statistical data, and aligns the class distribution of single-step training samples with the complete dataset by replaying these prototypes and repeating background pixels with appropriate frequency. Compared to the previous works that replay raw images, our method saves over 100 times the storage while achieving better performance. Moreover, STAR incorporates an old-class features maintaining (OCFM) loss, keeping old-class features unchanged while preserving sufficient plasticity for learning new classes. Furthermore, a similarity-aware discriminative (SAD) loss is employed to specifically enhance the feature diversity between similar old-new class pairs. Experiments on two public datasets, Pascal VOC 2012 and ADE20K, reveal that our model surpasses all previous state-of-the-art methods.

Multimodal optimization problems (MMOPs) have multiple global optima, hence the algorithm must preserve population diversity to locate multiple global optima and ensure the precision of the obtained solutions simultaneously. To achieve these, the niching technique is widely applied. Although the niching technique shows encouraging performance, some niches may continuously evolve even though accurate enough global optima in their regions have been found. This may cause the waste of computational resources and the inefficiency of search behavior. To maintain population diversity and accuracy, and to break through the mentioned deficiency, an optimal peaks detected-based differential evolution (OPPDE) algorithm is proposed, which has three novel components. Firstly, to maintain population diversity, OPDDE designs a parameter-insensitive OPTICS-based niching strategy to automatically partition niches. Secondly, to avoid wasting computation resources on founded global optima and enhance search efficiency, OPDDE designs an optimal peaks detection strategy that uses historical information to identify the founded global optima. Thirdly, a dynamic step local search strategy is used to refine solutions. The proposed OPDDE algorithm generally superiors some state-of-the-art algorithms regarding both the accuracy and completeness of solutions, according to experiments on widely used MMOP benchmarks.

Most of the existing deep learning-based video compression frameworks rely on motion estimation and compensation. However, the artifacts of the warped frames after motion compensation, which propagate the errors to the next frame, limit the video coding performance. In this work, we propose enhanced motion compensation for reduced error propagation in deep video compression. More specifically, we incorporate the designed convolutional neural network into Open DVC as the motion compensation enhancement network to remove noise in the predicted frame. With the enhanced frame, we jointly optimize the whole framework with a single loss function by considering the trade-off between bit cost and frame quality. Experiments show that the proposed enhanced motion compensation model reduces error propagation within a group of frames. Compared with Open DVC, our model can achieve 8.94% bit savings on average for standard test videos in terms of PSNR. Regarding MS-SSIM, our model outperforms Open DVC with 5.67% bit rate savings.

In this paper, a rate control scheme for screen content video coding is proposed for the Versatile Video Coding (VVC) standard. In view of the critical challenges arising from the spatial and temporal unnaturalness of screen content sequences, the proposed method relies on the specifically designed pre-analysis such that the content information regarding the scene complexity can be obtained. As such, the estimated residual complexity is then incorporated into the proposed complexity-aware rate models and distortion models, leading to the optimal bit allocations for each frame and coding tree unit (CTU). In particular, the optimization problem can be analytically solved with the proposed models, and the coding parameters such as Lagrangian multiplier$\lambda $and quantization parameter of each frame and CTU could be delicately derived according to the allocated bits through the proposed analytical models. Extensive experiments have been conducted to evaluate the effectiveness of the proposed method. Compared to the default hierarchical$\lambda $-domain rate control and other screen content rate control algorithms, the proposed method could achieve obvious RD performance gain, and the bit-rate accuracy could be improved.

Fully-supervised salient object detection (SOD) methods have made great progress, but such methods often rely on a large number of pixel-level annotations, which are time-consuming and labour-intensive. In this paper, we focus on a new weakly-supervised SOD task under hybrid labels, where the supervision labels include a large number of coarse labels generated by the traditional unsupervised method and a small number of real labels. To address the issues of label noise and quantity imbalance in this task, we design a new pipeline framework with three sophisticated training strategies. In terms of model framework, we decouple the task into label refinement sub-task and salient object detection sub-task, which cooperate with each other and train alternately. Specifically, the R-Net is designed as a two-stream encoder-decoder model equipped with Blender with Guidance and Aggregation Mechanisms (BGA), aiming to rectify the coarse labels for more reliable pseudo-labels, while the S-Net is a replaceable SOD network supervised by the pseudo labels generated by the current R-Net. Note that, we only need to use the trained S-Net for testing. Moreover, in order to guarantee the effectiveness and efficiency of network training, we design three training strategies, including alternate iteration mechanism, group-wise incremental mechanism, and credibility verification mechanism. Experiments on five SOD benchmarks show that our method achieves competitive performance against weakly-supervised/unsupervised methods both qualitatively and quantitatively. The code and results can be found from the link ofhttps://rmcong.github.io/proj_Hybrid-Label-SOD.html.

With a significant Rate-Distortion (RD) improvement than H.265/HEVC, Versatile Video Coding (VVC) has set a new milestone in lossy video compression. It also incorporates the emerging$\lambda $-domain rate control technique, aiming at a higher visual quality under a fixed bit constraint. However, the challenge remains how to efficiently allocate bits to all frames and Coding Tree Units (CTUs). In this paper, we propose an effective solution by formulating the above task as a Nash equilibrium problem, where all CTUs are treated as players that bargains with each other. By introducing$\lambda $-domain RD models, a constrained optimization is derived with no closed-form solution. We then propose a two-step strategy to address this issue: a Newton method to iteratively calculate an intermediate variable, and a final solution of Nash equilibrium to obtain an approximately optimal$\lambda $. Finally, we utilize the derived$\lambda $to perform an effective CTU-level bit allocation, which is the very first attempt to introduce Nash equilibrium in$\lambda $-domain rate control. Experimental results with Common Test Conditions (CTC) demonstrate the effectiveness and superiority of our method, which outperforms the state-of-the-art CTU-level rate allocation algorithms for VVC.

In this paper, a novel and effective image quality assessment (IQA) algorithm based on frequency disparity for high dynamic range (HDR) images is proposed, termed as local-global frequency feature-based model (LGFM). Motivated by the assumption that the human visual system (HVS) is highly adapted for extracting structural information and partial frequencies when perceiving the visual scene, the Gabor and the Butterworth filters are applied to the luminance component of the HDR image to extract the local and global frequency features, respectively. The similarity measurement and feature pooling strategy are sequentially performed on the frequency features to obtain the predicted single quality score. The experiments evaluated on four widely used benchmarks demonstrate that the proposed LGFM can provide a higher consistency with the subjective perception compared with the state-of-the-art HDR IQA methods. Our code is available at:https://github.com/eezkni/LGFM.

In this work, we propose a neural network based rate control algorithm for Versatile Video Coding (VVC). The proposed method relies on the modeling of the Rate-Quantization (R-Q) and Distortion-Quantization (D-Q) relationships in a data driven manner based upon the characteristics of prediction residuals. In particular, a pre-analysis framework is adopted, in an effort to obtain the prediction residuals which govern the Rate-Distortion (R-D) behaviors. By inferring from the prediction residuals with deep neural networks, the Coding Tree Unit (CTU) level R-Q and D-Q model parameters are derived, which could efficiently guide the optimal bit allocation. Subsequently, the coding parameters, including Quantization Parameter (QP) and$\lambda $, at both frame and CTU levels, are obtained according to allocated bit-rates. We implement the proposed rate control algorithm on VVC Test Model (VTM-13.0). Experimental results exhibit that the proposed rate control algorithm achieves 0.77% BD-Rate savings under Low Delay B (LDB) configurations when compared to the default rate control algorithm used in VTM-13.0. For Random Access (RA) configurations, 1.77% BD-Rate savings can be observed. Furthermore, with better bit-rate estimation, more stable buffer status can be observed, further demonstrating the advantages of the proposed rate control method.

This paper explores the task-oriented compact representation of 3D point clouds, which should maintain the performance of subsequent applications applied to such compact point clouds as much as possible. Designing from the perspective of matrix optimization, we propose MOPS-Net, a novel deep learning-based method that is distinguishable from existing approaches due to its interpretability and flexibility. The matrix optimization problem is challenging due to the discrete and combinatorial nature of the sampling matrix. Therefore, we tackle the challenges by relaxing the binary constraint of the sampling matrix and formulating a constrained and differentiable optimization problem. We then design a deep neural network to mimic the matrix optimization by exploring both the local and global structures of the input data. MOPS-Net can be end-to-end trained with a task network and is permutation-invariant, making it robust to the input. We also extend MOPS-Net such that a single network after one-time training is capable of handling arbitrary downsampling ratios. Extensive experimental results show that MOPS-Net can achieve favorable performance against state-of-the-art deep learning-based methods over various tasks, including classification, reconstruction, and registration. Besides, we validate the robustness of MOPS-Net on noisy data.

Recent deep image compression methods have achieved prominent progress by using nonlinear modeling and powerful representation capabilities of neural networks. However, most existing learning-based image compression approaches employ customized convolutional neural network (CNN) to utilize visual features by treating all pixels equally, neglecting the effect of local key features. Meanwhile, the convolutional filters in CNN usually express the local spatial relationship within the receptive field and seldom consider the long-range dependencies from distant locations. This results in the long-range dependencies of latent representations not being fully compressed. To address these issues, an end-to-end image compression method is proposed by integrating graph attention and asymmetric convolutional neural network (ACNN). Specifically, ACNN is used to strengthen the effect of local key features and reduce the cost of model training. Graph attention is introduced into image compression to address the bottleneck problem of CNN in modeling long-range dependencies. Meanwhile, regarding the limitation that existing attention mechanisms for image compression hardly share information, we propose a self-attention approach which allows information flow to achieve reasonable bit allocation. The proposed self-attention approach is in compliance with the perceptual characteristics of human visual system, as information can interact with each other via attention modules. Moreover, the proposed self-attention approach takes into account channel-level relationship and positional information to promote the compression effect of rich-texture regions. Experimental results demonstrate that the proposed method achieves state-of-the-art rate-distortion performances after being optimized by MS-SSIM compared to recent deep compression models on the benchmark datasets of Kodak and Tecnick. The project page with the source code can be found inhttps://mic.tongji.edu.cn.

This article proposes the scalable cross-modality compression (SCMC) paradigm, in which the image compression problem is further cast into a representation task by hierarchically sketching the image with different modalities. Herein, we adopt the conceptual organization philosophy to model the overwhelmingly complicated visual patterns, based upon the semantic, structure, and signal level representation accounting for different tasks. The SCMC paradigm that incorporates the representation at different granularities supports diverse application scenarios, such as high-level semantic communication and low-level image reconstruction. The decoder, which enables the recovery of the visual information, benefits from the scalable coding based upon the semantic, structure, and signal layers. Qualitative and quantitative results demonstrate that the SCMC can convey accurate semantic and perceptual information of images, especially at low bitrates, and promising rate-distortion performance has been achieved compared to state-of-the-art methods. The code will be available onlinehttps://github.com/ppingzhang/SCMC.

The goal of co-salient object detection (CoSOD) is to discover salient objects that commonly appear in a query group containing two or more relevant images. Therefore, how to effectively extract interimage correspondence is crucial for the CoSOD task. In this article, we propose a global-and-local collaborative learning (GLNet) architecture, which includes a global correspondence modeling (GCM) and a local correspondence modeling (LCM) to capture the comprehensive interimage corresponding relationship among different images from the global and local perspectives. First, we treat different images as different time slices and use 3-D convolution to integrate all intrafeatures intuitively, which can more fully extract the global group semantics. Second, we design a pairwise correlation transformation (PCT) to explore similarity correspondence between pairwise images and combine the multiple local pairwise correspondences to generate the local interimage relationship. Third, the interimage relationships of the GCM and LCM are integrated through a global-and-local correspondence aggregation (GLA) module to explore more comprehensive interimage collaboration cues. Finally, the intra and inter features are adaptively integrated by an intra-and-inter weighting fusion (AEWF) module to learn co-saliency features and predict the co-saliency map. The proposed GLNet is evaluated on three prevailing CoSOD benchmark datasets, demonstrating that our model trained on a small dataset (about 3k images) still outperforms 11 state-of-the-art competitors trained on some large datasets (about 8k-200k images).

So far, researchers have proposed many forensics tools to protect the authenticity and integrity of digital information. However, with the explosive development of machine learning, existing forensics tools may compromise against new attacks anytime. Hence, it is always necessary to investigate anti-forensics to expose the vulnerabilities of forensics tools. It is beneficial for forensics researchers to develop new tools as countermeasures. To date, one of the potential threats is the generative adversarial networks (GANs), which could be employed for fabricating or forging falsified data to attack forensics detectors. In this article, we investigate the anti-forensics performance of GANs by proposing a novel model, the ExS-GAN, which features an extra supervision system. After training, the proposed model could launch anti-forensics attacks on various manipulated images. Evaluated by experiments, the proposed method could achieve high anti-forensics performance while preserving satisfying image quality. We also justify the proposed extra supervision via an ablation study.

The job-shop scheduling problem (JSSP) is a challenging scheduling and optimization problem in the industry and engineering, which relates to the work efficiency and operational costs of factories. The completion time of all jobs is the most commonly considered optimization objective in the existing work. However, factories focus on both time and cost objectives, including completion time, total tardiness, advance time, production cost, and machine loss. Therefore, this article first time proposes a many-objective JSSP that considers all these five objectives to make the model more practical to reflect the various demands of factories. To optimize these five objectives simultaneously, a novel multiple populations for multiple objectives (MPMO) framework-based genetic algorithm (GA) approach, called MPMOGA, is proposed. First, MPMOGA employs five populations to optimize the five objectives, respectively. Second, to avoid each population only focusing on its corresponding single objective, an archive sharing technique (AST) is proposed to store the elite solutions collected from the five populations so that the populations can obtain optimization information about the other objectives from the archive. This way, MPMOGA can approximate different parts of the entire Pareto front (PF). Third, an archive update strategy (AUS) is proposed to further improve the quality of the solutions in the archive. The test instances in the widely used test sets are adopted to evaluate the performance of MPMOGA. The experimental results show that MPMOGA outperforms the compared state-of-the-art algorithms on most of the test instances.

In contrast to the traditional feature selection (FS), local FS (LFS) partitions the whole sample space and obtains the feature subset for each local region. However, most existing LFS algorithms lack a problem-specific objective function and instead simply apply the distance-like objective function, which limits their classification performance. In addition, obtaining a good LFS model is essentially a multiobjective optimization problem. Therefore, in this article, we propose a region purity (RP)-based LFS (RP-LFS) where, besides the proportion of the selected features and region-based distance metric, we design a novel objective function, RP, from the perspective of combining local features with classifiers. To solve the RP-LFS, an improved nondominated sorting genetic algorithm III is proposed. Specifically, a network-inspired crossover operator and a quick bit mutation are applied, which can improve the ability to search for better solutions. A regional feature sharing strategy between different local models is developed, which can preserve more effective features. Experimental studies on 11 UCI datasets and nine high-dimensional datasets validate the effectiveness of our proposed RP. In comparison with various state-of-the-art FS and LFS algorithms, RP-LFS can achieve very competitive classification accuracy while obtaining a reduced feature subset size.

Large-scale optimization problems (LSOPs) are challenging because the algorithm is difficult in balancing too many dimensions and in escaping from trapped bottleneck dimensions. To improve solutions, this paper introduces targeted modification to the certain values in the bottleneck dimensions. Analogous to gene targeting (GT) in biotechnology, we experiment on targeting the specific genes in candidate solution to improve its trait in differential evolution (DE). We propose a simple and efficient method, called GT-based DE (GTDE), to solve LSOPs. In the algorithm design, a simple GT-based modification is developed to perform on the best individual, comprising probabilistically targeting the location of bottleneck dimensions, constructing a homologous targeting vector, and inserting the targeting vector into the best individual. In this way, all the bottleneck dimensions of the best individual can be probabilistically targeted and modified to break the bottleneck and to provide global guidance for more optimal evolution. Note that the GT is only performed on the globally best individual and is just carried out as a simple operator that is added to the standard DE. Experimental studies compare the GTDE with some other state-of-the-art large-scale optimization algorithms, including the winners of CEC2010, CEC2012, CEC2013, and CEC2018 competitions on large-scale optimization. The results show that the GTDE is efficient and performs better than or at least comparable to the others in solving LSOPs.

The convergence and diversity enhancement of multiobjective evolutionary algorithms (MOEAs) to efficiently solve many-objective optimization problems (MaOPs) is an active topic in evolutionary computation. By considering the advantages of the multiple populations for multiple objectives (MPMO) framework in solving multiobjective optimization problems and even MaOPs, this article proposes an MPMO-based algorithm with a bias sorting (BS) method (termed MPMO-BS) for solving MaOPs to achieve both good convergence and diversity performance. For convergence, the BS method is applied to each population of the MPMO framework to enhance the role of nondominated sorting by biasedly paying more attention to the objective optimized by the corresponding population. This way, all the populations in the MPMO framework evolve together to promote the convergence performance on all objectives of the MaOP. For diversity, an elite learning strategy is adopted to generate locally mutated solutions, and a reference vector-based maintenance method is adopted to preserve diverse solutions. The performance of the proposed MPMO-BS algorithm is assessed on 29 widely used MaOP test problems and two real-world application problems. The experimental results show its high effectiveness and competitiveness when compared with seven state-of-the-art MOEAs for many-objective optimization.

Learning and optimization are the two essential abilities of human beings for problem solving. Similarly, computer scientists have made great efforts to design artificial neural network (ANN) and evolutionary computation (EC) to simulate the learning ability and the optimization ability for solving real-world problems, respectively. These have been two essential branches in artificial intelligence (AI) and computer science. However, in humans, learning and optimization are usually integrated together for problem solving. Therefore, how to efficiently integrate these two abilities together to develop powerful AI remains a significant but challenging issue. Motivated by this, this paper proposes a novel learning-aided evolutionary optimization (LEO) framework that plus learning and evolution for solving optimization problems. The LEO is integrated with the evolution knowledge learned by ANN from the evolution process of EC to promote optimization efficiency. The LEO framework is applied to both classical EC algorithms and some state-of-the-art EC algorithms including a champion algorithm, with benchmarking against the IEEE Congress on Evolutionary Computation competition data. The experimental results show that the LEO can significantly enhance the existing EC algorithms to better solve both single-objective and multi-/many-objective global optimization problems, suggesting that learning plus evolution is more intelligent for problem solving. Moreover, the experimental results have also validated the time efficiency of the LEO, where the additional time cost for using LEO is greatly deserved. Therefore, the promising LEO can lead to a new and more efficient paradigm for EC algorithms to solve global optimization problems by plus learning and evolution.

Cross-domain person re-identification (Re-ID) is a challenging and important task in monitoring safety and procedure compliance of industrial work places. In this article, a novel method is proposed to reduce background induced domain shift for adaptive person Re-ID. Specifically, a foreground-background joint clustering module is proposed to extract discriminative foreground and background features and an attention-based feature disentanglement module is designed to reduce the interference of background with the extraction of discriminative foreground features. Experimental results on three widely used person Re-ID benchmarking datasets (Market-1501, DukeMTMC-reID, and MSMT17) have demonstrated that the proposed method achieves promising performance compared with the state-of-the-art methods.

Due to the light absorption and scattering induced by the water medium, underwater images usually suffer from some degradation problems, such as low contrast, color distortion, and blurring details, which aggravate the difficulty of downstream underwater understanding tasks. Therefore, how to obtain clear and visually pleasant images has become a common concern of people, and the task of underwater image enhancement (UIE) has also emerged as the times require. Among existing UIE methods, Generative Adversarial Networks (GANs) based methods perform well in visual aesthetics, while the physical model-based methods have better scene adaptability. Inheriting the advantages of the above two types of models, we propose a physical model-guided GAN model for UIE in this paper, referred to as PUGAN. The entire network is under the GAN architecture. On the one hand, we design a Parameters Estimation subnetwork (Par-subnet) to learn the parameters for physical model inversion, and use the generated color enhancement image as auxiliary information for the Two-Stream Interaction Enhancement sub-network (TSIE-subnet). Meanwhile, we design a Degradation Quantization (DQ) module in TSIE-subnet to quantize scene degradation, thereby achieving reinforcing enhancement of key regions. On the other hand, we design the Dual-Discriminators for the style-content adversarial constraint, promoting the authenticity and visual aesthetics of the results. Extensive experiments on three benchmark datasets demonstrate that our PUGAN outperforms state-of-the-art methods in both qualitative and quantitative metrics. The code and results can be found from the link of https://rmcong.github.io/proj_PUGAN.html.

Convolutional Neural Networks (CNNs) dominate image processing but suffer from local inductive bias, which is addressed by the transformer framework with its inherent ability to capture global context through self-attention mechanisms. However, how to inherit and integrate their advantages to improve compressed sensing is still an open issue. This paper proposes CSformer, a hybrid framework to explore the representation capacity of local and global features. The proposed approach is well-designed for end-to-end compressive image sensing, composed of adaptive sampling and recovery. In the sampling module, images are measured block-by-block by the learned sampling matrix. In the reconstruction stage, the measurements are projected into an initialization stem, a CNN stem, and a transformer stem. The initialization stem mimics the traditional reconstruction of compressive sensing but generates the initial reconstruction in a learnable and efficient manner. The CNN stem and transformer stem are concurrent, simultaneously calculating fine-grained and long-range features and efficiently aggregating them. Furthermore, we explore a progressive strategy and window-based transformer block to reduce the parameters and computational complexity. The experimental results demonstrate the effectiveness of the dedicated transformer-based architecture for compressive sensing, which achieves superior performance compared to state-of-the-art methods on different datasets. Our codes is available at: https://github.com/Lineves7/CSformer.

In this paper, a joint decision tree and visual feature optimization rate control scheme for ultrahigh-definition (UHD) versatile video coding (VVC) is proposed. First, we design a new rate-distortion (R-D) model for UHD videos, and we establish a decision-tree-based multiclass classification scheme to improve the prediction accuracy of the R-D model by fully considering visual features. Second, based on the proposed R-D model, the globally optimal solution is obtained through convex optimization. Finally, we embed our algorithm into the latest VVC reference software, VTM 10.2. According to our experimental results, compared with the latest algorithm in VTM 10.2 and other state-of-the-art algorithms, our method can achieve significant bit rate reductions while maintaining a given peak signal-to-noise ratio (PSNR) or structural similarity index measure (SSIM).

In recent years, RGB-T salient object detection (SOD) has attracted continuous attention, which makes it possible to identify salient objects in environments such as low light by introducing thermal image. However, most of the existing RGB-T SOD models focus on how to perform cross-modality feature fusion, ignoring whether thermal image is really always matter in SOD task. Starting from the definition and nature of this task, this paper rethinks the connotation of thermal modality, and proposes a network named TNet to solve the RGB-T SOD task. In this paper, we introduce a global illumination estimation module to predict the global illuminance score of the image, so as to regulate the role played by the two modalities. In addition, considering the role of thermal modality, we set up different cross-modality interaction mechanisms in the encoding phase and the decoding phase. On the one hand, we introduce a semantic constraint provider to enrich the semantics of thermal images in the encoding phase, which makes thermal modality more suitable for the SOD task. On the other hand, we introduce a two-stage localization and complementation module in the decoding phase to transfer object localization cue and internal integrity cue in thermal features to the RGB modality. Extensive experiments on three datasets show that the proposed TNet achieves competitive performance compared with 20 state-of-the-art methods.

The austere challenge of visual object tracking is to find the target to be tracked in various noise interference and obtain its accurate bounding box coordinates. Recently, the object tracking technology based on the Siamese network has made great breakthroughs, and more and more Siamese network trackers have been proposed with superior performance. They still have some shortcomings. To this end, a new Multi-Stage visual tracking algorithm with Siamese Anchor-Free Proposal Network (MS-SiamAFPN) is proposed in this paper. The algorithm is a three-stage Siamese network tracker composed of Feature Extraction and Fusion (FEF) sub-network, Classification and Regression (CR) sub-network, Validation and Regression (VR) sub-network in series. Firstly, the Anchor-Free Proposal Network (AFPN) module is designed in the CR stage, which can make full use of positive and negative samples for training while reducing neural network parameters. Secondly, aim to achieve better robustness and recognizability in the VR stage, on the one hand, a novel Feature Purification (FP) module is designed, which can automatically select the important channels, and extract the features of irregular regions on the input fusion features, so as to strengthen the representation ability of image features. On the other hand, the target recognition and position regression are regarded as different processing tasks, and the recognition score and position fine-tuning of candidate targets are obtained by newly designing the Dual-Branch Network (DBN) structure, thereby avoiding feature ambiguity. Due to the synergy of the above these innovations, MS-SiamAFPN has obtained a large performance improvement, and achieved SOTA performance in multiple public dataset benchmarks.

Learned video compression has developed rapidly and achieved impressive progress in recent years. Despite efficient compression performance, existing signal fidelity oriented or semantic fidelity oriented video compression methods limit the capability to meet the requirements of both machine and human vision. To address this problem, a task-driven video compression framework is proposed to flexibly support vision tasks for both human vision and machine vision. Specifically, to improve the compression performance, the backbone of the video compression framework is optimized by using three novel modules, including multi-scale motion estimation, multi-frame feature fusion, and reference based in-loop filters. Then, based on the proposed efficient compression backbone, a task-driven optimization approach is designed to achieve the trade-off between signal fidelity oriented compression and semantic fidelity oriented compression. Moreover, a post-filter module is employed for the framework to further improve the performance of the human vision branch. Finally, rate-distortion performance, rate-accuracy performance, and subjective quality are employed as the evaluation metrics, and experimental results show the superiority of the proposed framework for both human vision and machine vision. The source code of this work can be found inhttps://mic.tongji.edu.cn.

The security of spread spectrum (SS) watermarking largely depends on the difficulty of estimating its secret key. Some estimators have been proposed to estimate the secret key in the known-message attack (KMA) scenario. However, the estimation accuracies of existing estimators are not satisfactory when the number of observations is not large enough. Currently, it is still a challenging and open problem to design more effective estimators. In this paper, we propose an equivalent keys (EK)-based estimator to estimate the secret key for both the traditional and more secure SS watermarking methods. Equivalent keys form an equivalent region, which is the intersection of a unit hypersphere and a hypercone. According to the Monte Carlo simulation, we find that the secret key can be estimated by adding up the equivalent keys uniformly sampled from the equivalent region. Thus, the proposed estimator selects equivalent keys from randomly-generated vectors by exploiting the pairs of watermarked signals and their embedded messages. A theoretical analysis is performed for the proposed estimator to evaluate the estimation accuracy. Experimental results verify the theoretical analysis and show the superiority of the proposed estimator over existing estimation methods. Furthermore, this paper also shows the insecurity of the more secure SS watermarking methods in the KMA scenario from a practical perspective for the first time.

The ever-growing multimedia traffic has underscored the importance of effective multimedia codecs. Among them, the up-to-date lossy video coding standard, Versatile Video Coding (VVC), has been attracting attentions of video coding community. However, the gain of VVC is achieved at the cost of significant encoding complexity, which brings the need to realize fast encoder with comparable Rate Distortion (RD) performance. In this paper, we propose to optimize the VVC complexity at intra-frame prediction, with a two-stage framework of deep feature fusion and probability estimation. At the first stage, we employ the deep convolutional network to extract the spatial-temporal neighboring coding features. Then we fuse all reference features obtained by different convolutional kernels to determine an optimal intra coding depth. At the second stage, we employ a probability-based model and the spatial-temporal coherence to select the candidate partition modes within the optimal coding depth. Finally, these selected depths and partitions are executed whilst unnecessary computations are excluded. Experimental results on standard database demonstrate the superiority of proposed method, especially for High Definition (HD) and Ultra-HD (UHD) video sequences.

The performance of a convolutional neural network (CNN) heavily depends on its hyperparameters. However, finding a suitable hyperparameters configuration is difficult, challenging, and computationally expensive due to three issues, which are 1) the mixed-variable problem of different types of hyperparameters; 2) the large-scale search space of finding optimal hyperparameters; and 3) the expensive computational cost for evaluating candidate hyperparameters configuration. Therefore, this article focuses on these three issues and proposes a novel estimation of distribution algorithm (EDA) for efficient hyperparameters optimization, with three major contributions in the algorithm design. First, a hybrid-model EDA is proposed to efficiently deal with the mixed-variable difficulty. The proposed algorithm uses a mixed-variable encoding scheme to encode the mixed-variable hyperparameters and adopts an adaptive hybrid-model learning (AHL) strategy to efficiently optimize the mixed-variables. Second, an orthogonal initialization (OI) strategy is proposed to efficiently deal with the challenge of large-scale search space. Third, a surrogate-assisted multi-level evaluation (SME) method is proposed to reduce the expensive computational cost. Based on the above, the proposed algorithm is named s urrogate-assisted hybrid-model EDA (SHEDA). For experimental studies, the proposed SHEDA is verified on widely used classification benchmark problems, and is compared with various state-of-the-art methods. Moreover, a case study on aortic dissection (AD) diagnosis is carried out to evaluate its performance. Experimental results show that the proposed SHEDA is very effective and efficient for hyperparameters optimization, which can find a satisfactory hyperparameters configuration for the CIFAR10, CIFAR100, and AD diagnosis with only 0.58, 0.97, and 1.18 GPU days, respectively.

The hippocampus plays a vital role in the diagnosis and treatment of many neurological disorders. Recent years, deep learning technology has made great progress in the field of medical image segmentation, and the performance of related tasks has been constantly refreshed. In this paper, we focus on the hippocampus segmentation task and propose a novel hierarchical feedback chain network. The feedback chain structure unit learns deeper and wider feature representation of each encoder layer through the hierarchical feature aggregation feedback chains, and achieves feature selection and feedback through the feature handover attention module. Then, we embed a global pyramid attention unit between the feature encoder and the decoder to further modify the encoder features, including the pair-wise pyramid attention module for achieving adjacent attention interaction and the global context modeling module for capturing the long-range knowledge. The proposed approach achieves state-of-the-art performance on three publicly available datasets, compared with existing hippocampus segmentation approaches. The code and results can be found from the link of https://github.com/easymoneysniper183/sematic_seg.

In this paper, we propose an efficient point cloud classification method via manifold learning based feature representation. Different from conventional methods, we use manifold learning algorithms to embed point cloud features for better considering the geometric continuity on the surface. Then, the nature of point cloud can be acquired in low dimensional space, and after being concatenated with features in the original three-dimensional (3D) space, both the capability of feature representation and the classification network performance can be improved. We explore three traditional manifold algorithms (i.e., Isomap, Locally-Linear Embedding, and Laplacian eigenmaps) in detail, and finally, we select the Locally-Linear Embedding (LLE) algorithm due to its low complexity and locality consistency preservation. Furthermore, we propose a neural network based manifold learning (NNML) method to implement manifold learning based non-linear projection. Experiments demonstrate that the proposed two manifold learning methods can obtain better performances than the state-of-the-art methods, and the obtained mean class accuracy (mA) and overall accuracy (oA) can reach 91.4% and 94.4%, respectively. Moreover, because of the improved feature learning capability, the proposed NNML method can also have better classification accuracy on models with prominent geometric shapes. To further demonstrate the advantages of PointManifold, we extend it as a plug and play method for point cloud classification task, which can be directly used with existing methods and gain a significant improvement.

In intra coding, Rate Distortion Optimization (RDO) is performed to achieve the optimal intra mode from a pre-defined candidate list. The optimal intra mode is also required to be encoded and transmitted to the decoder side besides the residual signal, where lots of coding bits are consumed. To further improve the performance of intra coding in Versatile Video Coding (VVC) , an intelligent intra mode derivation method is proposed in this paper, termed as Deep Learning based Intra Mode Derivation (DLIMD) . In specific, the process of intra mode derivation is formulated as a multi-class classification task, which aims to skip the module of intra mode signaling for coding bits reduction. The architecture of DLIMD is developed to adapt to different quantization parameter settings and variable coding blocks including non-square ones, where only one single trained model is required. Different from the existing deep learning based classification problems, the hand-crafted features are also fed into intra mode derivation network besides the learned features from feature learning network. To compete with traditional methods, one additional binary flag is utilized in the video codec to indicate the selected scheme with RDO. Extensive experimental results reveal that the proposed method can achieve 2.28%, 1.74%, and 2.18% bit rate reduction on average for Y, U, and V components on the platform of VVC test model, which outperforms the state-of-the-art works.

This paper investigates crowd counting in the frequency domain, which is a novel direction compared to the traditional view in the spatial domain. By transforming the density map into the frequency domain and using the properties of the characteristic function, we propose a novel method that is simple, effective, and efficient. The solid theoretical analysis ends up as an implementation-friendly loss function, which requires only standard tensor operations in the training process. We prove that our loss function is an upper bound of the pseudo sup norm metric between the ground truth and the prediction density map (over all of their sub-regions), and demonstrate its efficacy and efficiency versus other loss functions. The experimental results also show its competitiveness to the state-of-the-art on five benchmark data sets: ShanghaiTech A & B, UCF-QNRF, JHU++, and NWPU. Our codes will be available at: wb-shu/Crowd_Couniing_in_the_Frequency_Domain

In this paper, we propose a novel framework to exploit and utilize the shared information inner RGB-D data for efficient depth map compression. Two main codecs, designed based on the existing end-to-end image compression network, are adopted for RGB image compression and enhanced depth image compression with RGB-to-Depth structure prior, respectively. In particular, we propose a Structure Prior Fusion (SPF) module to extract the structure information from both RGB and depth codecs at multi-scale feature levels and fuse the cross-modal feature to generate more efficient structure priors for depth compression. Extensive experiments show that the proposed framework can achieve competitive rate-distortion performance as well as RGB-D task-specific performance at depth map compression compared with the direct compression scheme.

In this paper, we propose a deep video compression method for P-frame in sub-sampled color spaces regarding the YUV420, which has been widely adopted in many state-of-art hybrid video compression standards, in an effort to achieve high compression performance. We adopt motion estimation and motion compression to facilitate the inter prediction of the videos with YUV420 color format, shrinking the total data volume of motion information. Moreover, the motion compensation module on YUV420 is cooperated to enhance the quality of the compensated frame with the consideration of the resolution alignment in the sub-sampled color spaces. To explore the cross-component correlation, the residual encoder-decoder is accompanied with two head-branches and color information fusion. Additionally, a weighted loss emphasizing more on the Y component is utilized to enhance the compression efficiency. Experimental results show that the proposed method can realize 19.82% bit rate reductions on average compared to the deep video compression (DVC) method in terms of the combined PSNR and predominant gains on the Y component.

Existing deep learning-based full-reference IQA (FR-IQA) models usually predict the image quality in a deterministic way by explicitly comparing the features, gauging how severely distorted an image is by how far the corresponding feature lies from the space of the reference images. Herein, we look at this problem from a different viewpoint and propose to model the quality degradation in perceptual space from a statistical distribution perspective. As such, the quality is measured based upon the Wasserstein distance in the deep feature domain. More specifically, the 1D Wasserstein distance at each stage of the pre-trained VGG network is measured, based on which the final quality score is performed. The deep Wasserstein distance (DeepWSD) performed on features from neural networks enjoys better interpretability of the quality contamination caused by various types of distortions and presents an advanced quality prediction capability. Extensive experiments and theoretical analysis show the superiority of the proposed DeepWSD in terms of both quality prediction and optimization. The implementation of our method is publicly available at https://github.com/Buka-Xing/DeepWSD.

Getting rid of the fundamental limitations in fitting to the paired training data, recent unsupervised low-light enhancement methods excel in adjusting illumination and contrast of images. However, for unsupervised low light enhancement, the remaining noise suppression issue due to the lacking of supervision of detailed signal largely impedes the wide deployment of these methods in real-world applications. Herein, we propose a novel Cycle-Interactive Generative Adversarial Network (CIGAN) for unsupervised low-light image enhancement, which is capable of not only better transferring illumination distributions between low/normal-light images but also manipulating detailed signals between two domains, e.g., suppressing/synthesizing realistic noise in the cyclic enhancement/degradation process. In particular, the proposed low-light guided transformation feed-forwards the features of low-light images from the generator of enhancement GAN (eGAN) into the generator of degradation GAN (dGAN). With the learned information of real low-light images, dGAN can synthesize more realistic diverse illumination and contrast in low-light images. Moreover, the feature randomized perturbation module in dGAN learns to increase the feature randomness to produce diverse feature distributions, persuading the synthesized low-light images to contain realistic noise. Extensive experiments demonstrate both the superiority of the proposed method and the effectiveness of each module in CIGAN.

Scientific articles contain rich knowledge that can significantly assists scientific research, but it is difficult to precisely extract knowledge information due to the complexity of the discourse structure of scientific articles. To provide more accurate scientific research knowledge for researchers in a specific academic domain, it is necessary to study the discourse structure of domain scientific articles and to propose an automatic annotation approach to automatically annotate discourse information from articles. Unfortunately, few works have studied the discourse structure of domain scientific articles and the corresponding automatic discourse annotation. To fill this gap, we take scientific articles of the wastewater-based epidemiology domain as a case to study how to automatically and efficiently annotate discourse information. This paper has three contributions. Firstly, we propose a hierarchical discourse model with two layers to cover all potential discourses in various domain scientific articles. Specifically, the first layer defines four core discourse concepts to describe the main process of a scientific research which can be applied in all scientific articles in various domains. The second layer defines fine-granular domain-specific structure, which can accurately describe the entire research contents of a specific domain. Secondly, based on the proposed model, we build a corpus dataset of 100 annotated scientific articles in the wastewater-based epidemiology domain. Thirdly, based on the model and dataset, we propose a simple yet efficient Top-K resampling-based approach to train a more effective classifier for automatic annotation. Extensive experiments verify the effectiveness and efficiency of our proposed hierarchical discourse model and the Top-K resampling-based classification approach.

A densely-sampled light field (LF) is highly desirable in various applications, such as 3-D reconstruction, post-capture refocusing and virtual reality. However, it is costly to acquire such data. Although many computational methods have been proposed to reconstruct a densely-sampled LF from a sparsely-sampled one, they still suffer from either low reconstruction quality, low computational efficiency, or the restriction on the regularity of the sampling pattern. To this end, we propose a novel learning-based method, which accepts sparsely-sampled LFs with irregular structures, and produces densely-sampled LFs with arbitrary angular resolution accurately and efficiently. We also propose a simple yet effective method for optimizing the sampling pattern. Our proposed method, an end-to-end trainable network, reconstructs a densely-sampled LF in a coarse-to-fine manner. Specifically, the coarse sub-aperture image (SAI) synthesis module first explores the scene geometry from an unstructured sparsely-sampled LF and leverages it to independently synthesize novel SAIs, in which a confidence-based blending strategy is proposed to fuse the information from different input SAIs, giving an intermediate densely-sampled LF. Then, the efficient LF refinement module learns the angular relationship within the intermediate result to recover the LF parallax structure. Comprehensive experimental evaluations demonstrate the superiority of our method on both real-world and synthetic LF images when compared with state-of-the-art methods. In addition, we illustrate the benefits and advantages of the proposed approach when applied in various LF-based applications, including image-based rendering and depth estimation enhancement. The code is available at https://github.com/jingjin25/LFASR-FS-GAF.

Symmetric nonnegative matrix factorization (SNMF) has demonstrated to be a powerful method for data clustering. However, SNMF is mathematically formulated as a non-convex optimization problem, making it sensitive to the initialization of variables. Inspired by ensemble clustering that aims to seek a better clustering result from a set of clustering results, we propose self-supervised SNMF (S3NMF), which is capable of boosting clustering performance progressively by taking advantage of the sensitivity to initialization characteristic of SNMF, without relying on any additional information. Specifically, we first perform SNMF repeatedly with a random positive matrix for initialization each time, leading to multiple decomposed matrices. Then, we rank the quality of the resulting matrices with adaptively learned weights, from which a new similarity matrix that is expected to be more discriminative is reconstructed for SNMF again. These two steps are iterated until the stopping criterion/maximum number of iterations is achieved. We mathematically formulate S3NMF as a constrained optimization problem, and provide an alternative optimization algorithm to solve it with the theoretical convergence guaranteed. Extensive experimental results on 10 commonly used benchmark datasets demonstrate the significant advantage of our S3NMF over 14 state-of-the-art methods in terms of 5 quantitative metrics. The source code is publicly available athttps://github.com/jyh-learning/SSSNMF.

With the prevalence of thermal cameras, RGB-T multi-modal data have become more available for salient object detection (SOD) in complex scenes. Most RGB-T SOD works first individually extract RGB and thermal features from two separate encoders and directly integrate them, which pay less attention to the issue of defective modalities. However, such an indiscriminate feature extraction strategy may produce contaminated features and thus lead to poor SOD performance. To address this issue, we propose a novel CCFENet for a perspective to perform robust and accurate multi-modal expression encoding. First, we propose an essential cross-collaboration enhancement strategy (CCE), which concentrates on facilitating the interactions across the encoders and encouraging different modalities to complement each other during encoding. Such a cross-collaborative-encoder paradigm induces our network to collaboratively suppress the negative feature responses of defective modality data and effectively exploit modality-informative features. Moreover, as the network goes deeper, we embed several CCEs into the encoder, further enabling more representative and robust feature generation. Second, benefiting from the proposed robust encoding paradigm, a simple yet effective cross-scale cross-modal decoder (CCD) is designed to aggregate multi-level complementary multi-modal features, and thus encourages efficient and accurate RGB-T SOD. Extensive experiments reveal that our CCFENet outperforms the state-of-the-art models on three RGB-T datasets with a fast inference speed of 62 FPS. In addition, the advantages of our approach in complex scenarios (e.g., bad weather, motion blur, etc.) and RGB-D SOD further verify its robustness and generality. The source code will be publicly available via our project page:https://git.openi.org.cn/OpenVision/CCFENet.

The emergence of 3D point clouds (3DPCs) is promoting the rapid development of immersive communication, autonomous driving, and so on. Due to the huge data volume, the compression of 3DPCs is becoming more and more attractive. We propose a novel and efficient color attribute compression method for static 3DPCs. First, a 3DPC is partitioned into several sub-point clouds by color distribution analysis. Each sub-point cloud is then decomposed into a lot of 3D blocks by an improved k-d tree-based decomposition algorithm. Afterwards, a novel virtual adaptive sampling-based sparse representation strategy is proposed for each 3D block to remove the redundancy among points, in which the bases of the graph transform (GT) and the discrete cosine transform (DCT) are used as candidates of the complete dictionary. Experimental results over 10 common 3DPCs demonstrate that the proposed method can achieve superior or comparable coding performance when compared with the current state-of-the-art methods.

In this work, we propose a novel rate control algorithm for Versatile Video Coding (VVC) standard based on its distinct rate-distortion characteristics. By modelling the transform coefficients with the composite Cauchy distribution, higher accuracy compared with traditional distributions has been achieved. Based on the transform coefficient modelling, the theoretically derived R-Q and D-Q models which have been shown to deliver higher accuracy in characterizing RD characteristics for sequences with different content are incorporated into the rate control process. Furthermore, to establish an adaptive bit allocation scheme, the dependency between different levels of frames is modelled by a dependency factor to describe relationship between the reference and to-be-coded frames. Given the derived R-Q and D-Q relationships, as well as the dependency factor, an adaptive bit allocation scheme is developed for optimal bits allocation. We implement the proposed algorithm on VVC Test Model (VTM) 3.0. Experiments show that due to proper bit allocation, for low delay configuration the proposed algorithm can achieve 1.03% BD-Rate saving compared with the default rate control algorithm and 2.96% BD-Rate saving compared with fixed-QP scheme. Moreover, 1.29% BD-Rate saving and higher control accuracy have also been observed under the random access configuration.

In three-dimensional video system, the texture and depth videos are jointly encoded, and then the Depth Image Based Rendering (DIBR) is utilized to realize view synthesis. However, the compression distortion of texture and depth videos, as well as the disocclusion problem in DIBR degrade the visual quality of the synthesized view. To address this problem, a Two-stream Attention Network (TSAN)-based synthesized view quality enhancement method is proposed for 3D-High Efficiency Video Coding (3D-HEVC) in this article. First, the shortcomings of the view synthesis technique and traditional convolutional neural networks are analyzed. Then, based on these analyses, a TSAN with two information extraction streams is proposed for enhancing the quality of the synthesized view, in which the global information extraction stream learns the contextual information, and the local information extraction stream extracts the texture information from the rendered image. Third, a Multi-Scale Residual Attention Block (MSRAB) is proposed, which can efficiently detect features in different scales, and adaptively refine features by considering interdependencies among spatial dimensions. Extensive experimental results show that the proposed synthesized view quality enhancement method achieves significantly better performance than the state-of-the-art methods.

In the three-dimensional video system, the depth image-based rendering is a key technique for generating synthesized views, which provides audiences with depth perception and interactivity. However, the inaccuracy of depth information leads to geometrical rendering position errors, and the compression distortion of texture and depth videos degrades the quality of the synthesized views. Although existing quality enhancement methods can eliminate the distortions in the synthesized views, their huge computational complexity hinders their applications in real-time multimedia systems. To this end, a residual distillation enhanced network (RDEN)-guided lightweight synthesized view quality enhancement (SVQE) method is proposed to minimize holes and compression distortions in the synthesized views while reducing the model complexity. First, a rethinking on the deep-learning-based SVQE methods is performed. Then, a feature distillation attention block is proposed to effectively reduce the distortions in the synthesized views and make the model fulfill more real-time tasks, which is a lightweight and flexible feature extraction block using an information distillation mechanism and a lightweight multi-scale spatial attention mechanism. Third, a residual feature fusion block is proposed to improve the enhancement performance by using the feature fusion mechanism, which efficiently improves the feature extraction capability without introducing any additional parameters. Experimental results prove that the proposed RDEN efficiently improves the SVQE performance while consuming few computational complexities compared with the state-of-the-art SVQE methods.

Deep neural networks have achieved great performance on blind Image Quality Assessment (IQA), but it is still challenging for using one network to accurately predict the quality of images with different distortions. In this paper, a Distortion-Aware Convolutional Neural Network (DACNN) is proposed for blind IQA, which works effectively for not only synthetically distorted images but also authentically distorted images. The proposed DACNN consists of a distortion aware module, a distortion fusion module, and a quality prediction module. In the distortion aware module, a Siamese network-based pretraining strategy is proposed to design a synthetic distortion-aware network for full learning the synthetic distortions, and an authentic distortion-aware network is used for extracting the authentic distortions. To efficiently fuse the learned distortion features, and make the network pay more attention to the essential features, a weight-adaptive fusion network is proposed to adaptively adjust the weight of each distortion. Finally, the quality prediction module is adopted to map the fused features to a quality score. Extensive experiments on four authentic IQA databases and four synthetic IQA databases have proved the effectiveness of the proposed DACNN.

JPEG-domain enhancement improves the visual quality of JPEG images by directly manipulating the decoded DCT (discrete cosine transform) coefficients, which inevitably leads to mixed compression and enhancement artifacts. Existing forensic methods that merely consider JPEG artifacts are unsuitable to address such mixed artifacts and hence suffer a considerable performance decline in compression parameter estimation and lack the ability to estimate the enhancement parameter. This work attempts to explore the characterization of the mixed artifacts, and to further estimate both the enhancement and compression parameters of JPEG-domain enhanced images. First, a statistical likelihood function is proposed to characterize the periodicity of DCT coefficients, which can measure how well an enhanced image is de-enhanced back to its JPEG compressed version given the compression and enhancement parameters. The proposed likelihood function reaches its maximum if the parameters match their true values. Then, a forensic method of enhancement detection and parameter estimation is developed based on the proposed likelihood function for two kinds of classical JPEG-domain enhancement. Specifically, JPEG-domain enhanced images are detected by thresholding a scalar feature computed upon the likelihoods, and the enhancement and compression parameters are estimated by locating the maximal likelihood. In addition, mathematical proof of the de-enhancement feasibility is provided. Experimental results demonstrate that the proposed method outperforms the compared methods in both enhancement detection and parameter estimation.

Over the past two decades, spread spectrum (SS) embedding has been widely used in digital watermarking due to its competitive performance in robustness and security. However, the robustness of existing secure SS embedding methods, such as natural watermarking (NW) and robust-NW (RNW), is still weak. In this article, we propose a new secure SS embedding method named truncated-RNW (TRNW), which improves the robustness of RNW while maintaining the same security level. The main idea of TRNW is to move RNW-watermarked correlations within an origin-centered sphere onto the spherical surface along the radial direction. Moreover, Hungarian algorithm is used to reduce embedding distortion, and the optimized method is called Hungarian-TRNW (HTRNW). A theoretical analysis and extensive experiments are conducted to validate the effectiveness of the proposed method. The results show that HTRNW achieves the same security level as RNW and a significant improvement over existing representative secure SS embeddings in terms of robustness.

Human visual system has a limitation of sensitivity in detecting small distortion in an image/video and the minimum perceptual threshold is so called Just Noticeable Difference (JND). JND modelling is challenging since it highly depends on visual contents and perceptual factors are not fully understood. In this paper, we propose deep learning based JND and perceptual quality prediction models, which are able to predict the Satisfied User Ratio (SUR) and Video Wise JND (VWJND) of compressed videos with different resolutions and coding parameters. Firstly, the SUR prediction is modeled as a regression problem that fits deep learning tools. Then, Video Wise Spatial SUR method (VW-SSUR) is proposed to predict the SUR value for compressed video, which mainly considers the spatial distortion. Thirdly, we further propose Video Wise Spatial-Temporal SUR (VW-STSUR) method to improve the SUR prediction accuracy by considering the spatial and temporal information. Two fusion schemes that fuse the spatial and temporal information in quality score level and in feature level, respectively, are investigated. Finally, key factors including key frame and patch selections, cross resolution prediction and complexity are analyzed. Experimental results demonstrate the proposed VW-SSUR method outperforms in both SUR and VWJND prediction as compared with the state-of-the-art schemes. Moreover, the proposed VW-STSUR further improves the accuracy as compared with the VW-SSUR and the conventional JND models, where the mean SUR prediction error is 0.049, and mean VWJND prediction error is 1.69 in quantization parameter and 0.84 dB in peak signal-to-noise ratio.

Modeling 3D visual saliency has received great attention due to the development of emerging 3D display technologies. Traditional methods relying on low-level features may not be efficient in interpreting 3D visual content from high-level semantic perspective. Despite numerous efforts dedicated to this area, existing 3D visual saliency detection methods do not necessarily excel in exploring the stereoscopic image saliency driven by the intra-view and inter-view dependencies among left and right views. In this paper, we propose a visual saliency detection method for stereoscopic images grounded on adaptive viewpoint feature enhancement via binocular vision. More specifically, the correlation among left and right views is investigated through a delicately designed binocular stereoscopic saliency feature aggregation module, enabling the generation of more representative saliency features towards binocular vision. Subsequently, to further aggregate the saliency features in multiple scales, we design a progressive attention-based saliency feature pyramid extraction module to effectively integrate the features from top-level to down-level based on the network hierarchy mechanism. The saliency maps are ultimately produced for stereoscopic images by evaluating the obtained saliency features. In addition, we create a stereoscopic image saliency dataset (SIS-3D) that includes 1086 stereoscopic image pairs with various content and their corresponding human eye fixation annotations, aiming to further facilitate the research on visual saliency detection for stereoscopic images. Extensive experiments demonstrate that our proposed method improves CC by an average of 4.02% compared to representative counterparts on the newly built saliency dataset and another publicly available dataset.

Image splicing can be easily used for illegal activities such as falsifying propaganda for political purposes and reporting false news, which may result in negative impacts on society. Hence, it is highly required to detect spliced images and localize the spliced regions. In this work, we propose a multi-task squeeze and excitation network (SE-Network) for splicing localization. The proposed network consists of two streams, namely label mask stream and edge-guided stream, both of which adopt convolutional encoder-decoder architecture. The information from the edge-guided stream is transmitted to the label mask stream for enhancing the discrimination of features between the spliced and host regions. This work has three main contributions. First, image edges, along with label masks and mask edges, are exploited to supply more comprehensive supervision for the localization of spliced regions. Second, the low-level feature maps extracted from shallow layers are fused with the high-level feature maps from deep layers to provide more reliable feature for splicing localization. Finally, several squeeze and excitation attention modules are incorporated into the network to recalibrate the fused features to enhance the feature expression. Extensive experiments show that the proposed multi-task SE-Network outperforms existing splicing localization methods evidently on two synthetic splicing datasets and four benchmark splicing datasets.

The artificial colony (ABC) algorithm shows a relatively powerful exploration search capability but is constrained by the curse of dimensionality, especially on nonseparable functions, where its convergence speed slows dramatically. In this article, based on an analysis of the difference between updating mechanisms that include both all-variable and one-variable updating mechanisms, we find that when equipped with the former strategy, the algorithm rapidly converges to an optimal region, while with the latter strategy, it searches the solution space thoroughly. To utilize multivariable and one-variable updating mechanisms on nonseparable and separable functions, respectively, we embed an improved linkage identification strategy into the ABC by detecting the linkage between variables more effectively. Then, we propose three common strategies for ABC to improve its performance. First, a new approach that considers the historic experiences of the population is proposed to balance exploration and exploitation. Second, a new strategy for initializing scout bees is used to reduce the number of function evaluations. Finally, the individual with the worst performance is updated with a defined probability on multiple dimensions instead of one dimension, causing it to follow the population steps on nonseparable functions. This article is the first to propose all these concepts, which could be adopted for other ABC variants. The effectiveness of our algorithm is validated through basic, CEC2010, CEC2013, and CEC2014 functions and real-world problems.

This article explores the problem of semisupervised affinity matrix learning, that is, learning an affinity matrix of data samples under the supervision of a small number of pairwise constraints (PCs). By observing that both the matrix encoding PCs, called pairwise constraint matrix (PCM) and the empirically constructed affinity matrix (EAM), express the similarity between samples, we assume that both of them are generated from a latent affinity matrix (LAM) that can depict the ideal pairwise relation between samples. Specifically, the PCM can be thought of as a partial observation of the LAM, while the EAM is a fully observed one but corrupted with noise/outliers. To this end, we innovatively cast the semisupervised affinity matrix learning as the recovery of the LAM guided by the PCM and EAM, which is technically formulated as a convex optimization problem. We also provide an efficient algorithm for solving the resulting model numerically. Extensive experiments on benchmark datasets demonstrate the significant superiority of our method over state-of-the-art ones when used for constrained clustering and dimensionality reduction. The code is publicly available at https://github.com/jyh-learning/LAM.

Hash bit selection determines an optimal subset of hash bits from a candidate bit pool. It is formulated as a zero-one quadratic programming problem subject to binary and cardinality constraints. In this article, the problem is equivalently reformulated as a global optimization problem. A collaborative neurodynamic optimization (CNO) approach is applied to solve the problem by using a group of neurodynamic models initialized with particle swarm optimization iteratively in the CNO. Lévy mutation is used in the CNO to avoid premature convergence by ensuring initial state diversity. A theoretical proof is given to show that the CNO with the Lévy mutation operator is almost surely convergent to global optima. Experimental results are discussed to substantiate the efficacy and superiority of the CNO-based hash bit selection method to the existing methods on three benchmarks.

Undersampling is a popular method to solve imbalanced classification problems. However, sometimes it may remove too many majority samples which may lead to loss of informative samples. In this article, the hashing-based undersampling ensemble (HUE) is proposed to deal with this problem by constructing diversified training subspaces for undersampling. Samples in the majority class are divided into many subspaces by a hashing method. Each subspace corresponds to a training subset which consists of most of the samples from this subspace and a few samples from surrounding subspaces. These training subsets are used to train an ensemble of classification and regression tree classifiers with all minority class samples. The proposed method is tested on 25 UCI datasets against state-of-the-art methods. Experimental results show that the HUE outperforms other methods and yields good results on highly imbalanced datasets.

For solving large-scale multiobjective problems (LSMOPs), the transformation-based methods have shown promising search efficiency, which varies the original problem as a new simplified problem and performs the optimization in simplified spaces instead of the original problem space. Owing to the useful information provided by the simplified searching space, the performance of LSMOPs has been improved to some extent. However, it is worth noting that the original problem has changed after the variation, and there is thus no guarantee of the preservation of the original global or near-global optimum in the newly generated space. In this article, we propose to solve LSMOPs via a multivariation multifactorial evolutionary algorithm. In contrast to existing transformation-based methods, the proposed approach intends to conduct an evolutionary search on both the original space of the LSMOP and multiple simplified spaces constructed in a multivariation manner concurrently. In this way, useful traits found along the search can be seamlessly transferred from the simplified problem spaces to the original problem space toward efficient problem solving. Besides, since the evolutionary search is also performed in the original problem space, preserving the original global optimal solution can be guaranteed. To evaluate the performance of the proposed framework, comprehensive empirical studies are carried out on a set of LSMOPs with two to three objectives and 500–5000 variables. The experimental results highlight the efficiency and effectiveness of the proposed method compared to the state-of-the-art methods for large-scale multiobjective optimization.

Salient object detection (SOD) for optical remote sensing images (RSIs) aims at locating and extracting visually distinctive objects/regions from the optical RSIs. Despite some saliency models were proposed to solve the intrinsic problem of optical RSIs (such as complex background and scale-variant objects), the accuracy and completeness are still unsatisfactory. To this end, we propose a relational reasoning network with parallel multi-scale attention for SOD in optical RSIs in this paper. The relational reasoning module that integrates the spatial and the channel dimensions is designed to infer the semantic relationship by utilizing high-level encoder features, thereby promoting the generation of more complete detection results. The parallel multi-scale attention module is proposed to effectively restore the detail information and address the scale variation of salient objects by using the low-level features refined by multi-scale attention. Extensive experiments on two datasets demonstrate that our proposed RRNet outperforms the existing state-of-the-art SOD competitors both qualitatively and quantitatively.

The technological advancements of deep learning have enabled sophisticated face manipulation schemes, raising severe trust issues and security concerns in modern society. Generally speaking, detecting manipulated faces and locating the potentially altered regions are challenging tasks. Herein, we propose a conceptually simple but effective method to efficiently detect forged faces in an image while simultaneously locating the manipulated regions. The proposed scheme relies on a segmentation map that delivers meaningful high-level semantic information clues about the image. Furthermore, a noise map is estimated, playing a complementary role in capturing low-level clues and subsequently empowering decision-making. Finally, the features from these two modules are combined to distinguish fake faces. Extensive experiments show that the proposed model achieves state-of-the-art detection accuracy and remarkable localization performance.

Consistent quality oriented rate control (RC) in video coding has attracted much more attention. However, the existing efforts only focus on decreasing variations between every two adjacent frames, but neglect coding tradeoff problem between intraframes and interframes. In this article, we deal with it from a new perspective, where intraframe quantization parameter (IQP) and RC are optimized for balanced coding. First, due to the importance of intraframes, a new framework is proposed for consistent quality oriented IQP prediction, and then we remove unqualified IQP candidates using the proposed penalty term. Second, we extensively evaluate possible features, and select target bits per pixel for all remaining frames, average and standard variance of frame QPs, where equivalent acquisition methods for QP features are given. Third, predicted IQPs are clipped effectively according to bandwidth and previous information for better bit rate accuracy. Compared with high efficiency video coding reference baseline, experiments demonstrate that our method reduces quality fluctuation greatly by 37.2% on frame-level standard variance of peak-signal-noise-ratio and 45.1% on that of structural similarity. Moreover, it also can have satisfactory results on rate-distortion performance, bit accuracy and buffer control.

Guided by the free-energy principle, generative adversarial networks (GAN)-based no-reference image quality assessment (NR-IQA) methods have improved the image quality prediction accuracy. However, the GAN cannot well handle the restoration task for the free-energy principle-guided NR-IQA methods, especially for the severely destroyed images, which results in that the quality reconstruction relationship between the distorted image and its restored image cannot be accurately built. To address this problem, a visual compensation restoration network (VCRNet)-based NR-IQA method is proposed, which uses a non-adversarial model to efficiently handle the distorted image restoration task. The proposed VCRNet consists of a visual restoration network and a quality estimation network. To accurately build the quality reconstruction relationship between the distorted image and its restored image, a visual compensation module, an optimized asymmetric residual block, and an error map-based mixed loss function, are proposed for increasing the restoration capability of the visual restoration network. For further addressing the NR-IQA problem of severely destroyed images, the multi-level restoration features which are obtained from the visual restoration network are used for the image quality estimation. To prove the effectiveness of the proposed VCRNet, seven representative IQA databases are used, and experimental results show that the proposed VCRNet achieves the state-of-the-art image quality prediction accuracy. The implementation of the proposed VCRNet has been released at https://github.com/NUIST-Videocoding/VCRNet.

Underwater images typically suffer from color deviations and low visibility due to the wavelength-dependent light absorption and scattering. To deal with these degradation issues, we propose an efficient and robust underwater image enhancement method, called MLLE. Specifically, we first locally adjust the color and details of an input image according to a minimum color loss principle and a maximum attenuation map-guided fusion strategy. Afterward, we employ the integral and squared integral maps to compute the mean and variance of local image blocks, which are used to adaptively adjust the contrast of the input image. Meanwhile, a color balance strategy is introduced to balance the color differences between channel a and channel b in the CIELAB color space. Our enhanced results are characterized by vivid color, improved contrast, and enhanced details. Extensive experiments on three underwater image enhancement datasets demonstrate that our method outperforms the state-of-the-art methods. Our method is also appealing in its fast processing speed within 1s for processing an image of size 1024×1024×3 on a single CPU. Experiments further suggest that our method can effectively improve the performance of underwater image segmentation, keypoint detection, and saliency detection. The project page is available at https://li-chongyi.github.io/proj_MMLE.html.

Train driver fatigue and distraction are the main reasons for railway accidents. One of the new technologies to monitor drivers is by using the EEG signals, which provides vital signs monitoring of fatigue and distraction. However, monitoring systems involving full-head scalp EEG are time-consuming and uncomfortable for the driver. The aim of this study was to evaluate the suitability of recently introduced forehead EEG for train driver fatigue and distraction detection. We first constructed a unique dataset with experienced train drivers driving in a simulated train driving environment. The EEG signals were collected from an EEG recording device placed on the driver’s forehead, and numerous features including energy, entropy, rhythmic energy ratio and frontal asymmetry ratio were extracted from the EEG signals. Therefore, a time-series ensemble learning method was proposed to perform fatigue and distraction detection based on the extracted feature. The proposed method outperforms other popular machine learning algorithms including Support Vector Machine(SVM), K-Nearest Neighbor(KNN), Decision Tree(DT), and Long short-term memory(LSTM). The proposed method is stable and convenient to meet the real-time requirement of train driver monitoring.

The berth allocation problem (BAP) is an NP-hard problem in maritime traffic scheduling that significantly influences the operational efficiency of the container terminal. This paper formulates the BAP as a permutation-based combinatorial optimization problem and proposes an improved ant colony system (ACS) algorithm to solve it. The proposed ACS has three main contributions. First, an adaptive heuristic information (AHI) mechanism is proposed to help ACS handle the discrete and real-time difficulties of BAP. Second, to relieve the computational burden, a divide-and-conquer strategy based on variable-range receding horizon control (vRHC) is designed to divide the complete BAP into a set of sub-BAPs. Third, a partial solution memory (PSM) mechanism is proposed to accelerate the ACS convergence process in each receding horizon (i.e., each sub-BAP). The proposed algorithm is termed as adaptive ACS (AACS) with vRHC strategy and PSM mechanism. The performance of the AACS is comprehensively tested on a set of test cases with different scales. Experimental results show that the effectiveness and robustness of AACS are generally better than the compared state-of-the-art algorithms, including the well-performing adaptive evolutionary algorithm and ant colony optimization algorithm. Moreover, comprehensive investigations are conducted to evaluate the influences of the AHI mechanism, the vRHC strategy, and the PSM mechanism on the performance of the AACS algorithm.

A 360-degree streaming system can provide immersive, interactive, and autonomous experiences surrounding the user by means of viewpoint changes to see different angles of a 360-degree video. However, due to the limited capacity and highly dynamic conditions of cellular networks, high-resolution 360-degree video playback over mobile devices often suffers from playback freezing, and bandwidth waste is inevitably incurred in delivering out-of-view video data. In this paper, a hybrid control scheme is presented for segment-level continuous bitrate selection and tile-level bitrate allocation for 360-degree streaming over mobile devices to increase users’ quality of experience. First, a deep reinforcement learning (RL) method is proposed to predict the segment bitrate and avoid playback freezing. Second, a viewpoint-prediction-map-based cooperative bargaining game theory is proposed for bitrate allocation optimization to choose a suitable bitrate for each tile to reduce unreasonable bandwidth waste. The proposed scheme is compared with state-of-the-art approaches under a wide variety of mobile network conditions with multiple viewpoint traces and 360-degree video contents. The experimental results indicate that the proposed method outperforms the compared state-of-the-art approaches in terms of various experimental objectives on mobile devices.

Image-to-Image (I2I) translation is an emerging topic in academia, and it also has been applied in real-world industry for tasks like image synthesis, super-resolution, and colorization. Traditional I2I translation methods usually train data in two or more domains together. This requires lots of computation resources. The results are of lower quality, and contain more artifacts. The training process could be unstable when the data in different domains are not balanced, and modal collapse is more likely to happen. In this paper, we propose a new I2I translation method that generates a new model in the target domain via a series of model transformations on a pre-trained StyleGAN2 model in the source domain. After that, we develop an inversion method to achieve the conversion between an image and its latent vector. By feeding the latent vector into the generated model, we can perform I2I translation between the source domain and target domain. Both qualitative and quantitative evaluations were conducted to verify that the proposed method can achieve better performance in terms of image quality, diversity and semantic similarity to the input and reference images compared to state-of-the-art works.

Sketch-to-image (S2I) translation plays an important role in image synthesis and manipulation tasks, such as photo editing and colorization. Some specific S2I translations, including sketch-to-photo and sketch-to-painting, can be used as powerful tools in the art design industry. However, previous methods only support S2I translation with a single level of density, which gives less flexibility to users for controlling the input sketches. In this work, we propose the first multi-level density sketch-to-image translation framework, which allows the input sketch to cover a wide range from rough object outlines to microstructures. Moreover, to tackle the problem of noncontinuous representation of multi-level density input sketches, we project the density level into a continuous latent space, which can then be linearly controlled by a parameter. This allows users to conveniently control the densities of input sketches and the generation of images. Moreover, our method has been successfully verified on various datasets for different applications, including face editing, multi-modal sketch-to-photo translation, and anime colorization, providing coarse-to-fine levels of controls to these applications.

Traditional 2D image-based saliency prediction models suffer from unsatisfactory performance when dealing with stereoscopic 3D (S3D) images because eye movements in the case of freely viewing S3D images are demonstrated to be guided by both RGB and depth features. This paper studies the problem of saliency prediction on S3D images, where the interactions between RGB and depth modalities are both taken into account. Specifically, we design a novel deep neural network named Cross-modality Fusion and Progressive Integration Network (CFPI-Net) to address this problem. It consists of a Multi-level Cross-modality Feature Fusion (MCFF) module and a Multi-stage Progressive Feature Integration (MPFI) module. The MCFF module first captures hierarchical contexture features from each modality and then effectively fuses the hierarchical contexture features from different modalities at each level. The MPFI module involves multiple cascaded deeply supervised feature integration (DSFI) blocks in which the low-level and high-level cross-modality features are progressively integrated using the integrated features in the previous stage as a guidance. Our proposed CFPI-Net benefits from the advantages of multi-level feature representation, cross-modality feature fusion, and multi-stage progressive feature integration, which hereby fully boost the performance. Experimental results on two benchmark datasets demonstrate that CFPI-Net outperforms state-of-the-art saliency prediction methods both quantitatively and qualitatively. All the results and relevant codes will be made available to the public.

Recently, applying deep learning to no-reference image quality assessment (NR-IQA) has received significant attention. Especially in the last five years, an increasing interest has been drawn to the studies of rank learning since it can help mitigate the problem of small IQA datasets. However, on one hand, existing rank learning is not suitable for the authentically distorted images due to the lack of generated rank samples. On the other hand, the output of existing rank loss functions is uncontrollable, resulting in reduced performance. Motivated by these two limitations, we propose a novel rank learning based NR-IQA method, termed controllable list-wise ranking IQA (CLRIQA) in this paper. To be specific, we first present an imaging-heuristic approach, in which the over- and under-exposure is formulated as an inverse of the Weber-Fechner law, and fusion strategy and compression are adopted, to simulate the authentic distortion and generate the rank image samples. These samples are label-free yet associated with quality ranking information. Then we design a controllable list-wise ranking (CLR) loss function by setting an upper and lower bound of rank range and introducing an adaptive margin to tune rank interval. Finally, both the generated rank samples and proposed CLR are used to pre-train a convolutional neural network. Moreover, to obtain a more accurate prediction model, we take advantage of the IQA datasets to fine-tune the pre-trained network further. Various experiments are conducted on the IQA benchmark datasets, and experimental results demonstrate the effectiveness of the proposed CLRIQA method. The source code and network model can be downloaded at the following web address:https://github.com$/$GZHU-DVL$/$CLRIQA.

Visual quality of images captured by mobile devices is often inferior to that of images captured by a Digital Single Lens Reflex (DSLR) camera. This paper presents a novel generative adversarial network-based mobile image enhancement method, referred to as MIEGAN. It consists of a novel multi-module cascade generative network and a novel adaptive multi-scale discriminative network. The multi-module cascade generative network is built upon a two-stream encoder, a feature transformer, and a decoder. In the two-stream encoder, a luminance-regularizing stream is proposed to help the network focus on low-light areas. In the feature transformation module, two networks effectively capture both global and local information of an image. To further assist the generative network to generate the high visual quality images, a multi-scale discriminator is used instead of a regular single discriminator to distinguish whether an image is fake or real globally and locally. To balance the global and local discriminators, an adaptive weight allocation is proposed. In addition, a contrast loss is proposed, and a new mixed loss function is developed to improve the visual quality of the enhanced images. Extensive experiments on the popular DSLR photo enhancement dataset and MIT-FiveK dataset have verified the effectiveness of the proposed MIEGAN.

Hash bit selection (HBS) aims to find the most discriminative and informative hash bits from a hash pool generated by using different hashing algorithms. It is usually formulated as a binary quadratic programming problem with an information-theoretic objective function and a string-length constraint. In this article, it is equivalently reformulated in the form of a quadratic unconstrained binary optimization problem by augmenting the objective function with a penalty function. The reformulated problem is solved via collaborative neurodynamic optimization (CNO) with a population of classic discrete Hopfield networks. The two most important hyperparameters of the CNO approach are determined based on Monte Carlo test results. Experimental results on three benchmark data sets are elaborated to substantiate the superiority of the collaborative neurodynamic approach to several existing methods for HBS.

In traditional visual cryptography schemes (VCSs), pixel expansion remains to be an unsolved challenge. To alleviate the impact of pixel expansion, several colored-black-and-white VCSs, called CBW-VCSs, were proposed in recent years. Although these methods could ease the effect of pixel expansion, the reconstructed image obtained by these methods may also suffer from low contrasts. To address this issue, we propose a contrast-enhanced (k, n) CBW-VCS based on random grids, named (k,n) RG-CBW-VCS, in this article. By applying color random grids, a binary secret image is encrypted into n color shares that have no pixel expansion. When any k 1 (k 1 > k ) color shares are collected together, the stacked results of them can be identified as the secret image; whereas the superposition of any k 2 ( k 2 < k ) color shares shows nothing. Through theoretical analysis and experimental results, we justify the effectiveness of the proposed (k, n) RG-CBW-VCS. Compared with related methods in feature, contrast, and pixel expansion, the results indicate that the proposed method generally achieves better performance.

With the rapid development of the insurance industry, more diverse insurance products are produced for consumers. Insurance portfolio problems have received increasing attention. While most studies focus on insurance portfolio problem for a single insured, insurance portfolio problems for a specific group of insured are even more intricate but little attention has been paid to. In this article, we propose a group insurance portfolio model for investment allocation of several insurance policies so that the total payout of the whole group can be maximized. The statistical average value of each parameter is considered in the model to approximate the expectation payout of the group insurance portfolio problem. To solve this problem, a coevolutionary estimation of distribution algorithm (EDA) utilizing the divide-and-conquer strategy is proposed. First, as the payout of each insured under a certain portfolio plan can be calculated separately, the proposed approach decomposes the group insurance portfolio problem into several single-insured insurance portfolio problems. In this way, the dimension of the optimization problem becomes lower compared to the original problem. An adaptive EDA is proposed to optimize the portfolio plan of each insured independently. Second, the group insurance portfolio problem remains a nonseparable problem since the investment amount of each insured is limited by the total investable amount of the whole group. A particle swarm optimization algorithm is adopted to cooperate with the EDA to optimize the proportion of allocation to each insured. The proposed algorithm is verified on various scenarios. The experimental results validate that the proposed approach is effective for the group insurance portfolio problem.

Since multi-objective optimization (MOO) involves multiple conflicting objectives, the high dimensionality of the solution space has a much more severe impact on multi-objective problems than single-objective optimization. Taking the advantage of random embedding, some related works have been proposed to scale derivative-free MOO methods to high-dimensional functions. However, with the premise of "low effective dimensionality", a single randomly embedded subspace cannot guarantee the effectiveness of obtained solutions. Taking this cue, we propose an evolutionary multitasking paradigm for multi-objective optimization via random embedding (EMT-ReMO) to enhance the efficiency and effectiveness of current embedding-based methods in solving high-dimensional optimization problems with low effective dimensions. In EMT-ReMO, the target problem is firstly embedded into multiple low-dimensional subspaces by using different random embeddings, aiming to build up a multi-task environment for identifying the underlying effective subspace. Then the implicit multi-objective evolutionary multitasking is performed with seamless knowledge transfer to enhance the optimization process. Experimental results obtained on six high-dimensional MOO functions with or without low effective dimensions have confirmed the effectiveness as well as the efficiency of the proposed EMT-ReMO.

A joint reinforcement learning (RL) and game theory method is presented for segment-level continuous bitrate selection and tile-level bitrate allocation in tile-based 360-degree streaming to increase users’ quality of experience (QoE). First, a viewpoint prediction method based on single-user (SU) viewpoint traces and the saliency map (SM) model is presented to model viewing behaviours. Second, an RL method is proposed to predict segment bitrate and a cooperative bargaining game theory is proposed for bitrate allocation optimization to choose a suitable bitrate for every tile with the help of the viewpoint prediction map. Performance evaluation results indicate that the proposed method can outperform the state-of-the-art methods in terms of different QoE objectives.

In this paper, a quality of experience (QoE)-based neural live streaming method with dynamic adaptive video quality control is developed to improve streaming performance. First, the dynamic adaptive streaming issue is formulated as a Markov decision process (MDP) problem. Second, an reinforcement learning (RL)-based approach is proposed as an appropriate solution, where the client functions as an RL agent and the environment is made up of various networks. User QoE is the reward by mutual consideration of video quality and play-back state. Finally, to optimize the total reward, the RL algorithm chooses the required video quality for each video segment. Experimental results show that the proposed RL-based streaming algorithm outperforms state-of-the-art schemes in terms of both temporal and visual QoE metrics by a noticeable margin while guaranteeing application-level fairness when multiple clients share a bottlenecked network. The code is available on the following website: https://github.com/OpenCode007/ICME2021.

Depth map super-resolution is a task with high practical application requirements in the industry. Existing color-guided depth map super-resolution methods usually necessitate an extra branch to extract high-frequency detail information from RGB image to guide the low-resolution depth map reconstruction. However, because there are still some differences between the two modalities, direct information transmission in the feature dimension or edge map dimension cannot achieve satisfactory result, and may even trigger texture copying in areas where the structures of the RGB-D pair are inconsistent. Inspired by the multi-task learning, we propose a joint learning network of depth map super-resolution (DSR) and monocular depth estimation (MDE) without introducing additional supervision labels. For the interaction of two subnetworks, we adopt a differentiated guidance strategy and design two bridges correspondingly. One is the high-frequency attention bridge (HABdg) designed for the feature encoding process, which learns the high-frequency information of the MDE task to guide the DSR task. The other is the content guidance bridge (CGBdg) designed for the depth map reconstruction process, which provides the content guidance learned from DSR task for MDE task. The entire network architecture is highly portable and can provide a paradigm for associating the DSR and MDE tasks. Extensive experiments on benchmark datasets demonstrate that our method achieves competitive performance. Our code and models are available at https://rmcong.github.io/proj_BridgeNet.html.

The popularity and promotion of depth maps have brought new vigor and vitality into salient object detection (SOD), and a mass of RGB-D SOD algorithms have been proposed, mainly concentrating on how to better integrate cross-modality features from RGB image and depth map. For the cross-modality interaction in feature encoder, existing methods either indiscriminately treat RGB and depth modalities, or only habitually utilize depth cues as auxiliary information of the RGB branch. Different from them, we reconsider the status of two modalities and propose a novel Cross-modality Discrepant Interaction Network (CDINet) for RGB-D SOD, which differentially models the dependence of two modalities according to the feature representations of different layers. To this end, two components are designed to implement the effective cross-modality interaction: 1) the RGB-induced Detail Enhancement (RDE) module leverages RGB modality to enhance the details of the depth features in low-level encoder stage. 2) the Depth-induced Semantic Enhancement (DSE) module transfers the object positioning and internal consistency of depth features to the RGB branch in high-level encoder stage. Furthermore, we also design a Dense Decoding Reconstruction (DDR) structure, which constructs a semantic block by combining multi-level encoder features to upgrade the skip connection in the feature decoding. Extensive experiments on five benchmark datasets demonstrate that our network outperforms $15$ state-of-the-art methods both quantitatively and qualitatively. Our code is publicly available at:https://rmcong.github.io/proj_CDINet.html.

In this paper, we propose the complexity configurable learning-based genome data compression method, in an effort to achieve a good balance between coding complexity and performance in lossless DNA compression. In particular, we first introduce the concept of Group of Bases (GoB), which serves as the foundation and enables the parallel implementation of the learning-based genome data compression. Subsequently, the Markov model is introduced for modeling the initial content, and the learning-based inference is achieved for the remaining base data. The compression is finally achieved with efficient arithmetic coding, and based upon a set of configurations on compression ratios and inference speed, the proposed method is shown to be more efficient and provide more flexibility in real-world applications.

Traffic congestion has become one of the major problems of smart travel. The application of evolutionary computation (EC) for traffic signal timing optimization (TSTO) can effectively alleviate traffic congestion at a single intersection. However, while in more complicated regional traffic signal timing optimization (RTSTO) problems, the canonical EC algorithm such as particle swarm optimization (PSO) still has limitation due to population prematurity. In this paper, a multi-exemplar learning (MEL) strategy is adopted to improve the diversity of the population, so that the particles can have more opportunities to explore the search space. Furthermore, multiple traffic indicators are used in this paper to measure the comprehensive performance of the solution. Moreover, the microsimulation software is adopted to evaluate the solution to simulate the real-world intersection, making the obtained solution more practical in real-world application. Experiments are conducted to investigate the effectiveness and efficiency of MEL-PSO. The results show that the MEL-PSO algorithm is more effective and efficient than the compared algorithms on RTSTO problems.

Logistics scheduling is an important issue in nowadays smart city construction because the scheduling results can determine the efficiency of logistics distribution, and thus influence the development of logistics companies. Although many remarkable works attempted to solve the logistics scheduling problems, especially the logistics-related vehicle routing problem (VRP), most of them established the models based on Euclidean distance, which may result in suboptimal solutions due to the ignorance of road layout. That is, the optimal solution of the model may be suboptimal or even impractical when applied to the real-world situation because of the difference between the model and the real situation. To deal with this weakness, a VRP-based real traffic distance-aware logistics scheduling model that considers the road layout is established in this paper, where the real traffic distance is used as the input of the model. With the assistance of Baidu Map API, the real traffic distance between any two locations and the real traffic duration between them can be captured. In this way, a problem instance set with three scales (i.e., with 20, 30, and 40 locations) is built up for experiments. Besides, the ant colony system (ACS) is employed to solve the problem instances under the cases of using Euclidean distance, linear distance, and real traffic distance to measure the solutions. Comparison results from perspectives of both real traffic distance and real traffic duration show the better performance of solutions obtained under the case of real traffic distance.

This paper explores the problem of multi-view spectral clustering (MVSC) based on tensor low-rank modeling. Unlike the existing methods that all adopt an off-the-shelf tensor low-rank norm without considering the special characteristics of the tensor in MVSC, we design a novel structured tensor low-rank norm tailored to MVSC. Specifically, we explicitly impose a symmetric low-rank constraint and a structured sparse low-rank constraint on the frontal and horizontal slices of the tensor to characterize the intra-view and inter-view relationships, respectively. Moreover, the two constraints could be jointly optimized to achieve mutual refinement. On basis of the novel tensor low-rank norm, we formulate MVSC as a convex low-rank tensor recovery problem, which is then efficiently solved with an augmented Lagrange multiplier-based method iteratively. Extensive experimental results on seven commonly used benchmark datasets show that the proposed method outperforms state-of-the-art methods to a significant extent. Impressively, our method is able to produce perfect clustering. In addition, the parameters of our method can be easily tuned, and the proposed model is robust to different datasets, demonstrating its potential in practice. The code is available athttps://github.com/jyh-learning/MVSC-TLRR.

Positive label is often used as the supervisory information in the learning scenario, which refers to the category that a sample is assigned to. However, another side information lying in the labels, which describes the categories that a sample is exclusive of, have been largely ignored. In this paper, we propose a nonnegative matrix factorization (NMF) based classification method leveraging both positive and negative label information, which is termed as positive and negative label-driven NMF (PNLD-NMF). The proposed scheme concurrently accomplishes data representation and classification in a joint manner. Owing to the complementary characteristics between positive and negative labels, we further design a new regularization framework to take advantage of these two label types. Extensive experiments on six image classification benchmark datasets show that the proposed scheme is able to consistently deliver better classification accuracy.

In this paper, we focus on subjective and objective Point Cloud Quality Assessment (PCQA) in an immersive environment and study the effect of geometry and texture attributes in compression distortion. Using a Head-Mounted Display (HMD) with six degrees of freedom, we establish a subjective PCQA database, named SIAT Point Cloud Quality Database (SIAT-PCQD). Our database consists of 340 distorted point clouds compressed by the MPEG point cloud encoder with the combination of 20 sequences and 17 pairs of geometry and texture quantization parameters. The impact of distorted geometry and texture attributes is further discussed in this paper. Then, we propose two projection-based objective quality evaluation methods, i.e., a weighted view projection based model and a patch projection based model. Our subjective database and findings can be used in point cloud processing, transmission, and coding, especially for virtual reality applications. The subjective datasethttps://dx.doi.org/10.21227/ad8d-7r28http://codec.siat.ac.cn/video_download_siat-pcqd.htmlhasbeen released in the public repository.

Flexible optimization on video coding computational complexity is imperative to adapt to diverse terminals in video streaming, especially with high definition videos and increasingly comprehensive encoders. Until now, few efforts have been contributed to the encoder of multiview videos, which complicates its encoding structure with duplex frame display. To address this issue, we propose a flexible complexity optimization framework in this paper. In the first place, the proposed algorithm flexibly reduces the encoder complexity at different external-defined complexity constraints; furthermore, it is also committed to compression efficiency optimization at different complexity levels. The framework is achieved by a hybrid approach:complexity allocation, which allocates the external-defined complexity constraint to all views, hierarchical layers and frames based on linear programming; andcomplexity regulation, which dynamically adjusts local candidate partitions to fulfil the targeted local complexity constraint, with a probability-driven Alternate Partition Cost (APC) minimization. The overall algorithm is implemented on the popular multiview encoder, Multiview High Efficiency Video Coding (MV-HEVC), with promising Rate-Distortion (RD) performances at different complexity constraints, which are also superior to two recent complexity optimization algorithms.

Quantization plays a pivotal role in JPEG compression with respect to the tradeoff between image fidelity and storage size, and the blind estimation of quantization parameters has attracted considerable interest in the fields of image steganalysis and forensics. Existing estimation methods have made great progress, but they usually suffer a sharp decline in accuracy when addressing small-size JPEG decompressed bitmaps due to the insufficiency of coefficients. Aiming to alleviate this issue, this paper proposes a generic clustering-based framework to improve the performance of the existing methods. The core idea is to gather as many coefficients as possible by clustering subbands before feeding them into a step estimator. The proposed framework is implemented using hierarchical clustering with two kinds of histogram-like features. Extensive experiments are conducted to validate the effectiveness of the proposed framework on a variety of images of different sizes and quality factors, and the results show that notable improvements can be achieved. In addition to quantization step estimation, we believe the idea behind the proposed framework might provide inspiration for other forensic tasks to alleviate their performance issues induced by sample insufficiency.

Image quality assessment is a critical problem for image compression, which can be utilized as a guidance for image compression and codec evaluation. In this paper, we propose a full reference image quality assessment (IQA) algorithm to measure the perceptual quality of compressed images. The proposed IQA model utilizes a data-driven transform, multi-stage Karhunen-Loeve Transform (MS-KLT), as a feature extractor to decompose both reference and compressed images into feature domain, where the importance of feature distortions in different spectral components to human visual system (HVS) is easy to distinguish. Accordingly, an efficient weighting strategy is proposed to reflect the importance of feature distortions based on the energy of transformed coefficients. Considering HVS characteristics, weighted spatial masking effect is derived from both local and global perspectives. In addition, to avoid influences of random noises, a local adaptive low-pass filtering process is applied as a pre-processing operation. Extensive experimental results on popular datasets show that our proposed method correlates better with the subjective results compared with the state-of-the-art algorithms. Moreover, the proposed method behaves more robustly compared with existing methods, and achieves top-ranking performance on different IQA datasets.

In this paper, we propose one novel progressive point cloud upsampling framework to tackle the non-uniform distribution issue during the point cloud upsampling process. Specifically, we design an Up-UNet feature expansion module which is capable of learning the local and global point features via a down-feature operator and an up-feature operator, respectively, to alleviate the non-uniform distribution issue and remove the outliers. Moreover, we design a hybrid loss function considering both the multi-scale reconstruction loss and the rendering loss. The multi-scale reconstruction loss enables each upsampling module to generate a denser point cloud, while the rendering loss via point-based differentiable rendering ensures that the proposed model preserves the point cloud structures. Extensive experimental results demonstrate that our proposed model achieves state-of-the-art performance in terms of both qualitative and quantitative evaluations.

Being able to predict the salient object is of fundamental importance in image processing and computer vision. With numerous approaches proposed for automatic image and video salient object detection, much less work has been dedicated to detecting and segmenting salient objects from light fields. In this article, based on the intrinsic characteristics of light fields, we carefully explore the complementary coherence among multiple cues including spatial, edge and depth information, and elaborately design a multi-task collaborative network for light field salient object detection. More specifically, the correlation mechanisms among edge detection, depth inference and salient object detection are carefully investigated to facilitate the representative saliency features. We first model the coherence among low-level features and heuristic semantic priors, as well as the edge information. Subsequently, the depth-oriented saliency features are derived from the geometry of light fields, in which the 3D convolution operation is leveraged with powerful representation capability to model the disparity correlations among multiple viewpoint images. Finally, a feature-enhanced salient object generator is developed to integrate these complementary saliency features, leading to the final salient object predictions for light fields. Quantitative and qualitative experiments demonstrate the superiority of our proposed model against the state-of-the-art methods over the public light field salient object detection datasets.

Color images always exhibit a high correlation between luma and chroma components. Cross component linear model (CCLM) has been introduced to exploit such correlation for removing redundancy in the on-going video coding standard, i.e., versatile video coding (VVC). To further improve the coding performance, this paper presents a deep learning based intra chroma prediction method, termed as convolutional neural network based chroma prediction (CNNCP). More specifically, the process of chroma prediction is formulated to produce the colorful version from available information input. CNNCP includes two sub-networks for luma down-sampling and chroma prediction, which are jointly optimized to fully exploit spatial and cross component information. In addition, the outputs of CCLM are adopted as chroma initialization for performance enhancement, and the coding distortion level characterized by quantization parameter is fed into the network to release the negative affect from compression artifacts. To further improve the coding performance, the competition is performed between the conventional chroma prediction and CNNCP in terms of rate-distortion cost with a binary flag signalled. The learned CNNCP is incorporated into both video encoder and decoder. Extensive experimental results demonstrate that the proposed scheme can achieve 4.283%, 3.343%, and 4.634% bit rate savings for luma and two chroma components, compared with the VVC test model version 4.0 (VTM 4.0).

As a variant of non-negative matrix factorization (NMF), symmetric NMF (SymNMF) can generate the clustering result without additional post-processing, by decomposing a similarity matrix into the product of a clustering indicator matrix and its transpose. However, the similarity matrix in the traditional SymNMF methods is usually predefined, resulting in limited clustering performance. Considering that the quality of the similarity graph is crucial to the final clustering performance, we propose a new semisupervised model, which is able to simultaneously learn the similarity matrix with supervisory information and generate the clustering results, such that the mutual enhancement effect of the two tasks can produce better clustering performance. Our model fully utilizes the supervisory information in the form of pairwise constraints to propagate it for obtaining an informative similarity matrix. The proposed model is finally formulated as a non-negativity-constrained optimization problem. Also, we propose an iterative method to solve it with the convergence theoretically proven. Extensive experiments validate the superiority of the proposed model when compared with nine state-of-the-art NMF models.

Salient object detection from RGB-D images is an important yet challenging vision task, which aims at detecting the most distinctive objects in a scene by combining color information and depth constraints. Unlike prior fusion manners, we propose an attention steered interweave fusion network (ASIF-Net) to detect salient objects, which progressively integrates cross-modal and cross-level complementarity from the RGB image and corresponding depth map via steering of an attention mechanism. Specifically, the complementary features from RGB-D images are jointly extracted and hierarchically fused in a dense and interweaved manner. Such a manner breaks down the barriers of inconsistency existing in the cross-modal data and also sufficiently captures the complementarity. Meanwhile, an attention mechanism is introduced to locate the potential salient regions in an attention-weighted fashion, which advances in highlighting the salient objects and suppressing the cluttered background regions. Instead of focusing only on pixelwise saliency, we also ensure that the detected salient objects have the objectness characteristics (e.g., complete structure and sharp boundary) by incorporating the adversarial learning that provides a global semantic constraint for RGB-D salient object detection. Quantitative and qualitative experiments demonstrate that the proposed method performs favorably against 17 state-of-the-art saliency detectors on four publicly available RGB-D salient object detection datasets. The code and results of our method are available at https://github.com/Li-Chongyi/ASIF-Net.

Due to the population-based and iterative-based characteristics of evolutionary computation (EC) algorithms, parallel techniques have been widely used to speed up the EC algorithms. However, the parallelism usually performs in the population level where multiple populations (or subpopulations) run in parallel or in the individual level where the individuals are distributed to multiple resources. That is, different populations or different individuals can be executed simultaneously to reduce running time. However, the research into generation-level parallelism for EC algorithms has seldom been reported. In this article, we propose a new paradigm of the parallel EC algorithm by making the first attempt to parallelize the algorithm in the generation level. This idea is inspired by the industrial pipeline technique. Specifically, a kind of EC algorithm called local version particle swarm optimization (PSO) is adopted to implement a pipeline-based parallel PSO (PPPSO, i.e., P3SO). Due to the generation-level parallelism in P3SO, when some particles still perform their evolutionary operations in the current generation, some other particles can simultaneously go to the next generation to carry out the new evolutionary operations, or even go to further next generation(s). The experimental results show that the problem-solving ability of P3SO is not affected while the evolutionary speed has been substantially accelerated in a significant fashion. Therefore, generation-level parallelism is possible in EC algorithms and may have significant potential applications in time-consumption optimization problems.

The training of autoencoder (AE) focuses on the selection of connection weights via a minimization of both the training error and a regularized term. However, the ultimate goal of AE training is to autoencode future unseen samples correctly (i.e., good generalization). Minimizing the training error with different regularized terms only indirectly minimizes the generalization error. Moreover, the trained model may not be robust to small perturbations of inputs which may lead to a poor generalization capability. In this paper, we propose a localized stochastic sensitive AE (LiSSA) to enhance the robustness of AE with respect to input perturbations. With the local stochastic sensitivity regularization, LiSSA reduces sensitivity to unseen samples with small differences (perturbations) from training samples. Meanwhile, LiSSA preserves the local connectivity from the original input space to the representation space that learns a more robustness features (intermediate representation) for unseen samples. The classifier using these learned features yields a better generalization capability. Extensive experimental results on 36 benchmarking datasets indicate that LiSSA outperforms several classical and recent AE training methods significantly on classification tasks.

Large-scale optimization has become a significant and challenging research topic in the evolutionary computation (EC) community. Although many improved EC algorithms have been proposed for large-scale optimization, the slow convergence in the huge search space and the trap into local optima among massive suboptima are still the challenges. Targeted to these two issues, this article proposes an adaptive granularity learning distributed particle swarm optimization (AGLDPSO) with the help of machine-learning techniques, including clustering analysis based on locality-sensitive hashing (LSH) and adaptive granularity control based on logistic regression (LR). In AGLDPSO, a master-slave multisubpopulation distributed model is adopted, where the entire population is divided into multiple subpopulations, and these subpopulations are co-evolved. Compared with other large-scale optimization algorithms with single population evolution or centralized mechanism, the multisubpopulation distributed co-evolution mechanism will fully exchange the evolutionary information among different subpopulations to further enhance the population diversity. Furthermore, we propose an adaptive granularity learning strategy (AGLS) based on LSH and LR. The AGLS is helpful to determine an appropriate subpopulation size to control the learning granularity of the distributed subpopulations in different evolutionary states to balance the exploration ability for escaping from massive suboptima and the exploitation ability for converging in the huge search space. The experimental results show that AGLDPSO performs better than or at least comparable with some other state-of-the-art large-scale optimization algorithms, even the winner of the competition on large-scale optimization, on all the 35 benchmark functions from both IEEE Congress on Evolutionary Computation (IEEE CEC2010) and IEEE CEC2013 large-scale optimization test suites.

The control of virus spreading over complex networks with a limited budget has attracted much attention but remains challenging. This article aims at addressing the combinatorial, discrete resource allocation problems (RAPs) in virus spreading control. To meet the challenges of increasing network scales and improve the solving efficiency, an evolutionary divide-and-conquer algorithm is proposed, namely, a coevolutionary algorithm with network-community-based decomposition (NCD-CEA). It is characterized by the community-based dividing technique and cooperative coevolution conquering thought. First, to reduce the time complexity, NCD-CEA divides a network into multiple communities by a modified community detection method such that the most relevant variables in the solution space are clustered together. The problem and the global swarm are subsequently decomposed into subproblems and subswarms with low-dimensional embeddings. Second, to obtain high-quality solutions, an alternative evolutionary approach is designed by promoting the evolution of subswarms and the global swarm, in turn, with subsolutions evaluated by local fitness functions and global solutions evaluated by a global fitness function. Extensive experiments on different networks show that NCD-CEA has a competitive performance in solving RAPs. This article advances toward controlling virus spreading over large-scale networks.

There has been an increasing consensus in learning based face anti-spoofing that the divergence in terms of camera models is causing a large domain gap in real application scenarios. We describe a framework that eliminates the influence of inherent variance from acquisition cameras at the feature level, leading to the generalized face spoofing detection model that could be highly adaptive to different acquisition devices. In particular, the framework is composed of two branches. The first branch aims to learn the camera invariant spoofing features via feature level decomposition in the high frequency domain. Motivated by the fact that the spoofing features exist not only in the high frequency domain, in the second branch the discrimination capability of extracted spoofing features is further boosted from the enhanced image based on the recomposition of the high-frequency and low-frequency information. Finally, the classification results of the two branches are fused together by a weighting strategy. Experiments show that the proposed method can achieve better performance in both intra-dataset and cross-dataset settings, demonstrating the high generalization capability in various application scenarios.

Superpixel segmentation aims at dividing the input image into some representative regions containing pixels with similar and consistent intrinsic properties, without any prior knowledge about the shape and size of each superpixel. In this article, to alleviate the limitation of superpixel segmentation applied in practical industrial tasks that detailed boundaries are difficult to be kept, we regard each representative region with independent semantic information as a subspace, and correspondingly formulate superpixel segmentation as a subspace clustering problem to preserve more detailed content boundaries. We show that a simple integration of superpixel segmentation with the conventional subspace clustering does not effectively work due to the spatial correlation of the pixels within a superpixel, which may lead to boundary confusion and segmentation error when the correlation is ignored. Consequently, we devise a spatial regularization and propose a novel convex locality-constrained subspace clustering model that is able to constrain the spatial adjacent pixels with similar attributes to be clustered into a superpixel and generate the content-aware superpixels with more detailed boundaries. Finally, the proposed model is solved by an efficient alternating direction method of multipliers solver. Experiments on different standard datasets demonstrate that the proposed method achieves superior performance both quantitatively and qualitatively compared with some state-of-the-art methods.

This paper addresses the problem of generating dense point clouds from given sparse point clouds to model the underlying geometric structures of objects/scenes. To tackle this challenging issue, we propose a novel end-to-end learning-based framework. Specifically, by taking advantage of the linear approximation theorem, we first formulate the problem explicitly, which boils down to determining the interpolation weights and high-order approximation errors. Then, we design a lightweight neural network to adaptively learn unified and sorted interpolation weights as well as the high-order refinements, by analyzing the local geometry of the input point cloud. The proposed method can be interpreted by the explicit formulation, and thus is more memory-efficient than existing ones. In sharp contrast to the existing methods that work only for a pre-defined and fixed upsampling factor, the proposed framework only requires a single neural network with one-time training to handle various upsampling factors within a typical range, which is highly desired in real-world applications. In addition, we propose a simple yet effective training strategy to drive such a flexible ability. In addition, our method can handle non-uniformly distributed and noisy data well. Extensive experiments on both synthetic and real-world data demonstrate the superiority of the proposed method over state-of-the-art methods both quantitatively and qualitatively. The code will be publicly available at https://github.com/ninaqy/Flexible-PU.

In this paper, we propose an effective approach to infer the just noticeable distortion (JND) profile based on patch-level structural visibility learning. Instead of pixel-level JND profile estimation, the image patch, which is regarded as the basic processing unit to better correlate with the human perception, can be further decomposed into three conceptually independent components for visibility estimation. In particular, to incorporate the structural degradation into the patch-level JND model, a deep learning-based structural degradation estimation model is trained to approximate the masking of structural visibility. In order to facilitate the learning process, a JND dataset is further established, including 202 pristine images and 7878 distorted images generated by advanced compression algorithms based on the upcoming Versatile Video Coding (VVC) standard. Extensive experimental results further show the superiority of the proposed approach over the state-of-the-art. Our dataset is available at: https://github.com/ShenXuelin-CityU/PWJNDInfer.

The forthcoming Versatile Video Coding (VVC) standard adopts the trellis-coded quantization, which leverages the delicate trellis graph to map the quantization candidates within one block into the optimal path. Despite the high compression efficiency, the complex trellis search with soft-decision quantization may hinder the applications due to high complexity and low throughput capacity. To reduce the complexity, in this paper, we propose a low complexity trellis-coded quantization scheme in a scientifically sound way with theoretical modeling of the rate and distortion. As such, the trellis departure point can be adaptively adjusted, and unnecessarily visited branches are accordingly pruned, leading to the shrink of total trellis stages and simplification of transition branches. Extensive experimental results on the VVC test model show that the proposed scheme is effective in reducing the encoding complexity by 11% and 5% with all intra and random access configurations, respectively, at the cost of only 0.11% and 0.05% BD-Rate increase. Meanwhile, on average 24% and 27% quantization time savings can be achieved under all intra and random access configurations. Due to the excellent performance, the VVC test model has adopted one implementation of the proposed scheme.

Despite the remarkable advances in visual saliency analysis for natural scene images (NSIs), salient object detection (SOD) for optical remote sensing images (RSIs) still remains an open and challenging problem. In this paper, we propose an end-to-end Dense Attention Fluid Network (DAFNet) for SOD in optical RSIs. A Global Context-aware Attention (GCA) module is proposed to adaptively capture long-range semantic context relationships, and is further embedded in a Dense Attention Fluid (DAF) structure that enables shallow attention cues flow into deep layers to guide the generation of high-level feature attention maps. Specifically, the GCA module is composed of two key components, where the global feature aggregation module achieves mutual reinforcement of salient feature embeddings from any two spatial locations, and the cascaded pyramid attention module tackles the scale variation issue by building up a cascaded pyramid framework to progressively refine the attention map in a coarse-to-fine manner. In addition, we construct a new and challenging optical RSI dataset for SOD that contains 2,000 images with pixel-wise saliency annotations, which is currently the largest publicly available benchmark. Extensive experiments demonstrate that our proposed DAFNet significantly outperforms the existing state-of-the-art SOD competitors. https://github.com/rmcong/DAFNet_TIP20.

Light field imaging, originated from the availability of light field capture technology, offers a wide range of applications in the field of computational vision. The capability of predicting salient objects of light fields remains technologically challenging due to its complicated geometry structure. In this paper, we propose a light field salient object detection approach that formulates the geometric coherence among multiple views of light fields as graphs, where the angular/central views represent the nodes and their relations compose the edges. The spatial and disparity correlations between multiple views are effectively explored through multi-scale graph neural networks, enabling the more comprehensive understanding of light field content and more representative and discriminative saliency features generation. Moreover, a multi-scale saliency feature consistency learning module is embedded to enhance the saliency features. Finally, an accurate salient object map is produced for the light field based upon the extracted features. In addition, we establish a new light field salient object detection dataset (CITYU-Lytro) that contains 817 light fields with diverse contents and their corresponding annotations, aiming to further promote the research on light field salient object detection. Quantitative and qualitative experiments demonstrate that the proposed method performs favorably compared with the state-of-the-art methods on the benchmark datasets.

Mismatches between the precisions of representing the disparity, depth value and rendering position in 3D video systems cause redundancies in depth map representations. In this paper, we propose a highly efficient multiview depth coding scheme based on Depth Histogram Projection (DHP) and Allowable Depth Distortion (ADD) in view synthesis. Firstly, DHP exploits the sparse representation of depth maps generated from stereo matching to reduce the residual error from INTER and INTRA predictions in depth coding. We provide a mathematical foundation for DHP-based lossless depth coding by theoretically analyzing its rate-distortion cost. Then, due to the mismatch between depth value and rendering position, there is a many-to-one mapping relationship between them in view synthesis, which induces the ADD model. Based on this ADD model and DHP, depth coding with lossless view synthesis quality is proposed to further improve the compression performance of depth coding while maintaining the same synthesized video quality. Experimental results reveal that the proposed DHP based depth coding can achieve an average bit rate saving of 20.66% to 19.52% for lossless coding on Multiview High Efficiency Video Coding (MV-HEVC) with different groups of pictures. In addition, our depth coding based on DHP and ADD achieves an average depth bit rate reduction of 46.69%, 34.12% and 28.68% for lossless view synthesis quality when the rendering precision varies from integer, half to quarter pixels, respectively. We obtain similar gains for lossless depth coding on the 3D-HEVC, HEVC Intra coding and JPEG2000 platforms.

The airline crew rostering problem (CRP) is significant for balancing the workload of crew and for improving the satisfaction rate of crew’s preferences, which is related to the fairness and satisfaction of crew. However, most existing work considers only one objective on fairness or satisfaction. In this study, we propose a new practical model for CRP that takes both fairness and satisfaction into account simultaneously. To solve the multi-objective CRP efficiently, we develop an ant colony system (ACS) algorithm based on the multiple populations for multiple objectives (MPMO) framework, termed multi-objective ACS (MOACS). The main contributions of MOACS lie in three aspects. Firstly, two ant colonies are utilized to optimize fairness and satisfaction objectives, respectively. Secondly, a new hybrid complementary heuristic strategy with three kinds of heuristic information schemes is proposed to avoid ant colonies focusing only on their own objectives. Ant colonies randomly choose one of the three schemes to help explore the Pareto front (PF) sufficiently. Thirdly, a local search strategy with two types of local search respectively for fairness and satisfaction is designed to further approach the global PF. The MOACS is applied to seven real-world monthly CRPs with different sizes from a major North-American airline. Experimental results show that MOACS generally outperforms the greedy algorithm and some other popular multi-objective optimization algorithms, especially on large-scale instances.

Many image-to-image (I2I) translation problems are in nature of high diversity that a single input may have various counterparts. The multi-modal network that can build a many-to-many mapping between two visual domains has been proposed in prior works. However, most of them are guided by sampled noises. Some others encode the reference image into a latent vector, which would eliminate the semantic information of the reference image. In this work, we aim to provide a solution to control the output based on references semantically. Given a reference image and an input in another domain, we first perform semantic matching between the two visual content and generate an auxiliary image, which explicitly encourages the semantic characteristic to be preserved. A deep network then is used for I2I translation and the final outputs are expected to be semantically similar to both the input and the reference. However, few paired data can satisfy that dual-similarity in a supervised fashion, and so we build up a self-supervised framework in the training stage. We improve the quality and diversity of the outputs by employing non-local blocks and a multi-task architecture. We assess the proposed method through extensive qualitative and quantitative evaluations and also present comparisons with several state-of-the-art models.

Falls are the main cause of accidental injuries, and even death among elderly people, especially those who live alone in their homes. The absence of a reliable fall detection system has long been a serious problem for home health monitoring. A video surveillance system can be used to monitor elderly people at home to detect falls, but the traditional implementation of such intelligent detection falls short of personal privacy-related considerations; additionally, many people do not want to be watched in their homes. To solve this problem, we propose a fall detection system with visual shielding that can ensure the safety of elderly people in their homes while preserving their personal privacy. Multilayer compressed sensing is first used to achieve visually shielded video frames. By combining low-rank sparse decomposition theory with the improved local binary pattern on the three orthogonal planes, the object features are extracted from the shielded video frames. Finally, to compensate for the information lost in the compressed video to a certain extent, a private information-embedded classification model is proposed to identify fall-related behavior. The experimental results on two public fall datasets show that the proposed method delivers impressive accuracy and a low error rate while effectively distinguishing between fall- and nonfall-related behaviors in videos.

Concept drift is prevalent in non-stationary data environments but is rarely researched in image retrieval. Therefore, more research is needed on image retrieval in non-stationary data environments so that highly relevant images can still be retrieved when concept drifts happen. Hashing is a key technique to allow efficient image retrieval, so incremental hashing technique emerges in recent years for image retrieval in non-stationary environments. A state-of-the-art method isIncremental Hashing(ICH). ICH trains new hash tables on new data without considering the performance of previous hash tables, so the dependency of successive hash tables is ignored. To make use of this dependency in order to improve the performance of image retrieval in non-stationary environments,Complementary Incremental Hashing with query-adaptive Re-ranking(CIHR) is proposed in this paper. CIHR trains multiple hash tables incrementally, one for each data chunk of images. A new hash table is trained on a new data chunk of images as well as those images badly hashed by previous hash tables, thus the new hash table is complementary to the previous hash tables. To use the hash tables more effectively, a query-adaptive re-ranking method is used to weight all hash functions in each hash table according to their retrieval performance with respect to a given query. Weighted Hamming distance is finally used to evaluate the similarity between the query and the images in the database, as the basis of image retrieval. Experimental results on simulated non-stationary scenarios show that the proposed CIHR method achieves higher retrieval accuracy than all methods being compared, thus setting a new state of the art in image retrieval in non-stationary data environments.

Rate control (RC) plays a critical role in the transmission of high-quality video data under certain bandwidth restrictions in High Efficiency Video Coding (HEVC). Most current HEVC RC algorithms based on spatio-temporal information for rate-distortion (R-D) model parameters cannot effectively handle the cases with dynamic video sequences that contain fast moving objects, significant object occlusion or scene changes. In this paper, we propose an RC method based on deep reinforcement learning (DRL) for dynamic video sequences in HEVC to improve the coding efficiency. First, the rate control problem is formulated as a Markov decision process (MDP) problem. Second, with the MDP model, we develop a DRL-based algorithm to find the optimal quantization parameters (QPs) by training a deep neural network. The resulting intelligent agent selects the optimal RC strategy to reduce distortion, buffer and quality fluctuations by observing the current state of the encoder. The asynchronous advantage actor-critic (A3C) method is used to solve the MDP problem. Finally, the proposed DRL-based RC method is implemented in the newest video coding standard. Experimental results show that the proposed method offers substantially enhanced RC accuracy and consistently outperforms HEVC reference software and other state-of-the-art algorithms.

In this article, we propose a novel model for constrained clustering, namely, the dissimilarity propagation-guided graph-Laplacian principal component analysis (DP-GLPCA). By fully utilizing a limited number of weakly supervisory information in the form of pairwise constraints, the proposed DP-GLPCA is capable of capturing both the local and global structures of input samples to exploit their characteristics for excellent clustering. More specifically, we first formulate a convex semisupervised low-dimensional embedding model by incorporating a new dissimilarity regularizer into GLPCA (i.e., an unsupervised dimensionality reduction model), in which both the similarity and dissimilarity between low-dimensional representations are enforced with the constraints to improve their discriminability. An efficient iterative algorithm based on the inexact augmented Lagrange multiplier is designed to solve it with the global convergence guaranteed. Furthermore, we innovatively propose to propagate the cannot-link constraints (i.e., dissimilarity) to refine the dissimilarity regularizer to be more informative. The resulting DP model is iteratively solved, and we also prove that it can converge to a Karush-Kuhn-Tucker point. Extensive experimental results over nine commonly used benchmark data sets show that the proposed DP-GLPCA can produce much higher clustering accuracy than state-of-the-art constrained clustering methods. Besides, the effectiveness and advantage of the proposed DP model are experimentally verified. To the best of our knowledge, it is the first time to investigate DP, which is contrast to existing pairwise constraint propagation that propagates similarity. The code is publicly available at https://github.com/jyh-learning/DP-GLPCA.

Constrained spectral clustering (SC) based on pairwise constraint propagation has attracted much attention due to the good performance. All the existing methods could be generally cast as the following two steps, i.e., a small number of pairwise constraints are first propagated to the whole data under the guidance of a predefined affinity matrix, and the affinity matrix is then refined in accordance with the resulting propagation and finally adopted for SC. Such a stepwise manner, however, overlooks the fact that the two steps indeed depend on each other, i.e., the two steps form a "chicken-egg" problem, leading to suboptimal performance. To this end, we propose a joint PCP model for constrained SC by simultaneously learning a propagation matrix and an affinity matrix. Especially, it is formulated as a bounded symmetric graph regularized low-rank matrix completion problem. We also show that the optimized affinity matrix by our model exhibits an ideal appearance under some conditions. Extensive experimental results in terms of constrained SC, semisupervised classification, and propagation behavior validate the superior performance of our model compared with state-of-the-art methods.

Visual secret sharing (VSS) is a new technique for sharing a binary image into multiple shadows. For VSS, the original image can be reconstructed from the shadows in any qualified set, but cannot be reconstructed from those in any forbidden set. In most traditional VSS schemes, the shadows held by participants have the same importance. However, in practice, a certain number of shadows are given a higher importance due to the privileges of their owners. In this article, a novel ( t , s , k , n )-threshold VSS scheme is proposed based on access structure partition. First, we construct the basis matrix of the proposed ( t , s , k , n )-threshold VSS scheme by utilizing a new access structure partition method and sub-access structure merging method. Then, the secret image is shared by the basis matrix as n shadows, which are divided into s essential shadows and n - s non-essential shadows. To reconstruct the secret image, k or more shadows should be collected, which include at least t essential shadows; otherwise, no information about the secret image can be obtained. Compared with related schemes, our scheme achieves a smaller shadow size and a higher visual quality of the reconstructed image. Theoretical analysis and experiments indicate the effectiveness of the proposed scheme.

A block-level perceptual image compression framework is proposed in this work, including a block-level just noticeable difference (JND) prediction model and a preprocessing scheme. Specifically speaking, block-level JND values are first deduced by utilizing the OTSU method based on the variation of block-level structural similarity values between two adjacent picture-level JND values in the MCL-JCI dataset. After the JND value for each image block is generated, a convolutional neural network–based prediction model is designed to forecast block-level JND values for a given target image. Then, a preprocessing scheme is devised to modify the discrete cosine transform coefficients during JPEG compression on the basis of the distribution of block-level JND values of the target test image. Finally, the test image is compressed by the max JND value across all of its image blocks in the light of the initial quality factor setting. The experimental results demonstrate that the proposed block-level perceptual image compression method is able to achieve 16.75% bit saving as compared to the state-of-the-art method with similar subjective quality. The project page can be found at https://mic.tongji.edu.cn/43/3f/c9778a148287/page.htm.

Virtual network embedding (VNE) is an important problem in network virtualization for the flexible sharing of network resources. While most existing studies focus on centralized embedding for VNE, distributed embedding is considered more scalable and suitable for large-scale scenarios, but how virtual resources can be mapped to substrate resources effectively and efficiently remains a challenging issue. In this paper, we devise a distributed VNE system with historical archives (HAs) and metaheuristic approaches. First, we introduce metaheuristic approaches to each delegation of the distributed embedding system as the optimizer for VNE. Compared to the heuristic-based greedy algorithms used in existing distributed embedding approaches, which are prone to be trapped in local optima, metaheuristic approaches can provide better embedding performance for these distributed delegations. Second, an archive-based strategy is also introduced in the distributed embedding system to assist the metaheuristic algorithms. The archives are used to record the up-to-date information of frequently repeated tasks. By utilizing such archives as historical memory, metaheuristic algorithms can further improve embedding performance for frequently repeated tasks. Following this idea, we incorporate the set-based particle swarm optimization (PSO) as the optimizer and propose the distributed VNE system with HAs and set-based PSO (HA-VNE-PSO) system to solve the VNE problem in a distributed way. HA-VNE-PSO is empirically validated in scenarios of different scales. The experimental results verify that HA-VNE-PSO can scale well with respect to substrate networks, and the HA strategy is indeed effective in different scenarios.

The acquisition of light field images with high angular resolution is costly. Although many methods have been proposed to improve the angular resolution of a sparsely-sampled light field, they always focus on the light field with a small baseline, which is captured by a consumer light field camera. By making full use of the intrinsic geometry information of light fields, in this paper we propose an end-to-end learning-based approach aiming at angularly super-resolving a sparsely-sampled light field with a large baseline. Our model consists of two learnable modules and a physically-based module. Specifically, it includes a depth estimation module for explicitly modeling the scene geometry, a physically-based warping for novel views synthesis, and a light field blending module specifically designed for light field reconstruction. Moreover, we introduce a novel loss function to promote the preservation of the light field parallax structure. Experimental results over various light field datasets including large baseline light field images demonstrate the significant superiority of our method when compared with state-of-the-art ones, i.e., our method improves the PSNR of the second best method up to 2 dB in average, while saves the execution time 48×. In addition, our method preserves the light field parallax structure better.

The paper presents a novel method, Zero-Reference Deep Curve Estimation (Zero-DCE), which formulates light enhancement as a task of image-specific curve estimation with a deep network. Our method trains a lightweight deep network, DCE-Net, to estimate pixel-wise and high-order curves for dynamic range adjustment of a given image. The curve estimation is specially designed, considering pixel value range, monotonicity, and differentiability. Zero-DCE is appealing in its relaxed assumption on reference images, i.e., it does not require any paired or unpaired data during training. This is achieved through a set of carefully formulated non-reference loss functions, which implicitly measure the enhancement quality and drive the learning of the network. Our method is efficient as image enhancement can be achieved by an intuitive and simple nonlinear curve mapping. Despite its simplicity, we show that it generalizes well to diverse lighting conditions. Extensive experiments on various benchmarks demonstrate the advantages of our method over state-of-the-art methods qualitatively and quantitatively. Furthermore, the potential benefits of our Zero-DCE to face detection in the dark are discussed.

Light field (LF) images acquired by hand-held devices usually suffer from low spatial resolution as the limited sampling resources have to be shared with the angular dimension. LF spatial super-resolution (SR) thus becomes an indispensable part of the LF camera processing pipeline. The high-dimensionality characteristic and complex geometrical structure of LF images makes the problem more challenging than traditional single-image SR. The performance of existing methods are still limited as they fail to thoroughly explore the coherence among LF views and are insufficient in accurately preserving the parallax structure of the scene. In this paper, we propose a novel learning-based LF spatial SR framework, in which each view of an LF image is first individually super-resolved by exploring the complementary information among views with combinatorial geometry embedding. For accurate preservation of the parallax structure among the reconstructed views, a regularization network trained over a structure-aware loss function is subsequently appended to enforce correct parallax relationships over the intermediate estimation. Our proposed approach is evaluated over datasets with a large number of testing images including both synthetic and real-world scenes. Experimental results demonstrate the advantage of our approach over state-of-the-art methods, i.e., our method not only improves the average PSNR by more than 1.0 dB but also preserves more accurate parallax details, at a lower computation cost.

With numerous coding tools adopted in the forthcoming Versatile Video Coding (VVC) standard, much less work has been dedicated to study the corresponding Rate-Distortion (R-D) characteristics. This paper proposes a new quadratic R-D model for Versatile Video Coding. In particular, based on the proposed model, a new R-λ relationship is derived and used for frame level rate control. The rate control algorithm is implemented on VTM 2.0 platform for intra coding scenarios. Compared to the default rate control algorithm in VTM 2.0, experimental results show that proposed rate control algorithm can achieve 0.77% BD-BR reduction with similar control accuracy.

Perceptual video coding plays a very important role in video codec optimization aiming at removing the perceptual redundancies in video content. In this paper, a just noticeable distortion (JND) guided perceptually lossless coding framework is proposed for Versatile Video Coding (VVC) intra coding. Within this framework, a pattern-based pixel wise JND model is employed to guide the distortion distribution, and subsequently the most appropriate quantization parameter is chosen for each Coding Tree Unit (CTU). The content adaptive Laplacian distribution based D-Q model based on a two pass coding framework is established to derive the most proper QP that satisfies the perceptually lossless coding criteria. The whole framework is integrated into the H.266/VVC intra coding framework. Experimental results demonstrate that the proposed scheme can achieve high accuracy prediction and efficient perceptually lossless intra coding, leading to around 10% bitrate savings comparing with the frame level QP derivation scheme.

This paper explores the problem of reconstructing high-resolution light field (LF) images from hybrid lenses, including a high-resolution camera surrounded by multiple low-resolution cameras. To tackle this challenge, we propose a novel end-to-end learning-based approach, which can comprehensively utilize the specific characteristics of the input from two complementary and parallel perspectives. Specifically, one module regresses a spatially consistent intermediate estimation by learning a deep multidimensional and cross-domain feature representation; the other one constructs another intermediate estimation, which maintains the high-frequency textures, by propagating the information of the high-resolution view. We finally leverage the advantages of the two intermediate estimations via the learned attention maps, leading to the final high-resolution LF image. Extensive experiments demonstrate the significant superiority of our approach over state-of-the-art ones. That is, our method not only improves the PSNR by more than 2 dB, but also preserves the LF structure much better. To the best of our knowledge, this is the first end-to-end deep learning method for reconstructing a high-resolution LF image with a hybrid input. We believe our framework could potentially decrease the cost of high-resolution LF data acquisition and also be beneficial to LF data storage and transmission. The code is available at https://github.com/jingjin25/LFhybridSR-Fusion.

Compactly representing the visual signals is of fundamental importance in various image/video-centered applications. Although numerous approaches were developed for improving the image and video coding performance by removing the redundancies within visual signals, much less work has been dedicated to the transformation of the visual signals to another well-established modality for better representation capability. In this paper, we propose a new scheme for visual signal representation that leverages the philosophy of transferable modality. In particular, the deep learning model, which characterizes and absorbs the statistics of the input scene with online training, could be efficiently represented in the sense of rate-utility optimization to serve as the enhancement layer in the bitstream. As such, the overall performance can be further guaranteed by optimizing the new modality incorporated. The proposed framework is implemented on the state-of-the-art video coding standard (i.e., versatile video coding), and significantly better representation capability has been observed based on extensive evaluations.

In this work, we aim to learn an unpaired image enhancement model, which can enrich low-quality images with the characteristics of high-quality images provided by users. We propose a quality attention generative adversarial network (QAGAN) trained on unpaired data based on the bidirectional Generative Adversarial Network (GAN) embedded with a quality attention module (QAM). The key novelty of the proposed QAGAN lies in the injected QAM for the generator such that it learns domain-relevant quality attention directly from the two domains. More specifically, the proposed QAM allows the generator to effectively select semantic-related characteristics from the spatial-wise and adaptively incorporate style-related attributes from the channel-wise, respectively. Therefore, in our proposed QAGAN, not only discriminators but also the generator can directly access both domains which significantly facilitate the generator to learn the mapping function. Extensive experimental results show that, compared with the state-of-the-art methods based on unpaired learning, our proposed method achieves better performance in both objective and subjective evaluations.

Multimodal optimization problems (MMOPs) require the algorithm to locate multiple global optima and also achieve a certain accuracy on the found optima. When applying particle swarm optimization (PSO) to solve MMOPs, a fixed population communication topology may not be sufficient to handle these two requirements simultaneously. In this paper, a novel PSO with hybrid ring topology, termed HRTPSO, is proposed for MMOPs. In the early evolutionary process of HRTPSO, a sparse topology is constructed to enhance the population diversity to help locate multiple optima, while in the later evolutionary process of HRTPSO, the population communication topology is switched to a relatively dense topology for improving the convergence efficiency on the found optima. The switch of topology is controlled by a threshold and its effect is also analyzed in this paper. Experimental results on the 20 multimodal functions in CEC'2013 benchmark set show that HRTPSO has better performance than the other six multimodal optimization algorithms.

It is recognized that system trustworthiness is a hyperstructure embodied by the structural, behavioral, and system dimensions with a set of coherent attributes. We explore a theoretical framework of tripartite trustworthiness that can be applied to real-world autonomous systems. We present a formal study of the essences and mathematical models of system trustworthiness and their quantitative measurements in the contexts of autonomous and mission-critical intelligent systems where humans and machines interact in a hybrid environment.

Sparsity is a desirable property in many nonnegative matrix factorization (NMF) applications. Although some level of sparseness of NMF solutions can be achieved by using regularization, the resulting sparsity depends highly on the regularization parameter to be valued in an ad hoc way. In this letter we formulate sparse NMF as a mixed-integer optimization problem with sparsity as binary constraints. A discrete-time projection neural network is developed for solving the formulated problem. Sufficient conditions for its stability and convergence are analytically characterized by using Lyapunov's method. Experimental results on sparse feature extraction are discussed to substantiate the superiority of this approach to extracting highly sparse features.

High dynamic range (HDR) imaging techniques have witnessed a great improvement in the past few decades. However, saliency detection task on HDR content is still far from well explored. In this paper, we introduce a multi-exposure decomposition-fusion model for HDR image saliency detection inspired by the brightness adaption mechanism. The proposed model is composed of three modules. Firstly, a decomposition module converts the input raw HDR image into a stack of LDR images by uniformly sampling the exposure time range. Secondly, a saliency region proposal network is employed to generate the candidate saliency maps for each LDR image in the exposure stack. Finally, an uncertainty weighting based fusion algorithm is applied to generate the overall saliency map for the input HDR image by merging the obtained LDR saliency maps. Extensive experiments show that our proposed model achieves superior performance compared with the state-of-the-art methods on the existing HDR eye fixation databases. The source code of the proposed model are made publicly available at https://github.com/sunnycia/DFHSal.

High dynamic range (HDR) video compression technology, which is capable of delivering a wider range of luminance and a larger colour gamut than standard dynamic range (SDR) technology, has been widely used in recent years in many fields, including industrial image processing, digital entertainment, and machine vision. Rate control (RC) is of paramount importance to HDR compression and transmission; accordingly, an RC scheme for HDR in High Efficiency Video Coding (HEVC) is proposed in this paper. First, considering the HDR characteristics, we propose an HDR-Visual Difference Predictor (VDP)-2-based rate-distortion (R-D) model to improve the coding performance. Second, we directly utilize $\lambda $ rather than the bit rate in the optimization process to obtain the optimal solution. Finally, we propose a new model parameter estimation method to further reduce the RC errors. According to our experimental results, significant bit rate reductions in terms of HDR-VDP-2, the Video Quality Metric (VQM) and the mean peak-signal-to-noise ratio (mPSNR) can be achieved on average compared with the state-of-the-art algorithm used in HM16.19.

Depth information has been demonstrated to be useful for saliency detection. However, the existing methods for RGBD saliency detection mainly focus on designing straightforward and comprehensive models, while ignoring the transferable ability of the existing RGB saliency detection models. In this article, we propose a novel depth-guided transformation model (DTM) going from RGB saliency to RGBD saliency. The proposed model includes three components, that is: 1) multilevel RGBD saliency initialization; 2) depth-guided saliency refinement; and 3) saliency optimization with depth constraints. The explicit depth feature is first utilized in the multilevel RGBD saliency model to initialize the RGBD saliency by combining the global compactness saliency cue and local geodesic saliency cue. The depth-guided saliency refinement is used to further highlight the salient objects and suppress the background regions by introducing the prior depth domain knowledge and prior refined depth shape. Benefiting from the consistency of the entire object in the depth map, we formulate an optimization model to attain more consistent and accurate saliency results via an energy function, which integrates the unary data term, color smooth term, and depth consistency term. Experiments on three public RGBD saliency detection benchmarks demonstrate the effectiveness and performance improvement of the proposed DTM from RGB to RGBD saliency.

The decomposition-based evolutionary algorithm has become an increasingly popular choice for posterior multiobjective optimization. Facing the challenges of an increasing number of objectives, many techniques have been developed which help to balance the convergence and diversity. Nevertheless, according to a recent study by Ishibuchi et al., due to the predefined search directions toward the ideal point, their performance strongly depends on the Pareto front (PF) shapes, especially the orientation of the PFs. To balance the convergence and diversity for decomposition-based methods and to alleviate their performance dependence on the orientation of the PFs, this paper develops an adversarial decomposition method for many-objective optimization, which leverages the complementary characteristics of different subproblem formulations within a single paradigm. More specifically, two populations are co-evolved by two subproblem formulations with different contours and adversarial search directions. To avoid allocating redundant computational resources to the same region of the PF, the two populations are matched into one-to-one solution pairs according to their working regions upon the PF. Each solution pair can at most contribute one principal mating parent during the mating selection process. When comparing nine state-of-the-art many-objective optimizers, we have witnessed the competitive performance of our proposed algorithm on 130 many-objective test problems with various characteristics, including regular and inverted PFs.

Large-scale optimization with high dimensionality and high computational cost becomes ubiquitous nowadays. To tackle such challenging problems efficiently, devising distributed evolutionary computation algorithms is imperative. To this end, this paper proposes a distributed swarm optimizer based on a special master-slave model. Specifically, in this distributed optimizer, the master is mainly responsible for communication with slaves, while each slave iterates a swarm to traverse the solution space. An asynchronous and adaptive communication strategy based on the request-response mechanism is especially devised to let the slaves communicate with the master efficiently. Particularly, the communication between the master and each slave is adaptively triggered during the iteration. To aid the slaves to search the space efficiently, an elite-guided learning strategy is especially designed via utilizing elite particles in the current swarm and historically best solutions found by different slaves to guide the update of particles. Together, this distributed optimizer asynchronously iterates multiple swarms to collaboratively seek the optimum in parallel. Extensive experiments on a widely used large-scale benchmark set substantiate that the distributed optimizer could: 1) achieve competitive effectiveness in terms of solution quality as compared to the state-of-the-art large-scale methods; 2) accelerate the execution of the algorithm in comparison with the sequential one and obtain almost linear speedup as the number of cores increases; and 3) preserve a good scalability to solve higher dimensional problems.

Supply chain network design (SCND) is a complicated constrained optimization problem that plays a significant role in the business management. This article extends the SCND model to a large-scale SCND with uncertainties (LUSCND), which is more practical but also more challenging. However, it is difficult for traditional approaches to obtain the feasible solutions in the large-scale search space within the limited time. This article proposes a cooperative coevolutionary bare-bones particle swarm optimization (CCBBPSO) with function independent decomposition (FID), called CCBBPSO-FID, for a multiperiod three-echelon LUSCND problem. For the large-scale issue, binary encoding of the original model is converted to integer encoding for dimensionality reduction, and a novel FID is designed to efficiently decompose the problem. For obtaining the feasible solutions, two repair methods are designed to repair the infeasible solutions that appear frequently in the LUSCND problem. A step translation method is proposed to deal with the variables out of bounds, and a labeled reposition operator with adaptive probabilities is designed to repair the infeasible solutions that violate the constraints. Experiments are conducted on 405 instances with three different scales. The results show that CCBBPSO-FID has an evident superiority over contestant algorithms.

The multimodal optimization problem (MMOP) requires the algorithm to find multiple global optima of the problem simultaneously. In order to solve MMOP efficiently, a novel differential evolution (DE) algorithm based on the local binary pattern (LBP) is proposed in this paper. The LBP makes use of the neighbors' information for extracting relevant pattern information, so as to identify the multiple regions of interests, which is similar to finding multiple peaks in MMOP. Inspired by the principle of LBP, this paper proposes an LBP-based adaptive DE (LBPADE) algorithm. It enables the LBP operator to form multiple niches, and further to locate multiple peak regions in MMOP. Moreover, based on the LBP niching information, we develop a niching and global interaction (NGI) mutation strategy and an adaptive parameter strategy (APS) to fully search the niching areas and maintain multiple peak regions. The proposed NGI mutation strategy incorporates information from both the niching and the global areas for effective exploration, while APS adjusts the parameters of each individual based on its own LBP information and guides the individual to the promising direction. The proposed LBPADE algorithm is evaluated on the extensive MMOPs test functions. The experimental results show that LBPADE outperforms or at least remains competitive with some state-of-the-art algorithms.

Multi-solution problems extensively exist in practice. Particularly, the traveling salesman problem (TSP) may possess multiple shortest tours, from which travelers can choose one according to their specific requirements. However, very few efforts have been devoted to the multi-solution problems in the discrete domain. In order to fill this research gap and to effectively tackle the multi-solution TSP, we propose a niching memetic algorithm in this article. The proposed algorithm is characterized by a niche preservation technique to enable the parallel search of multiple optimal solutions; an adaptive neighborhood strategy to balance the exploration and exploitation; a critical edge-aware method to provide effective guidance to the reproduction; and a selective local search strategy to improve the search efficiency. To evaluate the performance of the proposed algorithm, we conduct comprehensive experiments on a recently published multi-solution optimization test suite. The experimental results show that our algorithm outperforms other compared algorithms. Furthermore, the proposed algorithm is adopted to tackle problems from the well-known TSPLIB library to obtain a set of distinct but good solutions.

Niching techniques have been widely incorporated into evolutionary algorithms (EAs) for solving multimodal optimization problems (MMOPs). However, most of the existing niching techniques are either sensitive to the niching parameters or require extra fitness evaluations (FEs) to maintain the niche detection accuracy. In this paper, we propose a new automatic niching technique based on the affinity propagation clustering (APC) and design a novel niching differential evolution (DE) algorithm, termed as automatic niching DE (ANDE), for solving MMOPs. In the proposed ANDE algorithm, APC acts as a parameter-free automatic niching method that does not need to predefine the number of clusters or the cluster size. Also, it can facilitate locating multiple peaks without extra FEs. Furthermore, the ANDE algorithm is enhanced by a contour prediction approach (CPA) and a two-level local search (TLLS) strategy. First, the CPA is a predictive search strategy. It exploits the individual distribution information in each niche to estimate the contour landscape, and then predicts the rough position of the potential peak to help accelerate the convergence speed. Second, the TLLS is a solution refine strategy to further increase the solution accuracy after the CPA roughly predicting the peaks. Compared with the other state-of-the-art DE and non-DE multimodal algorithms, even the winner of competition on multimodal optimization, the experimental results on 20 widely used benchmark functions illustrate the superiority of the proposed ANDE algorithm.

The temporal flicker distortion is one of the most annoying noises in synthesized virtual view videos when they are rendered by compressed multi-view video plus depth in Three Dimensional (3D) video system. To assess the synthesized view video quality and further optimize the compression techniques in 3D video system, objective video quality assessment which can accurately measure the flicker distortion is highly needed. In this paper, we propose a full reference sparse representation based video quality assessment method towards synthesized 3D videos. Firstly, a synthesized video, treated as a 3D volume data with spatial (X-Y) and temporal (T) domains, is reformed and decomposed as a number of spatially neighboring temporal layers, i.e., X-T or Y-T planes. Gradient features in temporal layers of the synthesized video and strong edges of depth maps are used as key features in detecting the location of flicker distortions. Secondly, dictionary learning and sparse representation for the temporal layers are then derived and applied to effectively represent the temporal flicker distortion. Thirdly, a rank pooling method is used to pool all the temporal layer scores and obtain the score for the flicker distortion. Finally, the temporal flicker distortion measurement is combined with the conventional spatial distortion measurement to assess the quality of synthesized 3D videos. Experimental results on synthesized video quality database demonstrate our proposed method is significantly superior to other state-of-the-art methods, especially on the view synthesis distortions induced from depth videos.

Underwater image enhancement has been attracting much attention due to its significance in marine engineering and aquatic robotics. Numerous underwater image enhancement algorithms have been proposed in the last few years. However, these algorithms are mainly evaluated using either synthetic datasets or few selected real-world images. It is thus unclear how these algorithms would perform on images acquired in the wild and how we could gauge the progress in the field. To bridge this gap, we present the first comprehensive perceptual study and analysis of underwater image enhancement using large-scale real-world images. In this paper, we construct an Underwater Image Enhancement Benchmark (UIEB) including 950 real-world underwater images, 890 of which have the corresponding reference images. We treat the rest 60 underwater images which cannot obtain satisfactory reference images as challenging data. Using this dataset, we conduct a comprehensive study of the state-of-the-art underwater image enhancement algorithms qualitatively and quantitatively. In addition, we propose an underwater image enhancement network (called Water-Net) trained on this benchmark as a baseline, which indicates the generalization of the proposed UIEB for training Convolutional Neural Networks (CNNs). The benchmark evaluations and the proposed Water-Net demonstrate the performance and limitations of state-of-the-art algorithms, which shed light on future research in underwater image enhancement. The dataset and code are available at.

Picture Wise Just Noticeable Difference (PW-JND), which accounts for the minimum difference of a picture that human visual system can perceive, can be widely used in perception-oriented image and video processing. However, the conventional Just Noticeable Difference (JND) models calculate the JND threshold for each pixel or sub-band separately, which may not reflect the total masking effect of a picture accurately. In this paper, we propose a deep learning based PW-JND prediction model for image compression. Firstly, we formulate the task of predicting PW-JND as a multi-class classification problem, and propose a framework to transform the multi-class classification problem to a binary classification problem solved by just one binary classifier. Secondly, we construct a deep learning based binary classifier named perceptually lossy/lossless predictor which can predict whether an image is perceptually lossy to another or not. Finally, we propose a sliding window based search strategy to predict PW-JND based on the prediction results of the perceptually lossy/lossless predictor. Experimental results show that the mean accuracy of the perceptually lossy/lossless predictor reaches 92%, and the absolute prediction error of the proposed PW-JND model is 0.79 dB on average, which shows the superiority of the proposed PW-JND model to the conventional JND models.

Improving the aesthetic quality of images is challenging and eager for the public. To address this problem, most existing algorithms are based on supervised learning methods to learn an automatic photo enhancer for paired data, which consists of low-quality photos and corresponding expert-retouched versions. However, the style and characteristics of photos retouched by experts may not meet the needs or preferences of general users. In this paper, we present an unsupervised image enhancement generative adversarial network (UEGAN), which learns the corresponding image-to-image mapping from a set of images with desired characteristics in an unsupervised manner, rather than learning on a large number of paired images. The proposed model is based on single deep GAN which embeds the modulation and attention mechanisms to capture richer global and local features. Based on the proposed model, we introduce two losses to deal with the unsupervised image enhancement: (1) fidelity loss, which is defined as a l2 regularization in the feature domain of a pre-trained VGG network to ensure the content between the enhanced image and the input image is the same, and (2) quality loss that is formulated as a relativistic hinge adversarial loss to endow the input image the desired characteristics. Both quantitative and qualitative results show that the proposed model effectively improves the aesthetic quality of images.

The raw video data can be compressed much by the latest video coding standard, high efficiency video coding (HEVC). However, the block-based hybrid coding used in HEVC will incur lots of artifacts in compressed videos, the video quality will be severely influenced. To settle this problem, the in-loop filtering is used in HEVC to eliminate artifacts. Inspired by the success of deep learning, we propose an efficient in-loop filtering algorithm based on the enhanced deep convolutional neural networks (EDCNN) for significantly improving the performance of in-loop filtering in HEVC. Firstly, the problems of traditional convolutional neural networks models, including the normalization method, network learning ability, and loss function, are analyzed. Then, based on the statistical analyses, the EDCNN is proposed for efficiently eliminating the artifacts, which adopts three solutions, including a weighted normalization method, a feature information fusion block, and a precise loss function. Finally, the PSNR enhancement, PSNR smoothness, RD performance, subjective test, and computational complexity/GPU memory consumption are employed as the evaluation criteria, and experimental results show that when compared with the filter in HM16.9, the proposed in-loop filtering algorithm achieves an average of 6.45% BDBR reduction and 0.238 dB BDPSNR gains.

The flexible partitioning structure such as quad-tree plus binary-tree (QTBT) plays important roles in the next generation video coding standard. This paper investigates new coding unit (CU) partitioning methods to further improve the compression efficiency. In particular, we propose the extended quad-tree partitioning and asymmetric ternary-tree partitioning to further develop the principle behind the existing partitioning structure. First, a central extended quad-tree (CENTRAL-EQT) partitioning is introduced, which extends the traditional QT partitioning with central pattern and generates four elaborately designed sub-CUs with different sizes. Second, we propose a parallel extended quad-tree (PARALLEL-EQT) partitioning that allows the CU to split along a single direction, leading to four identical size sub-blocks. Third, we present an asymmetric ternary-tree (ATT) method, which splits the CU asymmetrically into three sub-blocks. The proposed new partitioning methods allow the interleaving with binary-tree partitioning for enhanced adaptability, and they can be jointly enabled to capture different characteristics of the local content. Simulation results on the JEM7-QTBT-Only platform show that averagely 4.92%, 4.81% and 5.08% BD-Rate savings are achieved for the luma component by the proposed methods under random access (RA), low-delay P (LDP) and low-delay B (LDB) configurations, respectively, with around 725% encoding time increase and negligible decoding time increase. Furthermore, experimental results also reveal that the proposed partitioning schemes are effective when cooperating with the upcoming Versatile Video Coding standard.

In this paper, we devise a saliency prediction model for stereoscopic videos that learns to explore saliency inspired by the component-based interactions including spatial, temporal, as well as depth cues. The model first takes advantage of specific structure of 3D residual network (3D-ResNet) to model the saliency driven by spatio-temporal coherence from consecutive frames. Subsequently, the saliency inferred by implicit-depth is automatically derived based on the displacement correlation between left and right views by leveraging a deep convolutional network (ConvNet). Finally, a component-wise refinement network is devised to produce final saliency maps over time by aggregating saliency distributions obtained from multiple components. In order to further facilitate research towards stereoscopic video saliency, we create a new dataset including 175 stereoscopic video sequences with diverse content, as well as their dense eye fixation annotations. Extensive experiments support that our proposed model can achieve superior performance compared to the state-of-the-art methods on all publicly available eye fixation datasets.

In this paper, we propose a just noticeable distortion (JND)-based perceptual rate control method for high efficiency video coding (HEVC). First, the JND factor of a coding unit has been mathematically shown to be an approximation of the average pixel-level JND weight, which means that it can also be used as a weight for bitrate allocation. Second, rate-distortion (R-D) modelling is conducted based on the JND factor. Finally, the proposed R-D model is integrated into an existing rate control framework to improve the coding efficiency, and the proposed algorithm is implemented in the newest video coding standard. As the experimental results reveal, compared with HEVC reference software, our algorithm achieves significantly improved coding performance, subjective coding quality and bitrate accuracy.

In this paper, a novel intra prediction method is proposed to improve the video coding performance, in which the generative adversarial network (GAN) is adopted to intelligently remove the spatial redundancy with the inference process. The proposed GAN-based method improves the prediction by exploiting more information and generating more flexible prediction patterns. In particular, the intra prediction is modeled as an inpainting task, which is accomplished with the GAN model to fill in the missing part by conditioning on the available reconstructed pixels. As such, the learned GAN model is incorporated into both video encoder and decoder, and the rate-distortion optimization is performed for the competition between GAN-based intra prediction and traditional angular-based intra prediction to achieve better coding performance. The proposed scheme is implemented into the high-efficiency video coding test model (HM 16.17) and the versatile video coding test model (VTM 1.1). The experimental results show that the proposed algorithm can achieve 6.6%, 7.5%, and 7.5% under HM 16.17 and 6.75%, 7.63%, and 7.65% under VTM 1.1 bit rate savings on average for luma and chroma components in the intra coding scenario.

In this article, we propose a semi-supervised non-negative matrix factorization (NMF) model by means of elegantly modeling the label information. The proposed model is capable of generating discriminable low-dimensional representations to improve clustering performance. Specifically, a pair of complementary regularizers, i.e., similarity and dissimilarity regularizers, is incorporated into the conventional NMF to guide the factorization. And, they impose restrictions on both the similarity and dissimilarity of the low-dimensional representations of data samples with labels as well as a small number of unlabeled ones. The proposed model is formulated as a well-posed constrained optimization problem and further solved with an efficient alternating iterative algorithm. Moreover, we theoretically prove that the proposed algorithm can converge to a limiting point that meets the Karush-Kuhn-Tucker conditions. Extensive experiments as well as comprehensive analysis demonstrate that the proposed model outperforms the state-of-the-art NMF methods to a large extent over five benchmark data sets, i.e., the clustering accuracy increases to 82.2% from 57.0%.

Pairwise constraints (PCs) composed of must-links (MLs) and cannot-links (CLs) are widely used in many semisupervised tasks. Due to the limited number of PCs, pairwise constraint propagation (PCP) has been proposed to augment them. However, the existing PCP algorithms only adopt a single matrix to contain all the information, which overlooks the differences between the two types of links such that the discriminability of the propagated PCs is compromised. To this end, this article proposes a novel PCP model via dual adversarial manifold regularization to fully explore the potential of the limited initial PCs. Specifically, we propagate MLs and CLs with two separated variables, called similarity and dissimilarity matrices, under the guidance of the graph structure constructed from data samples. At the same time, the adversarial relationship between the two matrices is taken into consideration. The proposed model is formulated as a nonnegative constrained minimization problem, which can be efficiently solved with convergence theoretically guaranteed. We conduct extensive experiments to evaluate the proposed model, including propagation effectiveness and applications on constrained clustering and metric learning, all of which validate the superior performance of our model to state-of-the-art PCP models.

In dynamic optimization problems (DOPs), as the environment changes through time, the optima also dynamically change. How to adapt to the dynamic environment and quickly find the optima in all environments is a challenging issue in solving DOPs. Usually, a new environment is strongly relevant to its previous environment. If we know how it changes from the previous environment to the new one, then we can transfer the information of the previous environment, e.g., past solutions, to get new promising information of the new environment, e.g., new high-quality solutions. Thus, in this paper, we propose a neural network (NN)-based information transfer method, named NNIT, to learn the transfer model of environment changes by NN and then use the learned model to reuse the past solutions. When the environment changes, NNIT first collects the solutions from both the previous environment and the new environment and then uses an NN to learn the transfer model from these solutions. After that, the NN is used to transfer the past solutions to new promising solutions for assisting the optimization in the new environment. The proposed NNIT can be incorporated into population-based evolutionary algorithms (EAs) to solve DOPs. Several typical state-of-the-art EAs for DOPs are selected for comprehensive study and evaluated using the widely used moving peaks benchmark. The experimental results show that the proposed NNIT is promising and can accelerate algorithm convergence.

Rate control plays an important role in high efficiency video coding (HEVC), and bit allocation is the foundation of rate control. The video content characteristics are significant for bit allocation, and modeling an accurate relationship between video content characteristics and bit allocation is essential for bit allocation optimization. Therefore, in this article, a video content characteristics–based frame-level optimal bit allocation algorithm is proposed for improving the rate distortion (RD) performance of HEVC. First, the number of search points of motion estimation is used to evaluate the motion activity of video content, and the relationship between the search points and bit allocation is modeled as the search-points model. Second, the grey level co-occurrence matrix and temporal perceptual information are used to evaluate the spatial and temporal texture complexity, and the relationship between the video content texture complexity and bit allocation is modeled as the texture-complexity model. Then, the search-points model and texture-complexity model are jointly employed to allocate the coding bits for the second and third layers of the HEVC hierarchical coding structure. Finally, the remaining coding bits of a group-of-pictures (GOP) are allocated to the first layer of HEVC coding structure. To evaluate the performance of the proposed algorithm, the RD performance and bitrate accuracy are used as evaluation criteria, and the experimental results show that when compared with the popularly used R-λ model–based bit allocation algorithm, the proposed algorithm achieves an average of -3.43% BDBR reduction and 0.13 dB BDPSNR gains with only 0.02% loss of bitrate accuracy.

The learning algorithm of an extreme learning machine (ELM) has two fundamental steps: 1) random nonlinear feature transformation and 2) least squares learning. Since the probabilistic interpretation for a sample by the least squares method follows a Gaussian distribution, there are two limitations in ELM caused by the second step: 1) it may be inaccurate to handle binary classification problems, since the output of a binary dataset has a distribution far from Gaussian and 2) it may have difficulties in dealing with nontraditional data types (such as count data, ordinal data, etc.), which also do not follow Gaussian distribution. In order to solve the above-mentioned problems, this paper proposes a generalized ELM (GELM) framework by applying the exponential family distribution (EFD) to the output layer node of ELM. It simplifies the design of ELM models for task-specific output domains with different data types. We propose a unified learning paradigm for all the models under this GELM framework with different distributions in EFD, and prove that traditional ELM is a special instance of GELM by setting the output distribution as a Gaussian distribution (GELM-Gaussian). We also prove that the training of GELM-Gaussian can be finished in one iteration, in this case, GELM-Gaussian does not slow down the training speed of traditional ELM. Besides, we propose the kernel version of GELM, which can also be concretized to different models by applying different EFDs. Experimental comparisons demonstrate that GELM can give more accurate probabilistic interpretation to binary classification and GELM has a great potential in dealing with a broader range of machine learning tasks.

The human visual system excels at biasing the stereoscopic visual signals by the attention mechanisms. Traditional methods relying on the low-level features and depth relevant information for stereoscopic video saliency prediction have fundamental limitations. For example, it is cumbersome to model the interactions between multiple visual cues including spatial, temporal, and depth information as a result of the sophistication. In this paper, we argue that the high-level features are crucial and resort to the deep learning framework to learn the saliency map of stereoscopic videos. Driven by spatio-temporal coherence from consecutive frames, the model first imitates the mechanism of saliency by taking advantage of the 3D convolutional neural network. Subsequently, the saliency originated from the intrinsic depth is derived based on the correlations between left and right views in a data-driven manner. Finally, a Convolutional Long Short-Term Memory (Conv-LSTM) based fusion network is developed to model the instantaneous interactions between spatio-temporal and depth attributes, such that the ultimate stereoscopic saliency maps over time are produced. Moreover, we establish a new large-scale stereoscopic video saliency dataset (SVS) including 175 stereoscopic video sequences and their fixation density annotations, aiming to comprehensively study the intrinsic attributes for stereoscopic video saliency detection. Extensive experiments show that our proposed model can achieve superior performance compared to the state-of-the-art methods on the newly built dataset for stereoscopic videos.

The quad-tree plus binary-tree (QTBT) coding unit (CU) partitioning structure, which has been adopted to the next generation video coding standard, shows promising coding performance when compared with the conventional quad-tree structure in HEVC. In this paper, we propose the Extended Quad-tree (EQT) partitioning, which further extends the QTBT scheme and increases the partitioning exibility. More specifcally, EQT splits a parent CU into four sub-CUs of dierent sizes, which can adequately model the local image content that cannot be elaborately characterized with QTBT. Meanwhile, EQT partitioning allows the interleaving with BT partitioning for enhanced adaptability. Experimental results on the JEM7-QTBT-Only platform show that EQT brings better coding performance with 3.17%, 3.20% and 3.06% BD-Rate gains under random access, low-delay P and low-delay B configurations, respectively.

The Screen Content Coding (SCC) is an extension of High Efficiency Video Coding (HEVC), and it achieves significant improvement on compression ratio. However, the obtained coding efficiency is at the cost of high computational complexity. In this paper, to reduce the computation complexity, we propose to use an ensemble classifier for predicting the coding unit (CU) in intra-coding. Firstly, the L1-loss based linear support vector machine (SVM) is employed as basic classifier for its simplicity. Then, a bagging scheme is applied to train the linear classifiers and boost the prediction accuracy by ensemble learning. Compared with the reference software SCM-5.0, the proposed scheme can achieve 30% complexity reduction on average with only 1.64% bit rates increase.

Compressed image quality assessment plays an important role in image services, especially in image compression applications, which can be utilized as a guidance to optimize image processing algorithms. In this paper, we propose an objective image quality assessment algorithm to measure the quality of compressed images. The proposed method utilizes a data-driven transform, Saak (Subspace approximation with augmented kernels), to decompose images into hierarchical structural feature space. We measure the distortions of Saak features and accumulate these distortions according to the feature importance to human visual system. Compared with the state-of-the-art image quality assessment methods on widely utilized datasets, the proposed method correlates better with the subjective results. In addition, the proposed methods achieves more robust results on different datasets.

Multi-task learning is a powerful method for solving multiple correlated tasks simultaneously. However, it is often impossible to find one single solution to optimize all the tasks, since different tasks might conflict with each other. Recently, a novel method is proposed to find one single Pareto optimal solution with good trade-off among different tasks by casting multi-task learning as multiobjective optimization. In this paper, we generalize this idea and propose a novel Pareto multi-task learning algorithm (Pareto MTL) to find a set of well-distributed Pareto solutions which can represent different trade-offs among different tasks. The proposed algorithm first formulates a multi-task learning problem as a multiobjective optimization problem, and then decomposes the multiobjective optimization problem into a set of constrained subproblems with different trade-off preferences. By solving these subproblems in parallel, Pareto MTL can find a set of well-representative Pareto optimal solutions with different trade-off among all tasks. Practitioners can easily select their preferred solution from these Pareto solutions, or use different trade-off solutions for different situations. Experimental results confirm that the proposed algorithm can generate well-representative solutions and outperform some state-of-the-art algorithms on many multi-task learning applications.

Most of current hashing methods are proposed based on the assumption that the database is stationary. However, this assumption is not always true as the data environment is sometimes non-stationary. When new images being added to the database, data distributions of existing classes may change and new classes may also appear which result in concept drifts. The problem of concept drifts is unavoidable in non-stationary data environments. Incremental Hashing (ICH) is an effective method for image retrieval in non-stationary data environments with concept drifts using multiple hash tables. In ICH, new concept is adapted by training new hash table using the most updated data chunks. However, images in the new data chunk may not be all informative for updating. To enhance the efficiency of ICH, ICH with Undersampling (ICHUS) is proposed to select informative samples in the new data chunk for the training of new hash table to adapt to the non-stationary data environment. Experimental results show that ICHUS yields a better retrieval performance than ICH and state-of-art non-stationary hashing methods.

Pathway similarity search plays a vital role in the post-genomics era. Unfortunately, pathway similarity search involves the graph isomorphism problem which is NP-complete. Therefore, efficient search algorithms are desirable. In this work, we propose a novel global pathway similarity search approach named ToBio, which considers both topological and biological features for effective global pathway similarity search. Specifically, as motivated from nature, various topological and biological features including subgraph signature similarities, sequence similarities, and gene ontology similarities are considered in ToBio. Since different features carry different functional importance and dependences, we report three schemes of ToBio using different sets of features. In addition, to enhance the existing search algorithms for rigorous comparisons, post-processing pipelines are also proposed to investigate how different features can contribute to the search performance. ToBio and other state-of-the-art methods are benchmarked on the gold-standard pathway datasets from three species. The results demonstrate the competitive edges of ToBio over the state-of-the-arts ranging from the topological aspects to the biological aspects. Case studies have been conducted to reveal mechanistic insights into the unique search performance of ToBio.

In this paper, we introduce a closed-form sparse Bayesian kernel Poisson regression (SBKPR) model for count data regression problems based on the sparse Bayesian learning (SBL) approach. In Bayesian setting, a Gaussian prior is given to the model parameter, which is not the conjugate distribution of Poisson regression. Hence, the model parameters cannot be integrated analytically, which leads to the inference intractable problem. In this paper, the log-gamma Gaussian approximation method is proposed to solve this analytically intractable problem, which can give out the closed-form solutions. Furthermore, an individual Gaussian prior is given to the model parameters, which can enhance the flexibility of the proposed method. Finally, sparse solutions can be obtained by applying SBL, which can benefit the learning efficiency and reduce the computational time in practical applications. Experimental results demonstrate that the proposed SBKPR model can outperform some state-of-the-art count data regression models on both toy data and real-world data.

This paper develops a decomposition-based coevolutionary algorithm for many-objective optimization, which evolves a number of subpopulations in parallel for approaching the set of Pareto optimal solutions. The many-objective problem is decomposed into a number of subproblems using a set of well-distributed weight vectors. Accordingly, each subpopulation of the algorithm is associated with a weight vector and is responsible for solving the corresponding subproblem. The exploration ability of the algorithm is improved by using a mating pool that collects elite individuals from the cooperative subpopulations for breeding the offspring. In the subsequent environmental selection, the top-ranked individuals in each subpopulation, which are appraised by aggregation functions, survive for the next iteration. Two new aggregation functions with distinct characteristics are designed in this paper to enhance the population diversity and accelerate the convergence speed. The proposed algorithm is compared with several state-of-the-art many-objective evolutionary algorithms on a large number of benchmark instances, as well as on a real-world design problem. Experimental results show that the proposed algorithm is very competitive.

Through introducing the divide-and-conquer strategy, cooperative co-evolution (CC) has been successfully employed by many evolutionary algorithms (EAs) to solve large-scale optimization problems. In practice, it is common that different subcomponents of a large-scale problem have imbalanced contributions to the global fitness. Thus, how to utilize such imbalance and concentrate efforts on optimizing important subcomponents becomes an important issue for improving performance of cooperative co-EA, especially in distributed computing environment. In this paper, we propose a two-layer distributed CC (dCC) architecture with adaptive computing resource allocation for large-scale optimization. The first layer is the dCC model which takes charge of calculating the importance of subcomponents and accordingly allocating resources. An effective allocating algorithm is designed which can adaptively allocate computing resources based on a periodic contribution calculating method. The second layer is the pool model which takes charge of making fully utilization of imbalanced resource allocation. Within this layer, two different conformance policies are designed to help optimizers use the assigned computing resources efficiently. Empirical studies show that the two conformance policies and the computing resource allocation algorithm are effective, and the proposed distributed architecture possesses high scalability and efficiency.

The application of multiobjective evolutionary algorithms to many-objective optimization problems often faces challenges in terms of diversity and convergence. On the one hand, with a limited population size, it is difficult for an algorithm to cover different parts of the whole Pareto front (PF) in a large objective space. The algorithm tends to concentrate only on limited areas. On the other hand, as the number of objectives increases, solutions easily have poor values on some objectives, which can be regarded as poor bottleneck objectives that restrict solutions' convergence to the PF. Thus, we propose a coevolutionary particle swarm optimization with a bottleneck objective learning (BOL) strategy for many-objective optimization. In the proposed algorithm, multiple swarms coevolve in distributed fashion to maintain diversity for approximating different parts of the whole PF, and a novel BOL strategy is developed to improve convergence on all objectives. In addition, we develop a solution reproduction procedure with both an elitist learning strategy (ELS) and a juncture learning strategy (JLS) to improve the quality of archived solutions. The ELS helps the algorithm to jump out of local PFs, and the JLS helps to reach out to the missing areas of the PF that are easily missed by the swarms. The performance of the proposed algorithm is evaluated using two widely used test suites with different numbers of objectives. Experimental results show that the proposed algorithm compares favorably with six other state-of-the-art algorithms on many-objective optimization.

Insurance has been increasingly realized as an important way of investment and risk aversion.Fruitful insurance products are launched by insurers, but there is little research on how to make a proper insurance investment plan for a specific policyholder given different kinds of policies.In this paper, we aim to propose a practical approach to multipolicy insurance investment planning with a data-driven model and an estimation of distribution algorithm (EDA).First, by making use of the insurance data accumulated in the modern financial market, an optimization model about how to choose endowment and hospitalization policies is built to maximize the yearly profit of insurance investment.With the model parameters set according to the real data from insurance market, the resulting plan is practical and individualized.Second, as the optimal solution cannot be achieved by mathematical deduction under this datadriven model, an EDA is introduced.To adapt the EDA for the considered problem, the proposed EDA is mixed with both the continuous and discrete probability distribution models to handle different kinds of variables.In addition, an adaptive scheme for choosing suitable distribution models and an efficient constraint handling strategy are proposed.Experiments under different conditions confirm the effectiveness and efficiency of the proposed model and method.

The decomposition-based evolutionary multiobjective optimization (EMO) algorithm has become an increasingly popular choice for a posteriori multiobjective optimization. However, recent studies have shown that their performance strongly depends on the Pareto front (PF) shapes. This can be attributed to the decomposition method, of which the reference points and subproblem formulation settings are not well adaptable to various problem characteristics. In this paper, we develop a learning-to-decompose (LTD) paradigm that adaptively sets the decomposition method by learning the characteristics of the estimated PF. Specifically, it consists of two interdependent parts, i.e., a learning module and an optimization module. Given the current nondominated solutions from the optimization module, the learning module periodically learns an analytical model of the estimated PF. Thereafter, useful information is extracted from the learned model to set the decomposition method for the optimization module: 1) reference points compliant with the PF shape and 2) subproblem formulations whose contours and search directions are appropriate for the current status. Accordingly, the optimization module, which can be any decomposition-based EMO algorithm in principle, decomposes the multiobjective optimization problem into a number of subproblems and optimizes them simultaneously. To validate our proposed LTD paradigm, we integrate it with two decomposition-based EMO algorithms, and compare them with four state-of-the-art algorithms on a series of benchmark problems with various PF shapes.

The cooperative coevolution (CC) framework achieves a promising performance in solving large scale global optimization problems. The framework encounters difficulties on nonseparable problems, where variables interact with each other. Using the static grouping methods, variables will be theoretically grouped into one big subcomponent, whereas the random grouping strategy endures low efficiency. In this paper, a dynamic CC framework is proposed to tackle the challenge. The proposed framework works in a computationally efficient manner, in which the computational resources are allocated to a series of elitist subcomponents consisting of superior variables. First, a novel estimation method is proposed to evaluate the contribution of variables using the historical information of the best overall fitness. Based on the contribution and the interaction information, a dynamic grouping strategy is conducted to construct the dynamic subcomponent that evolves in the next evolutionary period. The constructed subcomponents are different from each other, and therefore the required parameters to control the optimization of each subcomponent vary a lot in each evolutionary period. A stage-by-stage parameter adaptation strategy is proposed to adapt the optimizer to the dynamic optimization environment. Experimental results indicate that the proposed framework achieves competitive results compared with the state-of-the-art CC frameworks.

Arising from the various object types and scales, diverse imaging orientations, and cluttered backgrounds in optical remote sensing image (RSI), it is difficult to directly extend the success of salient object detection for nature scene image to the optical RSI. In this paper, we propose an end-to-end deep network called LV-Net based on the shape of network architecture, which detects salient objects from optical RSIs in a purely data-driven fashion. The proposed LV-Net consists of two key modules, i.e., a two-stream pyramid module (L-shaped module) and an encoder-decoder module with nested connections (V-shaped module). Specifically, the L-shaped module extracts a set of complementary information hierarchically by using a two-stream pyramid structure, which is beneficial to perceiving the diverse scales and local details of salient objects. The V-shaped module gradually integrates encoder detail features with decoder semantic features through nested connections, which aims at suppressing the cluttered backgrounds and highlighting the salient objects. In addition, we construct the first publicly available optical RSI data set for salient object detection, including 800 images with varying spatial resolutions, diverse saliency types, and pixel-wise ground truth. Experiments on this benchmark data set demonstrate that the proposed method outperforms the state-of-the-art salient object detection methods both qualitatively and quantitatively.

The artificial bee colony is a popular evolutionary algorithm that exhibits strong exploration ability but slow convergence. This paper proposes two new updating equations to boost the performances of employed and onlooker bees, respectively. In the new updating equations, two intelligent learning strategies give bees a chance to learn from individuals with better performances. New control operators are also utilized to balance global and local searches. Second, we define a new search direction mechanism to overcome the oscillation phenomenon in employed bees. Finally, an intelligent learning mechanism is proposed to accelerate the convergence rate of the worst employed bee. To test the effectiveness of our algorithm, a series of benchmark functions and two industrial problems are utilized. Experimental results demonstrate that our proposed algorithm performs more favorably on both theoretical and practical problems.

A large number of industrial video applications are expected to work in real-time and power-constrained scenarios. For such applications, the coding complexity has a great impact on their performance. In this paper, we propose a complexity control method in the high-efficiency video coding intracoding to facilitate these video applications. The proposed method is performed on the coding tree unit (CTU) level, which consists of three steps, namely complexity estimation, complexity allocation, and prediction unit (PU) adaption. In the first step, a complexity estimation model is proposed to estimate the coding complexity of each CTU based on the sum of absolute transformed difference. Then, the complexity budget is allocated to each CTU proportionally to its estimated coding complexity. In PU adaption, only a subset of PU sizes are selected for the CTU according to its allocated complexity and prediction performance. A feedback-based error elimination scheme removes the complexity error during the encoding process. Experimental results show that the proposed method is able to adjust the complexity ratio from 100% to 20%. Meanwhile, the rate-distortion performance and complexity control accuracy of the proposed method are superior to those of the state-of-the-art methods.

Nonnegative matrix factorization (NMF) is a well-known paradigm for data representation. Traditional NMF-based classification methods first perform NMF or one of its variants on input data samples to obtain their low-dimensional representations, which are successively classified by means of a typical classifier [e.g., k -nearest neighbors (KNN) and support vector machine (SVM)]. Such a stepwise manner may overlook the dependency between the two processes, resulting in the compromise of the classification accuracy. In this paper, we elegantly unify the two processes by formulating a novel constrained optimization model, namely dual embedding regularized NMF (DENMF), which is semi-supervised. Our DENMF solution simultaneously finds the low-dimensional representations and assignment matrix via joint optimization for better classification. Specifically, input data samples are projected onto a couple of low-dimensional spaces (i.e., feature and label spaces), and locally linear embedding is employed to preserve the identical local geometric structure in different spaces. Moreover, we propose an alternating iteration algorithm to solve the resulting DENMF, whose convergence is theoretically proven. Experimental results over five benchmark datasets demonstrate that DENMF can achieve higher classification accuracy than state-of-the-art algorithms.

Pathway analysis is a cornerstone of system biology. In particular, pathway similarity search plays a key role in establishing structural, functional, and evolutionary relationships between different biological entities. Given a query pathway as well as a database, a pathway similarity search aims to identify novel pathways that are homologous to the query pathway. Unfortunately, the pathway similarity search is computationally inefficient due to the NP-complete graph isomorphism problem. In this study, we introduce a novel algorithmic framework for pathway similarity search, named PathEmb (Pathway Embedding), which is analogous to the Skip-gram model where each pathway is represented as a "document." PathEmb exploits a second order random walk strategy to explore diverse pathway patterns. All signaling paths traversed from random walks are regarded as "sentences," which are constituted as a "document" afterwards. Then, the "document" pattern for the individual pathway is mapped into a low-dimensional feature space for downstream tasks. Furthermore, PathEmb is a topology-free pathway similarity search algorithm, which is feasible to handle any pathway with arbitrary structure. We have extensively evaluated PathEmb and other cutting-edge methods on three pathway datasets. The experimental results demonstrate that PathEmb outperforms the existing methods in terms of computational efficiency and search accuracy. The source code of PathEmb are freely available online https://github.com/zhangjiaobxy/PathEmb.

Superpixel segmentation aims at grouping discretizing pixels into high-level correlative units and reducing the complexity of subsequent tasks, e.g., saliency detection and object tracking. Existing superpixel segmentation algorithms mainly focus on maintaining the geometrical information, while neglecting the irregular structure of superpixels. In this paper, a superpixel segmentation method is proposed to generate approximately structural superpixels with sharp boundary adherence and comprehensive semantic information. The superpixel segmentation is formulated as a square-wise asymmetric partition problem, where the semantic perceptual superpixels are recorded in a square level to preserve abundant semantic information and save storage simultaneously. Moreover, in order to achieve regular-shape superpixel units to better adhere to image boundaries and contours, a combinatorial optimization strategy is devised to achieve an optimal combination of squares and isolated pixels. Experimental comparisons with some state-of-the-art superpixel segmentation methods on the public benchmarks demonstrate the effectiveness of the proposed method quantitatively and qualitatively. In addition, we have applied the method to brain tissue segmentation to illustrate superior performance.

To improve the parallel processing capability of video coding, the emerging high efficiency video coding (HEVC) standard introduces two parallel techniques, i.e., Wavefront Parallel Processing (WPP) andTiles, to make it much more parallel-friendly than its predecessors. However, these two techniques are designed to explore coarse-grained parallelism in HEVC encoding on multicore Central Processing Unit (CPU) platforms. As the computing architecture undergoes a trend toward heterogeneity in the last decade, multi-grained parallel computing methods can be designed to accelerate HEVC encoding on heterogeneous systems. In this paper, a multi-grained parallel solution (MPS) is proposed to optimize HEVC encoding on a typical heterogeneous platform. A massively parallel motion estimation algorithm is employed by MPS to parallelize part of HEVC encoding on Graphic Processing Unit (GPU). Meanwhile, several other HEVC encoding modules are accelerated on CPU through the cooperation of WPP and an adaptive parallel mode decision algorithm. The parallelism between CPU and GPU is well designed and implemented to guarantee an efficient concurrent execution of HEVC encoding on multi-grained parallel levels. The effectiveness of the proposed MPS for HEVC encoding is verified on a number of experiments.

In this paper, we propose a coding tree unit (CTU)-level rate control scheme from the perspective of SSIM-based rate-distortion optimization to improve the coding efficiency. First, we establish the SSIM-based rate-distortion model based on the divisive normalization scheme, which characterizes the relationship between the local visual quality and the coding bits. Then, the established model is applied to the CTU-level rate control and transformed into a global optimization problem solved by convex optimization. Finally, a new model parameter updating strategy for the CTU-level rate control is presented that is robust to scene variations. Our algorithm can achieve optimal CTU-level bit allocation given the bit-rate budget. The experimental results show that our algorithm substantially enhances the coding performance and consistently outperforms both the rate control scheme in the HEVC reference software and existing algorithms in terms of rate-perceptual distortion performance using different test configurations.

In this article, statistical Early Termination (ET) and Early Skip (ES) models are proposed for fast Coding Unit (CU) and prediction mode decision in HEVC INTRA coding, in which three categories of ET and ES sub-algorithms are included. First, the CU ranges of the current CU are recursively predicted based on the texture and CU depth of the spatial neighboring CUs. Second, the statistical model based ET and ES schemes are proposed and applied to optimize the CU and INTRA prediction mode decision, in which the coding complexities over different decision layers are jointly minimized subject to acceptable rate-distortion degradation. Third, the mode correlations among the INTRA prediction modes are exploited to early terminate the full rate-distortion optimization in each CU decision layer. Extensive experiments are performed to evaluate the coding performance of each sub-algorithm and the overall algorithm. Experimental results reveal that the overall proposed algorithm can achieve 45.47% to 74.77%, and 58.09% on average complexity reduction, while the overall Bjøntegaard delta bit rate increase and Bjøntegaard delta peak signal-to-noise ratio degradation are 2.29% and −0.11 dB, respectively.

For solving multi-label classification problems, traditional random K-labelsets method has two main drawbacks: 1) the randomly selected label set may result in highly imbalanced data for single-label multi-class learning, and 2) the dependency relations among different labels in the same label set may cause serious information redundancy and overlap. Both of these two drawbacks can affect the generalization capability of the multi-label learner. In order to overcome these two problems, in this paper, we propose a K-labelsets ensemble method based on mutual information and joint entropy. First, the mutual information and joint entropy are adopted to evaluate the redundancy level and imbalance level of each K-labelset. Then, disjoint sampling is performed iteratively, where during each iteration, a number of K-labelsets with low mutual information are retained to be the candidates, and the one with the highest joint entropy is selected. Afterwards, for each selected K-labelset, the label powerset method is employed and a multi-class classification model is constructed. Finally, the multi-class models on different K-labelsets are integrated, and a voting based ensemble model is generated to perform the predictions for unseen samples. We conduct extensive experiments on real-world multi-label data sets. Experimental results demonstrate the effectiveness of the proposed method.

High coding complexity is an obstruction when promoting the HEVC standard. In this paper, we propose a complexity control scheme for HEVC, which improves our previous work by employing a finer-grained complexity allocation scheme and mode sorting. In CTU-level complexity allocation, the time budget is allocated to each CTU proportionally to its estimated complexity. Then, the time budget for a CTU is further allocated to each CTU quadtree depth according to its probability of being the dominant depth. At last, a subset of modes are selected to reach the target complexity based on mode sorting. Compared with our previous work of which the least supported complexity ratio is 40%, the proposed scheme further reduces the lower bound of the ratio range to 20%.

In this paper, we propose a new algorithm for constrained clustering, in which a new regularizer elegantly incorporates a small amount of weakly supervisory information in the form of pair-wise constraints to regularize the similarity between the low-dimensional representations of a set of data samples. By exploring both the local and global structures of the data samples with the guidance of the supervisory information, the proposed algorithm is capable of learning the low-dimensional representations with strong separability. Technically, the proposed algorithm is formulated and relaxed as a convex optimization model, which is further efficiently solved with the global convergence guaranteed. Experimental results on multiple benchmark data sets show that our proposed model can produce higher clustering accuracy than state-of-the-art algorithms.

Spectral clustering (SC) is one of the most widely used clustering methods. In this letter, we extend the traditional SC with a semi-supervised manner. Specifically, with the guidance of small amount of supervisory information, we build a matrix with anti-block-diagonal appearance, which is further utilized to regularize the product of the low-dimensional embedding and its transpose. Technically, we formulate the proposed model as a constrained optimization problem. Then, we relax it as a convex problem, which can be efficiently solved with the global convergence guaranteed via the inexact augmented Lagrangian multiplier method. Experimental results over four real-world datasets demonstrate that higher accuracy and normalized mutual information are achieved when compared with state-of-the-art methods.

In the latest video coding standard high efficiency video coding (HEVC), a quadtree-based coding unit (CU) partitioning scheme is adopted to better adapt to the characteristics of the video contents. However, the flexible scheme significantly increases the coding complexity, because large amount of possible CU partitioning modes should be traversed. In this paper, we propose a two-stage fast inter CU decision method to reduce the coding complexity of the HEVC encoders. In Stage I, all the CUs are classified into three categories based on the Bayesian method after the prediction unit (PU) mode merge 2N × 2N is checked. Early CU pruning and early CU skipping are then applied to two of the categories, respectively. For the remaining category which is difficult to differentiate by the rate-distortion cost of the PU mode merge 2N × 2N, an early CU pruning scheme based on conditional random fields is performed in Stage II, which takes both the local characteristics of the current CU and the coding information of its neighboring CUs into consideration. Experimental results show that our method can reduce 54.93% and 45.84% of the coding complexity on average with only 1.19% and 1.03% Bjontegaard delta bitrate increment under the random access main and the low delay P configurations, respectively.

High Efficiency Video Coding (HEVC) INTRA coding improves compression efficiency by adopting advanced coding technologies, such as multi-level quad-tree block partitioning and up to 35-mode INTRA prediction. However, it significantly increases the coding complexity, memory access, and power consumption, which goes against its widely applications, especially for ultra-high definition and/or mobile video applications. To tackle this problem, we propose effective data driven coding unit (CU) size decision approaches for HEVC INTRA coding, which consists of two stages of support vector machine-based fast INTRA CU size decision schemes at four CU decision layers. At the first stage classification, a three output classifier with offline learning is developed to early terminate the CU size decision or early skip checking the current CU depth. As for the samples that neither early skipped nor early terminated, the second stage of binary classification, which learns online from previous coded frames, is proposed to further refine the CU size decision. Representative features for the CU size decision are explored at different decision layers and stages of classifications. Finally, the optimal parameters derived from the training data are achieved to reasonably allocate complexity among different CU layers at given total rate-distortion degradation constraint. Extensive experiments show that the proposed overall algorithm can achieve 27.95%–80.53% and 52.48% on average complexity reduction for the CU size decision as compared with the original HM16.7 model. Meanwhile, the average Bjonteggard delta peak-signal-to-noise ratio degradation is only −0.08 dB, which is negligible. The overall performance of the proposed algorithm outperforms the state-of-the-art benchmark schemes.

Security analysis is a very important issue for digital watermarking. Several years ago, according to Kerckhoffs' principle, the famous four security levels, namely insecurity, key security, subspace security, and stego-security, were defined for spread-spectrum (SS) embedding schemes in the framework of watermarked-only attack. However, up to now there has been little application of the definition of these security levels to the theoretical analysis of the security of SS embedding schemes, due to the difficulty of the theoretical analysis. In this paper, based on the security definition, we present a theoretical analysis to evaluate the security levels of five typical SS embedding schemes, which are the classical SS, the improved SS (ISS), the circular extension of ISS, the nonrobust and robust natural watermarking, respectively. The theoretical analysis of these typical SS schemes are successfully performed by taking advantage of the convolution of probability distributions to derive the probabilistic models of watermarked signals. Moreover, simulations are conducted to illustrate and validate our theoretical analysis. We believe that the theoretical and practical analysis presented in this paper can bridge the gap between the definition of the four security levels and its application to the theoretical analysis of SS embedding schemes.

This paper studies a specific class of multiobjective combinatorial optimization problems (MOCOPs), namely the permutation-based MOCOPs. Many commonly seen MOCOPs, e.g., multiobjective traveling salesman problem (MOTSP), multiobjective project scheduling problem (MOPSP), belong to this problem class and they can be very different. However, as the permutation-based MOCOPs share the inherent similarity that the structure of their search space is usually in the shape of a permutation tree, this paper proposes a generic multiobjective set-based particle swarm optimization methodology based on decomposition, termed MS-PSO/D. In order to coordinate with the property of permutation-based MOCOPs, MS-PSO/D utilizes an element-based representation and a constructive approach. Through this, feasible solutions under constraints can be generated step by step following the permutation-tree-shaped structure. And problem-related heuristic information is introduced in the constructive approach for efficiency. In order to address the multiobjective optimization issues, the decomposition strategy is employed, in which the problem is converted into multiple single-objective subproblems according to a set of weight vectors. Besides, a flexible mechanism for diversity control is provided in MS-PSO/D. Extensive experiments have been conducted to study MS-PSO/D on two permutation-based MOCOPs, namely the MOTSP and the MOPSP. Experimental results validate that the proposed methodology is promising.

Multimodal optimization problem (MMOP), which targets at searching for multiple optimal solutions simultaneously, is one of the most challenging problems for optimization. There are two general goals for solving MMOPs. One is to maintain population diversity so as to locate global optima as many as possible, while the other is to increase the accuracy of the solutions found. To achieve these two goals, a novel dual-strategy differential evolution (DSDE) with affinity propagation clustering (APC) is proposed in this paper. The novelties and advantages of DSDE include the following three aspects. First, a dual-strategy mutation scheme is designed to balance exploration and exploitation in generating offspring. Second, an adaptive selection mechanism based on APC is proposed to choose diverse individuals from different optimal regions for locating as many peaks as possible. Third, an archive technique is applied to detect and protect stagnated and converged individuals. These individuals are stored in the archive to preserve the found promising solutions and are reinitialized for exploring more new areas. The experimental results show that the proposed DSDE algorithm is better than or at least comparable to the state-of-the-art multimodal algorithms when evaluated on the benchmark problems from CEC2013, in terms of locating more global optima, obtaining higher accuracy solution, and converging with faster speed.

The quality of synthesized view plays an important role in the three dimensional (3D) video system. In this paper, to further improve the coding efficiency, a convolutional neural network (CNN) based synthesized view quality enhancement method for 3D High Efficiency Video Coding (HEVC) is proposed. Firstly, the distortion elimination in synthesized view is formulated as an image restoration task with the aim to reconstruct the latent distortion free synthesized image. Secondly, the learned CNN models are incorporated into 3D HEVC codec to improve the view synthesis performance for both view synthesis optimization (VSO) and the final synthesized view, where the geometric and compression distortions are considered according to the specific characteristics of synthesized view. Thirdly, a new Lagrange multiplier in the rate-distortion (RD) cost function is derived to adapt the CNN based VSO process to embrace a better 3D video coding performance. Extensive experimental results show that the proposed scheme can efficiently eliminate the artifacts in the synthesized image, and reduce 25.9% and 11.7% bit rate in terms of peak-signal-to-noise ratio (PSNR) and structural similarity (SSIM) index, which significantly outperforms the state-of-theart methods.

Utilizing large-scale GPS data to improve taxi services has become a popular research problem in the areas of data mining, intelligent transportation, geographical information systems, and the Internet of Things. In this paper, we utilize a large-scale GPS data set generated by over 7,000 taxis in a period of one month in Nanjing, China, and propose TaxiRec: a framework for evaluating and discovering the passenger-finding potentials of road clusters, which is incorporated into a recommender system for taxi drivers to seek passengers. In TaxiRec, the underlying road network is first segmented into a number of road clusters, a set of features for each road cluster is extracted from real-life data sets, and then a ranking-based extreme learning machine (ELM) model is proposed to evaluate the passenger-finding potential of each road cluster. In addition, TaxiRec can use this model with a training cluster selection algorithm to provide road cluster recommendations when taxi trajectory data is incomplete or unavailable. Experimental results demonstrate the feasibility and effectiveness of TaxiRec.

Dynamic Adaptive Streaming over HTTP (DASH) has demonstrated to be an emerging and promising multimedia streaming technique, owing to its capability of dealing with the variability of networks. Rate adaptation mechanism, a challenging and open issue, plays an important role in DASH based systems since it affects Quality of Experience (QoE) of users, network utilization, etc. In this paper, based on non-cooperative game theory, we propose a novel algorithm to optimally allocate the limited export bandwidth of the server to multi-users to maximize their QoE with fairness guaranteed. The proposed algorithm is proxy-free. Specifically, a novel user QoE model is derived by taking a variety of factors into account, like the received video quality, the reference buffer length, and user accumulated buffer lengths, etc. Then, the bandwidth competing problem is formulated as a non-cooperation game with the existence of Nash Equilibrium that is theoretically proven. Finally, a distributed iterative algorithm with stability analysis is proposed to find the Nash Equilibrium. Compared with state-of-the-art methods, extensive experimental results in terms of both simulated and realistic networking scenarios demonstrate that the proposed algorithm can produce higher QoE, and the actual buffer lengths of all users keep nearly optimal states, i.e., moving around the reference buffer all the time. Besides, the proposed algorithm produces no playback interruption.

In order to meet the high computational demand to achieve superior coding efficiency and to explore the parallelism of parallel processing architectures, the emerging high efficiency video coding (HEVC) standard has been designed to be more parallelizable than previous video coding standards. However, it is still desirable to design an efficient parallel HEVC encoder to fully exploit the parallelism of the increasingly powerful multicore platforms, especially when considering the amount of parallelism, the scalability of parallelization, and the coding efficiency. In this work, a performance model of HEVC encoding is first introduced to investigate the speedup and the limitations of the technique of wavefront parallel processing (WPP) under various conditions. Then, a collaborative scheduling-based parallel solution (CSPS) for HEVC encoding is proposed, which includes adaptive parallel mode decision, asynchronous frame-level pixel interpolation, and multigrained task scheduling. The goal of the proposed CSPS is to defeat the disadvantages of WPP and further improve the parallelization of HEVC encoding on multicore platforms. Extensive experimental results demonstrate the efficiency of the proposed CSPS for parallelizing HEVC encoding as the computing resources of multicore architectures can be fully utilized.

Dynamic adaptive streaming over HTTP (DASH) has emerged as an efficient technology for video streaming. For a DASH system, a most common case is that a limited server bandwidth is competed by multiusers. In order to improve user quality of experience (QoE) and guarantee fairness, we propose to use the game theory in a proxy server to allocate the bandwidth collaboratively for multiusers. By taking user buffer length, received video bit rates, video qualities, etc., into account, the bandwidth allocation problem is formulated as a cooperative bargaining problem and the Nash bargaining solution (NBS) is obtained by convex optimization. The requested bit rate of users will be rewritten as the proxy calculated bit rate (i.e., NBS) when the user requested bit rate is larger. Experimental results demonstrate that user QoE and fairness can be improved significantly, i.e., the delay frequency and duration are smaller, and the received video qualities are higher and more stable, when comparing the proposed method with existing methods.

Among the existing video-related applications, a large proportion have requirements for the scalability of the video coding complexity, such as live video chatting and video coding on power-limited mobile devices. Hence, the complexity control algorithms, which aim to make an effective and flexible tradeoff between coding complexity and rate-distortion (RD) performance, have a great practical value. In this paper, a novel complexity control scheme for high efficiency video coding (HEVC) is proposed by dynamically adjusting the depth range for each coding tree unit (CTU). To control the complexity accurately, a statistical model is proposed to estimate the coding complexity of each CTU. Then the complexity budget is allocated to each CTU proportionally to its estimated complexity. At last, the depth range is optimized for each CTU based on the allocated complexity and the probability that contains the actual maximum depth. Our method works well even if the ratio of target complexity to full complexity drops to 40%. The experimental results show that our proposed method outperforms other four state-of-the-art methods in terms of the RD performance, and has superior complexity control accuracy and complexity control stability compared with other one-pass complexity control strategies.

As a variant of nonnegative matrix factorization (NMF), symmetric NMF (SNMF) has shown to be effective for capturing the cluster structure embedded in the graph representation. In contrast to the existing SNMF-based clustering methods that empirically construct the similarity matrix and rigidly introduce the supervisory information to the assignment matrix, in this paper, we propose a novel SNMF-based semisupervised clustering method, namely, pairwise constraint propagation-induced SNMF (PCPSNMF). By formulating a single-constrained optimization problem, PCPSNMF is capable of learning the similarity and assignment matrices adaptively and simultaneously, in which a small amount of supervisory information in the form of pairwise constraints is introduced in a flexible way to guide the construction of the similarity matrix, and the two matrices communicate with each other to achieve mutual refinement until convergence. In addition, we propose an efficient alternating iterative algorithm to solve the optimization problem, whose convergence is theoretically proven. Experimental results over several benchmark image data sets demonstrate that PCPSNMF is less sensitive to initialization and produces higher clustering performance, compared with the state-of-the-art methods.

This paper proposes a novel surrogate-model-based multi-objective evolutionary algorithm, which is called Multi-objective Bayesian Optimization Algorithm based on Decomposition (MOBO/D). In this algorithm, a multi-objective problem is decomposed into several subproblems which will be solved simultaneously. MOBO/D builds Gaussian process model for each objective to learn the optimization surface, and defines utility function for each subproblem to guide the searching process. At each generation, MOEA/D algorithm is called to locate a set of candidate solutions which maximize all utility functions respectively, and a subset of those candidate solutions is selected for parallel batch evaluation. Experimental study on different test instances validates that MOBO/D can efficiently solve expensive multi-objective problems in parallel. The performance of MOBO/D is also better than several classical expensive optimization methods.

By transforming a multi-objective optimization problem into a number of single-objective optimization problems and optimizing them simultaneously, decomposition-based evolutionary multi-objective optimization algorithms have attracted much attention in the field of multi-objective optimization. In decomposition-based algorithms, the population diversity is maintained using a set of predefined weight vectors, which are often evenly sampled on a unit simplex. However, when the Pareto front of the problem is not a hyperplane but more complex, the distribution of the final solution set will not be that uniform. In this paper, we propose an adaptive method to periodically regenerate the weight vectors for decomposition-based multi-objective algorithms according to the geometry of the estimated Pareto front. In particular, the Pareto front is estimated via Gaussian process regression. Thereafter, the weight vectors are reconstructed by sampling a set of points evenly distributed on the estimated Pareto front. Experimental studies on a set of multi-objective optimization problems with different Pareto front geometries verify the effectiveness of the proposed adaptive weights generation method.

In this paper, we present the results of a recent large-scale subjective study of image quality on a collection of screen contents distorted by a variety of application-relevant processes. With the development of multi-device interactive multimedia applications, metrics to predict the visual quality of screen content images (SCIs) as perceived by subjects are becoming fundamentally important. For developing the objective image quality assessment (IQA) method, there is a need for large-scale public database with diversity of distorted types and scene contents, and available subjective scores of distorted SCIs. The resulting Immersive Media Laboratory screen content image quality database (IML-SCIQD) contains 1250 distorted SCIs from 25 reference SCIs with 10 distortion types. Each image was rated by 35 human observers, and the different mean opinion scores (DMOS) were obtained after data processing. The performance comparison of 17 state-of-the-arts, publicly available IQA algorithms are evaluated on the new database. The database will be available online in our project website.

In this paper, an incremental learning based multi-class Prediction Units (PUs) ranking approach is presented for High Efficiency Video Coding (HEVC) Rate-Distortion-Complexity (RDC) optimization. In particular, the process of PUs selection is formulated as a binary classification plus multi-class ranking task, and incremental learning is applied for classifier training to better exploit the information in the emerging training data. Furthermore, the proposed most probable PUs selection scheme is incorporated into a joint RDC optimization framework, where the complexity can be flexibly allocated targeting at minimizing computational cost under a constrained RD performance degradation. Experimental results demonstrate that the proposed approach can reduce 53.7% and 50.4% computational complexity on average under low delay P and random access configurations with ignorable RD performance degradation, which outperforms the state-of-the-art approaches in terms of RDC performance.

MOTIVATION: The exponential growth of biological network database has increasingly rendered the global network similarity search (NSS) computationally intensive. Given a query network and a network database, it aims to find out the top similar networks in the database against the query network based on a topological similarity measure of interest. With the advent of big network data, the existing search methods may become unsuitable since some of them could render queries unsuccessful by returning empty answers or arbitrary query restrictions. Therefore, the design of NSS algorithm remains challenging under the dilemma between accuracy and efficiency. RESULTS: We propose a global NSS method based on regression, denotated as NSSRF, which boosts the search speed without any significant sacrifice in practical performance. As motivated from the nature, subgraph signatures are heavily involved. Two phases are proposed in NSSRF: offline model building phase and similarity query phase. In the offline model building phase, the subgraph signatures and cosine similarity scores are used for efficient random forest regression (RFR) model training. In the similarity query phase, the trained regression model is queried to return similar networks. We have extensively validated NSSRF on biological pathways and molecular structures; NSSRF demonstrates competitive performance over the state-of-the-arts. Remarkably, NSSRF works especially well for large networks, which indicates that the proposed approach can be promising in the era of big data. Case studies have proven the efficiencies and uniqueness of NSSRF which could be missed by the existing state-of-the-arts. AVAILABILITY AND IMPLEMENTATION: The source code of two versions of NSSRF are freely available for downloading at https://github.com/zhangjiaobxy/nssrfBinary and https://github.com/zhangjiaobxy/nssrfPackage . CONTACT: [email protected]. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

• A large-scale JND-based coded video quality dataset is presented. • The VideoSet contains 220 5-s sequences in four resolutions coded by H.264/AVC. • The subjective test procedure, JND data cleaning and properties are described. • The significance and implications of the VideoSet are discussed. • This work points out a clear path to data-driven perceptual coding. A new methodology to measure coded image/video quality using the just-noticeable-difference (JND) idea was proposed in Lin et al. (2015). Several small JND-based image/video quality datasets were released by the Media Communications Lab at the University of Southern California in Jin et al. (2016) and Wang et al. (2016) [3]. In this work, we present an effort to build a large-scale JND-based coded video quality dataset. The dataset consists of 220 5-s sequences in four resolutions (i.e., 1920 × 1080 , 1280 × 720 , 960 × 540 and 640 × 360 ). For each of the 880 video clips, we encode it using the H.264/AVC codec with QP = 1 , … , 51 and measure the first three JND points with 30 + subjects. The dataset is called the “VideoSet”, which is an acronym for “Video Subject Evaluation Test (SET)”. This work describes the subjective test procedure, detection and removal of outlying measured data, and the properties of collected JND data. Finally, the significance and implications of the VideoSet to future video coding research and standardization efforts are pointed out. All source/coded video clips as well as measured JND data included in the VideoSet are available to the public in the IEEE DataPort (Wang et al., 2016 [4]).

Object quality assessment for compressed video is critical to various video compression systems that are essential in the video delivery and storage. Although mean squared error (MSE) is computationally simple, it may not be accurate to reflect the perceptual quality of compressed videos, which are also affected dramatically by the characteristics of the human visual system (HVS), such as contrast sensitivity, visual attention, and masking effect. In this paper, a video quality metric is proposed based on perceptually weighted MSE. A low-pass filter is designed to model the contrast sensitivity of the HVS with the consideration of visual attention. The imperceptible distortion is adaptively removed in the salient and nonsalient regions. To quantitatively measure the masking effect, the randomness of video content is proposed in both the spatial and temporal domains. Since the masking effect highly depends on the regularity of structure and motion in the spatial and temporal directions, the video signal is modeled as a linear dynamic system, and the prediction error of future frames from previous frames is used as randomness to measure the significance of masking. The relation is investigated between MSE and perceptual quality scores across various contents, and a masking modulation model is proposed to compensate the impact of the masking effect on the MSE. The performance of the proposed quality metric is validated on three video databases with various compression distortions. The experimental results demonstrate that the proposed algorithm outperforms other benchmark quality metrics.

In this paper, a new optimization approach is designed for convolutional neural network (CNN) which introduces explicit logical relations between filters in the convolutional layer. In a conventional CNN, the filters' weights in convolutional layers are separately trained by their own residual errors, and the relations of these filters are not explored for learning. Different from the traditional learning mechanism, the proposed correlative filters (CFs) are initiated and trained jointly in accordance with predefined correlations, which are efficient to work cooperatively and finally make a more generalized optical system. The improvement in CNN performance with the proposed CF is verified on five benchmark image classification datasets, including CIFAR-10, CIFAR-100, MNIST, STL-10, and street view house number. The comparative experimental results demonstrate that the proposed approach outperforms a number of state-of-the-art CNN approaches.

Sparse signal reconstruction can be regarded as a problem of locating the nonzero entries of the signal. In presence of measurement noise, conventional methods such as l1norm relaxation methods and greedy algorithms, have shown their weakness in finding the nonzero entries accurately. In order to reduce the impact of noise and better locate the nonzero entries, in this paper, we propose a two-phase algorithm which works in a coarse-to-fine manner. In phase 1, a decomposition-based multiobjective evolutionary algorithm is applied to generate a group of robust solutions by optimizing l1norm of the solutions. To remove the interruption of noise, the statistical features with respect to each entry among these solutions are extracted and an initial set of nonzero entries are determined by clustering technique. In phase 2, a forward-based selection method is proposed to further update this set and locate the nonzero entries more precisely based on these features. At last, the magnitudes of the reconstructed signal are obtained by the method of least squares. We conduct the comparison of our proposed method with several state-of-the-art compressive sensing recover methods, the best result in phase 1 and the approach combining phases 1 and 2 without the statistical features. Experimental results on benchmark signals as well as randomly generated signals demonstrate that our proposed method outperforms the above methods, achieving higher recover precision and maintaining larger sparsity.

The balance between convergence and diversity is the cornerstone of evolutionary multiobjective optimization (EMO). The recently proposed stable matching-based selection provides a new perspective to handle this balance under the framework of decomposition multiobjective optimization. In particular, the one-one stable matching between subproblems and solutions, which achieves an equilibrium between their mutual preferences, is claimed to strike a balance between convergence and diversity. However, the original stable marriage model has a high risk of matching a solution with an unfavorable subproblem, which finally leads to an imbalanced selection result. In this paper, we introduce the concept of incomplete preference lists into the stable matching model to remedy the loss of population diversity. In particular, each solution is only allowed to maintain a partial preference list consisting of its favorite subproblems. We implement two versions of stable matching-based selection mechanisms with incomplete preference lists: one achieves a two-level one-one matching and the other obtains a many-one matching. Furthermore, an adaptive mechanism is developed to automatically set the length of the incomplete preference list for each solution according to its local competitiveness. The effectiveness and competitiveness of our proposed methods are validated and compared with several state-of-the-art EMO algorithms on 62 benchmark problems.

Multiple-instance active learning (MIAL) is a paradigm to collect sufficient training bags for a multiple-instance learning (MIL) problem, by selecting and querying the most valuable unlabeled bags iteratively. Existing works on MIAL evaluate an unlabeled bag by its informativeness with regard to the current classifier, but neglect the internal distribution of its instances, which can reflect the diversity of the bag. In this paper, two diversity criteria, i.e., clustering-based diversity and fuzzy rough set based diversity, are proposed for MIAL by utilizing a support vector machine (SVM) based MIL classifier. In the first criterion, a kernel k-means clustering algorithm is used to explore the hidden structure of the instances in the feature space of the SVM, and the diversity degree of an unlabeled bag is measured by the number of unique clusters covered by the bag. In the second criterion, the lower approximations in fuzzy rough sets are used to define a new concept named dissimilarity degree, which depicts the uniqueness of an instance so as to measure the diversity degree of a bag. By incorporating the proposed diversity criteria with existing informativeness measurements, new MIAL algorithms are developed, which can select bags with both high informativeness and diversity. Experimental comparisons demonstrate the feasibility and effectiveness of the proposed methods.

In this paper, a joint machine learning and game theory modeling (MLGT) framework is proposed for inter frame coding tree unit (CTU) level bit allocation and rate control (RC) optimization in high efficiency video coding (HEVC). First, a support vector machine-based multi-classification scheme is proposed to improve the prediction accuracy of CTU-level rate-distortion (R-D) model. The legacy "chicken-and-egg" dilemma in video coding is proposed to be overcome by the learning-based R-D model. Second, a mixed R-D model-based cooperative bargaining game theory is proposed for bit allocation optimization, where the convexity of the mixed R-D model-based utility function is proved, and Nash bargaining solution is achieved by the proposed iterative solution search method. The minimum utility is adjusted by the reference coding distortion and frame-level quantization parameter (QP) change. Finally, intra frame QP and inter frame adaptive bit ratios are adjusted to make inter frames have more bit resources to maintain smooth quality and bit consumption in the bargaining game optimization. Experimental results demonstrate that the proposed MLGT-based RC method can achieve much better R-D performances, quality smoothness, bit rate accuracy, buffer control results, and subjective visual quality than the other state-of-the-art one-pass RC methods, and the achieved R-D performances are very close to the performance limits from the FixedQP method.

With the popularity of high-efficiency video coding (HEVC) standard, a video server usually transcodes a video stream to HEVC for its higher compression ratio. In this paper, a fast H.264/advanced video coding (AVC) to HEVC transcoding method is proposed. In the HEVC encoding procedure, a coding unit (CU), which is a motion-homogeneous block, is first checked based on the analysis of the decoded information from H.264/AVC bit stream. Then, for motion-homogeneous blocks, CU depth and the corresponding prediction unit (PU) mode's early termination strategies are proposed based on the CU size and corresponding prior statistical knowledge. For non-motion-homogeneous blocks, a corresponding PU mode's early termination strategy is also proposed. Experimental results demonstrate the effectiveness of the proposed method.

This paper investigates how to use a pre-selection approach to improve the performance of the multiobjective evolutionary algorithm based on decomposition (MOEA/D). It proposes a novel MOEA/D algorithm with classification to serve this purpose. The proposed algorithm builds a classification model on the search space to filter all new generated solutions, and mainly evaluates those promising solutions for reducing real function evaluation costs during the search process. Experimental study on different test instances validates that the pre-selection approach can significantly improve the performance of a classical MOEA/D.

Due to the extensive and various information that natural images contain, it is very challenging to estimate the sparsity for an image. In this paper, we propose an adaptive sparsity estimation model for image patches, which consists of an offline training phase and online estimation phase. In offline training, for the training patch, MOEA/D is applied to obtain a group of Pareto solutions and determine a sparsity range. By processing a reduced number of representative training patches, all the sparsity ranges are stored in a look-up table (LUT) for reuse. In the online estimation phase, for a query patch, its sparsity range is set to that of the most similar training patch. And the corresponding sparse representation vector can be obtained by a sparsity-restricted greedy algorithm (SRGA) constrained by this range. Thus, the sparsity is adaptively determined by this sparse representation vector within this range. By comparing with the state-of-the-art greedy algorithms with fixed sparsity and one adaptive method, experimental studies on benchmark dataset demonstrate that our proposed approach is able to achieve better sparse representation quality in terms of PSNR and coding efficiency.

Phase Congruency (PC) features are firstly introduced into image and video coding field in this paper. As an effective tool to measure the edge information for image textures, PC change can be used to evaluate the compression loss, i.e. the coding distortions in image and video coding. Firstly, the compression influences on PC maps are given and analyzed. Secondly, the relationship between the consumed bits and the PC distortion are modeled. Lastly, the Mean-Squared-Error (MSE) based and PC distortion based optimized Coding Tree Unit (CTU) level bit allocation solutions are combined as a two step bit allocation and rate control method for intra frames for High Efficiency Video Coding (HEVC). Experimental results demonstrate that, compared with the state-of-the-art JCTVC-K0103 and JCTVC-M0257 methods, for small size videos, the proposed method can achieve significant R-D performance gains, and also works well on PC map preservation, quality smoothness and bit rate accuracy.