Out-of-distribution (OOD) detection plays a critical role in ensuring the robustness of machine learning models in open-world settings. While extensive efforts have been made in vision, language, and graph domains, the challenge of OOD detection in hypergraph-structured data remains unexplored. In this work, we formalize the problem of hypergraph out-of-distribution (HOOD) detection, which aims to identify nodes or hyperedges whose high-order relational contexts differ significantly from those seen during training. We propose HyperGOOD, a unified energy-based detection framework that integrates multi-scale spectral decomposition with structure-aware uncertainty propagation. By preserving both low- and high-frequency signals and diffusing uncertainty across the hypergraph, HyperGOOD effectively captures subtle and relationally entangled anomalies. Experimental results on nine hypergraph datasets demonstrate the effectiveness of our approach, establishing a new foundation for robust hypergraph learning under distributional shifts.

Visible-Infrared (RGB-IR) Unmanned Aerial Vehicle (UAV) object detection integrates complementary cues from visible and infrared sensors, offering broad application potential. However, due to sensor parallax, it still faces the challenge of weak spatial misalignment, which significantly limits its performance in UAV-based object detection. Existing methods emphasize strict alignment, overlooking spectral heterogeneity under varying illumination. To address these issues, we propose the Illumination Guided Implicit Alignment Network (IGIANet) to mitigate modality heterogeneity without explicit alignment. Specifically, we integrate three novel modules. First, we propose an illumination-guided frequency modulation module that adaptively allocates fusion weights to visible and infrared features based on global illumination estimation, effectively alleviating modality imbalance under varying lighting conditions. Second, we introduce a frequency-guided cross-modality differential enhancement module, which computes differential cues across frequency domains to enhance complementary information and highlight weakly aligned and low-contrast regions. Finally, we introduce an implicit alignment-driven dynamic fusion module that actively estimates offsets and generates dynamic, position-adaptive fusion kernels to align and fuse modalities. Extensive experiments demonstrate that IGIANet outperforms state-of-the-art models on various benchmarks, achieving 80.9% mAP on DroneVehicle, 57.1% mAP on VEDAI, and 49.4% mAP on FLIR.

Self-supervised monocular depth estimation methods severely compromise accuracy in dynamic objects due to their static scene assumption. Existing approaches for dynamic scenes suffer from two critical shortcomings: 1) reliance on supervised segmentation models (requiring costly annotations) or computationally intensive multi-branch models to isolate moving objects, and 2) simple integration of 2D/3D motion flow without reliable supervision for dynamic objects. We propose AdaDepth, a two‑stage framework that jointly performs unsupervised scene decomposition and dynamic-aware depth learning. In the initial structural stage, our geometry-motion joint scene decomposition (GMoDecomp) module ensures the robust generation of a depth prior and simultaneously partitions the scene into multiple regions through the fusion of geometric and motion cues. In the region-adaptive refinement stage, we exploit the depth prior and decomposed regions to introduce motion-aware and geometry-consistent constraints, effectively improving depth estimation in dynamic scenes. AdaDepth achieves accurate depth prediction in highly dynamic scenes without relying on external labels or specialized segmentation models. Extensive experiments on KITTI, Cityscapes, and Waymo Open demonstrate its superiority over state-of-the-art approaches.

Neural textures have emerged as pivotal assets in next-generation neural rendering pipelines. However, hardware limitations and programming interface constraints lead to suboptimal performance in multi-instance real-time rendering scenarios. This bottleneck becomes particularly acute for texture-intensive tasks such as font rendering. To address this, we propose Neural Outline Cache (NOC), a novel neural font texture supporting real-time anti-aliased rendering and procedural editing within modern neural graphics pipelines. NOC's lightweight network leverages multi-resolution hash encoding to cache spline-derived SDFs, delivering anti-aliased rendering via standard graphics pipelines. For massive-instance scalability, our cache buffer layout (CBL) and batch-fused inference (BFI), tailored for NOC, mitigate neural texture streaming bottlenecks. We constructed an evaluation dataset using five font styles. In offline rendering, our proposed method achieves overall average results of 57.35 dB PSNR, 0.998 SSIM, and 1.1584e-3 pixel RMSE, while maintaining approximately 0.5ms frame latency with 500 real-time instances. To demonstrate its versatility, we integrated a procedural editor for visual effects editing of NOC textures. These results all prove that NOC is a reliable, production-ready neural asset.

Despite the progress made through deep learning, existing Visual Object Tracking (VOT) frameworks struggle with real-world challenges. Recent approaches incorporate additional modalities like Depth, Thermal Infrared, and Language to enhance the robustness of VOT, particularly with the improvement of the depth sensor precision, facilitating RGB-D tracking. However, current RGB-D trackers often copy RGB tracking paradigms, leading to inefficiency due to two-stream architectures that fail to exploit heterogeneous features, and reliance on simplistic or large-parameter fusion methods. To address these challenges, we propose AMTrack, a one-stream RGB-D tracker leveraging Mamba's linear complexity for simultaneous feature extraction and two-stage cross-modal feature fusion. Our innovation also includes a low-parameter Multimodal Mix Mamba (3M) module, which optimizes deep feature fusion and reduces computational overhead. The advantage of the 3M module stems from our Multimodal State Space Model (MSSM), a multimodal feature interaction component reconstructed based on SSM. Experiments across multiple RGB-D tracking datasets indicate that AMTrack achieves superior performance with lower parameters and memory demands compared to state-of-the-arts.

As a core problem in unsupervised learning, anomaly detection focuses on identifying abnormal patterns in datasets, thereby providing support for uncovering potential problems and extracting valuable information. However, most existing methods fail to extract sufficient information in feature interactions when dealing with heterogeneous datasets. To address this challenge, a novel anomaly detection method based on multi-sequence fuzzy feature interaction is proposed. Firstly, we propose multi-sequence features based on joint fuzzy information entropy to capture complex feature interactions and to quantify the interdependencies among features. Secondly, forward and reverse multi-sequence feature subset pairs are constructed to characterize the correlation between features from different angles, enhancing the accuracy of representing complex interactions in heterogeneous data and improving the ability to identify potential anomalies. Subsequently, an uncertainty measure based on multi-sequence information fusion is introduced, and anomaly scores are accumulated by incorporating instance weights, thereby ensuring stable detection performance in heterogeneous datasets. Finally, an anomaly detection algorithm based on multi-sequence fuzzy feature interaction (ADMSFI) is proposed. The experimental results demonstrate that the proposed algorithm ADMSFI significantly outperforms 13 existing algorithms in terms of performance and flexibility in 24 datasets.

The development of mobile web services has brought significant attention to spatial crowdsourcing. The uneven distribution of tasks and workers has led to recent research on Cross-Platform Spatial Crowdsourcing (CPSC), aiming for a multi-win situation for platforms, workers, and task requesters. Previous studies on CPSC problems focused on task assignment and worker selection performance, overlooking the importance of privacy preservation. This article addresses the existing challenges of privacy preservation and service quality by formulating a Privacy-Preserving Cross-Platform Spatial Crowdsourcing (PP-CPSC) problem and proves it to be NP-hard. We propose an Evolutionary Differential Privacy (Evo-DP) approach to optimize PP-CPSC. Evo-DP’s evolutionary framework enables efficient and flexible optimization of privacy budget allocation. Within Evo-DP, each solution to the privacy budget allocation is represented as an individual in the population. To approximate the optimal solution, three evolutionary operations—mutation, crossover, and scaling—are employed for population updates, along with a selection process. A hybrid population model is introduced to balance exploration and exploitation abilities. Experimental results demonstrate Evo-DP’s superiority over previous strategies in terms of solution quality, convergence speed, and scalability.

Mobile edge computing (MEC) has recently gained significant attention as a promising solution for processing delay sensitive and resource-intensive computational jobs. Existing system schedulers in MEC networks typically assume homogeneous service providers, uniformly distributed user equipment (UE), and identical service requirements, making them unsuitable for practical MEC scenarios where jobs are randomly generated with varying service and completion time requirements. Thus, in this work, we jointly optimize job scheduling and resource allocation in a heterogeneous multi-unmanned aerial vehicle (UAV) enabled MEC network, considering practical factors such as diverse service requirements of jobs, unknown distribution of UEs, and spatial-temporal job arrivals. We aim to reduce the overall job miss rate and the average energy consumption of both UAVs and UEs by jointly planning safe UAV trajectories and onboard resource allocation. To learn uncertain and dynamic UE-side states (e.g., job arrivals and mobility patterns) and ensure the UAV's safety during the flight, we propose a multi-agent safe reinforcement learning algorithm that combines a Shared Soft Actor-Critic architecture for extracting features of heterogeneous UAVs and a two-agent Markov Game of Intervention mechanism for collision avoidance, named SSAC-MGI. In particular, SSAC MGI further incorporates a fine-grained resource allocation scheme to improve onboard resource utilization and reduce job miss rate. Extensive real trace-driven simulations based on Alibaba cluster data validate the effectiveness and superiority of SSAC-MGI, compared with several state-of-the-art algorithms.

Multimodal recommendation provides richer and more accurate personalized recommendations by jointly modeling user’s historical behaviors and different modality of items, such as text, image, audio, and video in online platforms. Most existing work of multimodal recommendation focuses on leveraging modal features and modal correlation graph structures to learn user preferences. Due to insufficient exploration of user collaborative preferences and the noise during high-order multimodal data connections, valuable information may be lost, leading to deviations in understanding user preferences. Therefore, an I ndependent T opological Preference-Aware and Co operative H ypergraph D iffusion-based M ultimodal Rec ommender Model (ITCoHD-MRec) is necessary for online platforms. This article aims to develop an ITCoHD-MRec that incorporates topological perception as well as generative diffusion models in multimodal hypergraph recommendation to make the model more adaptive and robust in complex environments. Firstly, leveraging a Graph Convolutional Network (GCN), the model independently captures user preference representations for both collaborative relevance and modal relevance from the user-item interaction graph, which contains ID embeddings and modal features. This enables the extraction of deeper associations between users and items. Secondly, leveraging topological pruning techniques, the model learns differentiated features in different modal blocks to prevent node representations from becoming homogenized. This helps further identify user preferred connectivity patterns and removes redundant noisy connections. Finally, by employing the diffusion model, information regarding the higher-order interaction patterns between attributes and items within the hypergraph structure is propagated. This effectively captures the potential global dependencies between attributes and items, thereby providing deeper associations enriched with more substantial semantic information for subsequent recommendation tasks. The model autonomously learns different features and higher-order connectivity of nodes, which enables the model to obtain a wider and more accurate perception of user preferences in complex interaction environments. Experimental comparisons with 15 models on four real datasets—Baby, Sports, Clothing, and Electronics show that the model improves the recall by 0.85%–3.57% and the normalized discounted cumulative gain by 2.31%–3.43%, which validates the effectiveness of ITCoHD-MRec.

Mobile edge computing (MEC) is promising in handling delay-sensitive or resource-intensive tasks in mobile internet. Existing system schedulers in MEC networks usually schedule all service providers in a synchronous manner, which may not suit the practical scenario where tasks are randomly generated and require different computational resources and service times. In this work, we jointly optimize the task scheduling and resource allocation in an unmanned aerial vehicle (UAV)-enabled MEC network, where multiple UAVs asynchronously and cooperatively deliver task offloading and computing services to edge devices (EDs), for maximizing the average per-UAV energy utility and minimizing the overall task missing ratio. To enhance scheduling efficiency and jointly optimize task scheduling and resource allocation, we develop an asynchronous layered multi-agent proximal policy optimization (AL-MAPPO) algorithm, by incorporating the multi-UAV asynchronous action execution mechanism and a discrete-continuous layered action space into the general MAPPO framework. AL-MAPPO enables each UAV to perform flexible task scheduling and fine-grained resource allocation asynchronously. Extensive trace-driven simulations based on Alibaba Cluster Data V2017 validate the effectiveness of AL-MAPPO, compared with several baseline algorithms.

Reconfigurable intelligent surfaces (RIS) are emerging as a promising technology for next-generation wireless communications, capable of mitigating severe propagation attenuation, enhancing spectral efficiency, and expanding signal coverage. This paper focuses on online millimeter-wave (mmWave) beam tracking for multi-RIS-assisted hybrid beamforming systems. We develop two novel beam tracking algorithms based on multi-agent deep reinforcement learning (DRL): a multi-agent deep deterministic policy gradient (MADDPG)-based algorithm for continuous-domain beam angle tracking and a multi-agent deep Q-network (MADQN)-based algorithm for codebook-based discrete-domain beam angle tracking. Both algorithms are designed to maximize the sum rate by jointly optimizing analog beamforming for the base station (BS) and reflection coefficients for multiple RISs in dynamic environments, leveraging historical information and without requiring current user position or channel information. After determining analog beamforming and RIS reflection coefficients, digital beamforming for the BS is constructed by estimating the end-to-end effective channel, which significantly reduces the overhead of channel estimation. Experimental results demonstrate that the proposed algorithms effectively adapt the analog beamformer and RIS reflection coefficients to account for user mobility, significantly outperforming existing benchmark schemes.

Time series forecasting has various applications, such as meteorological rainfall prediction, traffic flow analysis, financial forecasting, and operational load monitoring for various systems. Due to the sparsity of time series data, relying solely on time-domain or frequency-domain modeling limits the model's ability to fully leverage multi-domain information. Moreover, when applied to time series forecasting tasks, traditional attention mechanisms tend to over-focus on irrelevant historical information, which may introduce noise into the prediction process, leading to biased results. We proposed WDformer, a wavelet-based differential Transformer model. This study employs the wavelet transform to conduct a multi-resolution analysis of time series data. By leveraging the advantages of joint representation in the time-frequency domain, it accurately extracts the key information components that reflect the essential characteristics of the data. Furthermore, we apply attention mechanisms on inverted dimensions, allowing the attention mechanism to capture relationships between multiple variables. When performing attention calculations, we introduced the differential attention mechanism, which computes the attention score by taking the difference between two separate softmax attention matrices. This approach enables the model to focus more on important information and reduce noise. WDformer has achieved state-of-the-art (SOTA) results on multiple challenging real-world datasets, demonstrating its accuracy and effectiveness. Code is available at https://github.com/xiaowangbc/WDformer.

Multisensor image fusion aims to generate a high-quality composite image by integrating information from diverse sources. While deep learning-based approaches enhance fusion quality, they often suffer from high computational costs and information loss due to single-step feature integration. We propose ConvFuse, a lightweight DL framework for infrared and visible image fusion. Our context-aware convformer block effectively preserves local-global and contextual details without relying on attention mechanisms. A progressive intermodality fusion strategy enhances modality-specific features, while a multiscale decoder ensures seamless feature integration across different scales. Experimental results on benchmark datasets show that ConvFuse surpasses transformer-based and SOTA DL-based methods in fusion quality and efficiency.

Mobile chargers (MCs) have been widely used in wireless rechargeable sensor networks (WRSNs) to deliver energy to sensor nodes. This paper concerns the fundamental problem of dispatching the minimum number of MCs to charge nodes within a large-scale WRSN, i.e., given a set of rechargeable nodes, we aim to minimize the total number of dispatched MCs by appropriately designing the charging path of each dispatched MC, such that the charging demand of each node is satisfied. Due to its complexity, we solve this problem by first dividing it into two subproblems, i.e., charging points selection and charging paths design, which are both NP-hard. Then, we propose a computational geometry-based two-step heuristic algorithm to solve the two subproblems respectively. In the first step, we develop a peeling-off searching algorithm (POSA) to determine the charging points where MCs can stop to charge nodes within their charging ranges, by jointly considering the charging efficiency and moving distance. In the second step, we gradually assign the determined charging points to each dispatched MC while constructing the corresponding charging path. During the path construction, we first generate a shortest closed tour connecting all the currently assigned charging points and then use a break-and-tie method to insert the depot to form the charging path. Extensive evaluations validate the superiority of our proposed algorithm, compared with some other algorithms.

Heterophilic graph neural networks (GNNs) have gained prominence for their ability to learn effective representations in graphs with diverse, attribute-aware relationships. While existing methods leverage attribute inference during message passing to improve performance, they often struggle with challenging heterophilic graphs. This is due to edge distribution shifts introduced by diverse connection patterns, which blur attribute distinctions and undermine message-passing stability. This paper introduces H₂OGNN, a novel framework that reframes edge attribute inference as an out-of-distribution (OOD) detection problem. H₂OGNN introduces a simple yet effective symbolic energy regularization approach for OOD learning, ensuring robust classification boundaries between homophilic and heterophilic edge attributes. This design significantly improves the stability and reliability of GNNs across diverse connectivity patterns. Through theoretical analysis, we show that H₂OGNN addresses the graph denoising problem by going beyond feature smoothing, offering deeper insights into how precise edge attribute identification boosts model performance. Extensive experiments on nine benchmark datasets demonstrate that H₂OGNN not only achieves state-of-the-art performance but also consistently outperforms other heterophilic GNN frameworks, particularly on datasets with high heterophily.

Multi-radio access technology (multi-RAT) enabled mobile edge computing (MEC) has emerged as a promising paradigm for supporting heterogeneous applications. However, efficiently managing resources for both ultra-reliable low-latency communications (URLLC) and enhanced mobile broadband (eMBB) services in large-scale networks remains challenging. In this paper, we investigate a joint optimization problem involving user association and bandwidth allocation in multi-RAT-enabled MEC systems. We propose a novel cooperative evolutionary framework operated based on the interplay between inner and outer agents to efficiently optimize large-scale networks. Extensive simulation results demonstrate that the proposed approach significantly outperforms the conventional single-RAT MEC system and several representative evolutionary computation algorithms.

Current sketch modeling methods face challenges in terms of efficiency and quality due to frequent view changes. To empower users to create models seamlessly and accurately from a single reference drawing, we present WidgetSketcher, a single-view, sketch-based modeling method that incorporates widget manipulations. To ensure seamlessness, we implement a single-view workflow in sketch-based modeling with designed widget manipulations and other interactions. Each user stroke is equipped with a transient axis widget, allowing 3D pose specification and part creation from a single view. To improve accuracy, we develop a two-stage shape generation algorithm, ensuring the precise generation of shapes with detailed features and asymmetry. Our method enables the quick and accurate creation of 3D models consistent with reference drawings, while eliminating frequent view changes. To demonstrate the efficiency of our method, we evaluate the system usability by conducting a user study and compare the results to state-of-the-art techniques.

Power delivery issues are increasingly evident in cyber-physical smart grid systems as energy transactions frequently overlook the physical constraints of distribution, leading to transmission congestion and compromising network security and reliability. This article presents a novel and cost-effective solution to power delivery challenges by utilizing electric vehicles (EVs) with dynamic transportation capabilities as free carriers. Unlike traditional approaches, a deep reinforcement learning (DRL)-based optimization framework is designed to effectively manage incomplete information in real-time. Our method first introduces an investment-free model that leverages existing EV routes to transport energy during congestion, operating in a “free-riding” transmission mode. This not only enhances network reliability but also curtails costs. Then, we develop a Markov decision process (MDP) for sequential decision-making of 24-h optimal control, aimed at minimizing operational losses including load shedding and battery degradation. To deal with the stochastic nature of energy requests and EV routes in the control problem, we employ a model-free DRL algorithm to tackle the challenge of incomplete information. An Actor-Critic network, combining value-based and policy-based approaches, helps discover approximately optimal strategies in a continuous action space. Finally, the simulation results numerically demonstrate the performance of the proposed method.

With the rise of federated learning (FL) in the realm of machine learning for data privacy protection, its unique distributed data processing characteristics have garnered widespread attention. However, the implementation of FL faces many challenges, as achieving a balance between data privacy, model security, and system efficiency is difficult, often requiring the sacrifice of efficiency for privacy and security. Moreover, this process typically assumes the existence of a trusted server for coordination. Addressing these challenges, this article proposes a privacy-preserved and efficient FL framework with blockchain (PEFL). PEFL utilizes blockchain and differential privacy techniques to coordinate privacy protection among clients, and filters out anomalous model parameters through an aggregation-side detection algorithm to resist poisoning attacks. Under the assumption of an untrusted server, we design the model-validated fault-tolerant federation (MFF) consensus mechanism based on a committee, balancing efficiency expectations to regulate the server and ensure the reliability of the training process. Through experiments on the MNIST and CIFAR10 datasets, and comparison with typical FL schemes, PEFL demonstrates better defense against various attack models. Besides, it achieves higher training efficiency while ensuring privacy security.

Federated edge learning (FEL) enables Industrial Internet of Things (IIoT) devices to collaboratively train machine learning models without exposing their local data. However, insecure communication environments pose significant threats to the security of model transmission in FEL. Signcryption, as a novel cryptographic primitive, can provide confidentiality, integrity, and other security guarantees for model transmission. Nevertheless, most existing signcryption schemes are designed for a single recipient and therefore cannot meet the multi-recipient requirements of FEL. Additionally, these schemes lack mechanisms for revoking signcryption privileges, which allows malicious edge nodes to continue participating in model transmission and disrupt the training of the global model. To address these challenges, this paper proposes the Lightweight and Efficient Signcryption for Federated Edge Learning in IIoT (LES), which achieves efficient one-to-many signcryption by leveraging bilinear pairings and Lagrange interpolation. LES balances computational and communication overhead while ensuring security. Moreover, the LES scheme incorporates blockchain technology and the Chinese Remainder Theorem to enable revocation of signcryption privileges, preventing compromised edge nodes from continuing to engage in model transmission. Formal security proofs of the LES scheme are provided. A comprehensive comparison between LES and eight representative signcryption schemes proposed in recent years highlights the feasibility of LES and its clear advantages in terms of computational and communication overhead. Under partial participation, LES achieves at least a 29.1% reduction in computational cost and an 81.8% reduction in communication cost compared with the most efficient single recipient scheme among the eight evaluated.

Multiple Object Tracking (MOT) is a critical task in computer vision with a wide range of practical applications. However, current methods often use a uniform approach for associating all targets, overlooking the varying conditions of each target. This can lead to performance degradation, especially in crowded scenes with dense targets. To address this issue, we propose a novel Condition-Aware Tracking method (CATrack) to differentiate the appearance feature flow for targets under different conditions. Specifically, we propose three designs for data association and feature update. First, we develop an Adaptive Appearance Association Module (AAAM) that selects suitable track templates based on detection conditions, reducing association errors in long-tail cases like occlusions or motion blur. Second, we design an ambiguous track filtering Selective Update strategy (SU) that filters out potential low-quality embeddings. Thus, the noise accumulation in the maintained track feature will also be reduced. Meanwhile, we propose a confidence-based Adaptive Exponential Moving Average (AEMA) method for the feature state transition. By adaptively adjusting the weights of track and detection embeddings, our AEMA better preserves high-quality target features. By integrating the above modules, CATrack enhances the discriminative capability of appearance features and improves the robustness of appearance-based associations. Extensive experiments on the MOT17 and MOT20 benchmarks validate the effectiveness of the proposed CATrack. Notably, the state-of-the-art results on MOT20 demonstrate the superiority of our method in highly crowded scenarios.

RGBT target tracking accomplishes the tracking task by fusing visible and thermal infrared information. The development of Convolutional Neural Networks (CNNs) and Transformer has greatly advanced this field. Most existing transformer-based trackers focus on global modeling while neglecting the utilization of local information. In this paper, we propose a novel Convolutional Attention Fusion Module (CAFM) for RGBT target tracking. To be specific, this module continuously slides local windows on the image like convolution, and captures context features in each window like attention. Additionally, local position embedding is added to the window and works in conjunction with global position embedding to enhance the model's understanding of spatial information. Therefore, our CAFM enhances the extraction of local features by restricting the attention area and promotes multimodal fusion through cross-attention. We extend OSTrack to RGBT tracking and integrate the proposed CAFM into it. Experimental results show that our method performs well on the LasHeR, RGBT210, and RGBT234 datasets, and is superior to other advanced trackers.

Advances in language models have enabled significant strides in developing language technologies tailored for analyzing and processing Dialectical Arabic (DA), which exhibits unique linguistic features and variations compared to standard Arabic. This progress has sparked a surge of interest in various research tasks within the Arabic Natural Language Processing (ANLP) domain, encompassing areas such as sentiment analysis, dialect identification, normalization and classification, fake news detection, and part-of-speech tagging. The primary objective of this survey paper is to provide a comprehensive overview of the advancements made in dialectical ANLP from 2014 to 2024. A thorough analysis is undertaken, covering a corpus of approximately 200 research papers, to offer insights into the latest developments, resources, and applications concerning dialectical Arabic. By identifying and discussing the challenges and opportunities for future research, this study aspires to serve as a valuable reference for researchers, practitioners, and enthusiasts interested in the subject matter. Central to the investigation are the recent strides in natural language processing techniques that pertain to dialectical Arabic, namely DA sentiment analysis, DA identification, DA classification, DA normalization, DA part-of-speech tagging, and the role of DA in fake news detection, among other applications. Each research category is meticulously examined, providing a comprehensive understanding of their respective contributions, significance, encountered challenges, and the availability of pertinent datasets. This exhaustive survey paper encompasses existing studies within dialectical Arabic research categories. As a result, readers are presented with a detailed reference source in pursuing advancements and innovations within this field.

This paper presents a novel approach that leverages two models to integrate features from numerous unlabeled images, addressing the challenge of semi-supervised salient object detection (SSOD). Unlike conventional methods that rely on selecting high-quality pseudo labels, our method identifies the model that produces consistent predictions for original images and their color transformation versions from two models to infer reliable pseudo labels for all unlabeled images, improving the diversity of the training set. Specifically, we propose adaptive selection indicators to quantify prediction differences and guide the updates of the two models using the unlabeled set alternatively. Initially, two models used in our framework are trained on the labeled set. Once the adaptive selection indicator conditions are satisfied, one model is designated as the proxy, generating pseudo labels, while the other serves as the saliency model, which is further trained using these pseudo labels. Subsequently, the updated saliency model optimizes the proxy model’s parameters according to another adaptive selection indicator. Experimental results and ablation studies on six benchmark salient object detection datasets confirm the effectiveness and robustness of our method. Our approach achieves performance comparable to recent fully supervised methods while using only one eighth of the labeled data, demonstrating its potential for efficient and scalable SSOD. This paper is publicly available athttps://github.com/Liyuan0905/CATNet.

Recently, researchers have proposed many deep generative models, including generative adversarial networks (GANs) and denoising diffusion models. Although significant breakthroughs have been made and empirical success has been achieved with the GAN, its mathematical underpinnings remain relatively unknown. This paper focuses on a rigorous mathematical theoretical framework: the composite-functional-gradient GAN (CFG). Specifically, we reveal the theoretical connection between the CFG model and score-based models. We find that the CFG discriminator’s training objective is equivalent to finding an optimal$D(\mathrm {x})$. The optimal$D(\mathrm {x})$’s gradient differentiates the integral of the differences between the score functions of real and synthesized samples. Conversely, training the CFG generator involves finding an optimal$G(\mathrm {x})$that minimizes this difference. In this paper, we aim to derive an annealed weight preceding the CFG discriminator’s weight. This new explicit theoretical explanation model is called the annealed CFG method. To overcome the annealed CFG method’s limitation, as the method is not readily applicable to the state-of-the-art (SOTA) GAN model, we propose a nested annealed training scheme (NATS). This scheme keeps the annealed weight from the CFG method and can be seamlessly adapted to various GAN models, no matter their structural, loss, or regularization differences. We conduct thorough experimental evaluations on various benchmark datasets for image generation. The results show that our annealed CFG and NATS methods significantly improve the synthesized samples’ quality and diversity. This improvement is clear when comparing the CFG method and the SOTA GAN models.

Visible-infrared remote sensing object detection aims to achieve all-weather object detection by leveraging the complementary information from paired visible and infrared (RGB-IR) images. However, modality differences and weak alignment often limit its performance. Existing methods largely neglect the frequency discrepancies between modalities and require strict alignment, increasing complexity. To address these challenges, this study proposes a novel mask-guided frequency feature fusion (MGFF) method for RGB-IR object detection in remote sensing. Specifically, we develop a feature frequency decomposition and enhancement module using wavelet transform to reduce modality differences between RGB and IR images by restructuring and enhancing their frequency components. Additionally, we introduce a mask-guided feature reconstruction module and a feature-guided consistency loss, ensuring that even under weak alignment, the focus remains on integrating the target features from different modalities. Meanwhile, this loss is used to guide the reconstruction of features from different modalities. Finally, We design a multi-directional perception cross-modality fusion module to achieve deep fusion of multimodal information, which enhances object perception from different directions across modalities. Extensive evaluations on the widely recognized RGB-IR remote sensing benchmarks, including DroneVehicle and VEDAI, as well as the RGB-IR pedestrian dataset KAIST, substantiate the effectiveness of the proposed MGFF method. The results consistently demonstrate that the MGFF achieves a superior performance in terms of detection accuracy and robustness compared to existing state-of-the-art approaches.

Due to the limited output categories, semi-supervised salient object detection faces challenges in adapting conventional semi-supervised strategies. To address this limitation, we propose a multi-branch architecture that extracts complementary features from labeled data. Specifically, we introduce TripleNet, a three-branch network architecture designed for contour, content, and holistic saliency prediction. The supervision signals for the contour and content branches are derived by decomposing the limited ground truths. After training on the labeled data, the model produces pseudo-labels for unlabeled images, including contour, content, and salient objects. By leveraging the complementarity between the contour and content branches, we construct coupled pseudo-saliency labels by integrating the pseudo-contour and pseudo-content labels, which differ from the model-inferred pseudo-saliency labels. We further develop an enhanced pseudo-labeling mechanism that generates enhanced pseudo-saliency labels by combining reliable regions from both pseudo-saliency labels. Moreover, we incorporate a partial binary cross-entropy loss function to guide the learning of the saliency branch to focus on effective regions within the enhanced pseudo-saliency labels, which are identified through our adaptive thresholding approach. Extensive experiments demonstrate that the proposed method achieves state-of-the-art performance using only 329 labeled training images.

Dynamic convolution demonstrates outstanding representation capabilities, which are crucial for natural image segmentation. However, it fails when applied to medical image segmentation (MIS) and infrared small target segmentation (IRSTS) due to limited data and limited fitting capacity. In this paper, we propose a new type of dynamic convolution called dynamic parameter convolution (DPConv) which shows superior fitting capacity, and it can efficiently leverage features from deep layers of encoder in reconstruction tasks to generate DPConv kernels that adapt to input variations. Moreover, we observe that DPConv, built upon deep features derived from reconstruction tasks, significantly enhances downstream segmentation performance. We refer to the segmentation network integrated with DPConv generated from reconstruction network as the siamese reconstruction-segmentation network (SRS). We conduct extensive experiments on seven datasets including five medical datasets and two infrared datasets, and the experimental results demonstrate that our method can show superior performance over several recently proposed methods. Furthermore, the zero-shot segmentation under unseen modality demonstrates the generalization of DPConv. The code is available at: https://github.com/fidshu/SRSNet.

3D keypoint detection is of great interest to researchers in computer vision and graphics because it is an integral part of realizing many tasks, such as object tracking, 3D reconstruction, and shape registration. However, it is challenging to detect 3D keypoints quickly and stably due to the ambiguity of the keypoints and the presence of noise, density changes, and geometric distortions in the 3D point cloud. This paper proposes a novel 3D keypoint detection method based on point cloud structural saliency (PCSS) to realize stable and efficient 3D keypoint detection. First, we propose an effective point cloud feature descriptor called local spatial geometric feature, which can effectively combine spatial and geometric information to improve feature distinguishability. Second, we define a point cloud structural saliency representation that effectively characterizes the structured information in the point cloud. Finally, we generate 3D keypoints based on point cloud structural saliency using a non-maximum suppression method. We evaluate our method on five 3D keypoint benchmark datasets, and the experimental results demonstrate that it achieves state-of-the-art performance in 3D keypoint detection. Comparing it with previous keypoint detection methods further demonstrates the effectiveness and superiority of our method.

Although significant progress has been made in multi-view learning over the past few decades, it remains challenging, especially in the context of incomplete multi-view clustering, where modeling complex correlations among different views and handling missing data are key difficulties. In this paper, we propose a novel incomplete multi-view clustering network to address the aforementioned issue, named Incomplete Multi-view Clustering via Multi-level Contrastive Learning (IMC-MCL). Specifically, the proposed model aims to minimize the conditional entropy between views to recover missing data by dual prediction strategy. Moreover, the approach learns multi-level features, including latent, high-level and semantic features, with the goal of satisfying both reconstruction and consistency objectives in distinct feature spaces. Specifically, latent features are utilized to accomplish the reconstruction objective, while high-level features and semantic labels are employed to achieve the two consistency goals through contrastive learning. This framework enables the exploration of shared semantics within high-level features and achieves clustering assignment using semantic features. Extensive experiments have shown that the proposed approach outperforms other state-of-the-art incomplete multi-view clustering methods on seven challenging datasets.

Open-vocabulary multi-object tracking (OVMOT) is a cutting research direction within the multi-object tracking field. It employs large multi-modal models to effectively address the challenge of tracking unseen objects within dynamic visual scenes. While models require robust domain generalization and temporal adaptability, OVTrack, the only existing open-vocabulary multi-object tracker, relies solely on static appearance information and lacks these crucial adaptive capabilities. In this paper, we propose OVSORT, a new framework designed to improve domain generalization and temporal information processing. Specifically, we first propose the Adaptive Contextual Normalization (ACN) technique in OVSORT, which dynamically adjusts the feature maps based on the dataset's statistical properties, thereby fine-tuning our model's to improve domain generalization. Then, we introduce motion cues for the first time. Using our Joint Motion and Appearance Tracking (JMAT) strategy, we obtain a joint similarity measure and subsequently apply the Hungarian algorithm for data association. Finally, our Hierarchical Adaptive Feature Update (HAFU) strategy adaptively adjusts feature updates according to the current state of each trajectory, which greatly improves the utilization of temporal information. Extensive experiments on the TAO validation set and test set confirm the superiority of OVSORT, which significantly improves the handling of novel and base classes. It surpasses existing methods in terms of accuracy and generalization, setting a new state-of-the-art for OVMOT.

Event matching is a key component in a large-scale content-based publish/subscribe system. The performance of most existing algorithms is easily affected by the subscription matching probability. In this paper, we propose a new data structure, named AWAW B+-Tree, which is based on the width of the predicates, to efficiently index the subscriptions. The most notable feature ofAW B+-Treeis its ability to combine the advantages of different matching methods, thus achieving high and robust performance in dynamic environments. First, we implement both a forward matching method (AFM) and a backward matching method (ABM) based onAW B+-Tree. Then, we introduce a hybrid matching method (AHM) that combines AFM and ABM. Moreover, we extendAW B+-Treein three aspects: approximate matching, string type matching, and fine-grained parallelization. We conducted extensive experiments to evaluate the performance of the proposed matching algorithms on synthetic and real-world datasets. The experiment results reveal that AHM achieves a reduction in matching time by up to 53.8% compared to the state-of-the-art method. Additionally, AHM exhibits improved performance robustness, with up to a 76.9% reduction in terms of the standard deviation of matching time. Particularly in dynamic scenarios, AHM is at least 2.3 times faster and 41.3% more stable than its counterparts. Furthermore, by implementing parallelization, the matching speed of 8 threads can be accelerated by 4.16 times compared to the single-thread matching speed.

Keypoint detection plays a fundamental role in many applications, such as 3D reconstruction, object registration, and shape retrieval, and has attracted significant interest from researchers in computer vision and graphics. However, due to the ambiguity of the keypoint and the complexity of 3D objects, it is still tricky for existing 3D keypoint detection methods to generate stable keypoints with good coverage, especially for unsupervised detection methods. This paper proposes a 3D keypoint detection method based on hierarchical point saliency. This method can effectively and accurately locate the keypoints of a 3D point cloud, and it does not require complex training processes. First, we propose a simple and effective point descriptor called the local geometric structure feature, which can effectively characterize the geometric structure changes of 3D point clouds and has a strong feature identification ability. Second, we define two saliency measures used to characterize the saliency of points in the point cloud, which are low-level and high-level saliency. Third, we hierarchically characterize the saliency of points by combining the low-level and high-level saliency, thus measuring the probability that a point belongs to a keypoint. Finally, we extensively test our method on three benchmark 3D point cloud datasets, and the experimental results demonstrate that our method achieves state-of-the-art performance in keypoint detection tasks, significantly superior to the prior hand-crafted and deep-learning-based 3D keypoint detection methods.

Multi-radio access technology (multi-RAT) enabled mobile edge computing (MEC) has emerged as a promising paradigm for supporting diverse applications with heterogeneous service requirements. However, efficiently managing resources to accommodate both ultra-reliable low-latency communications (URLLC) and enhanced mobile broadband (eMBB) services remains challenging, especially in large-scale networks. In this paper, we investigate a joint optimization problem involving user association, task offloading, power and bandwidth allocation, and scheduling policies within a multi-RAT-enabled MEC system to efficiently address the heterogeneous demands of URLLC and eMBB services. We first formulate a generalized optimization problem and mathematically derive optimal power and task offloading strategies to reduce the search space. We then propose improved scheduling algorithms that sequentially update scheduling decisions based on arrival times at the edge server. Furthermore, we develop a matrix-based cooperative evolutionary computation framework with inner and outer agents to efficiently handle the large-scale optimization problem. Extensive simulation results demonstrate that our proposed approach significantly outperforms conventional scheduling methods and representative evolutionary algorithms.

Consensus mechanism is the foundational protocol for achieving distributed consistency among replicas in a blockchain network. A well-designed consensus mechanism needs to balance performance such as complexity, consensus mechanism initiative and dynamic adaptability. Based on Hot-Stuff (a BFT-like consensus with O(n) complexity), we propose a practical and robust consensus mechanism, namely Practical and Robust HotStuff, denoted as PRO-HotStuff. Firstly, PRO-HotStuff redesigns a pacemaker that simultaneously supports replica synchronization and quorum certificate caching, and thus achieves practical view change with O(n) communication complexity while avoiding the additional phase introduced by HotStuff. Secondly, PRO-HotStuff gives the leader election basis by introducing the theory of planed behavior (TPB) and a reputation mechanism. It facilitates restricting the malicious replicas while encouraging the trustworthy replicas, thus to enhance the robustness of PRO-HotStuff. Thirdly, the implementation design of PRO-HotStuff as well as its reconfiguration mechanism for dynamic adaptability is presented. Proofs of correctness of PRO-HotStuff are also provided. Finally, experiments demonstrate that compared to existing HotStuff-like consensus mechanisms, PRO-HotStuff has significant advantages in terms of consensus performance, security, and dynamic adaptability.

Content-based publish/subscribe systems have the capability to achieve fine-grained data distribution, rapidly forwarding data from publishers to subscribers with specific requirements. The event matching algorithm is a fundamental component, quickly searching for subscriptions that match an event based on constraints defined by subscribers. As data scales continue to expand, there is a heightened demands for more efficient, robust, and versatile event matching algorithms. In this paper, we propose a novel data structure called the Dual-ended Interval Tree (DI-Tree). Firstly, given the splitting point, this data structure classifies intervals into three categories based on the joint distribution of their left and right endpoints in the attribute value domain. Furthermore, the DI-Tree utilizes blue and green nodes to store these three categories of intervals, resulting in enhanced indexing efficiency. Moreover, by utilizing the DITree to efficiently search matching and unmatching intervals, we develop innovative forward and backward event matching algorithms. Additionally, to enhance matching efficacy and reduce memory usage, we introduce key optimization techniques, focusing on improving node balance and bitset optimization. We conduct extensive experiments to evaluate the performance of DITree. When compared with five state-of-the-art event matching algorithms, the DI-Tree demonstrates an average reduction of up to 76.8 % in terms of matching time. This significant improvement highlights the effectiveness of our proposed strategies and the potential of DI-Tree in optimizing event matching performance.

In this work, we study the problem of dispatching an unmanned aerial vehicle (UAV) for data collection of Internet of Things (IoT) devices, where a UAV departs from a data center, then visits some IoT devices for data collection and finally returns to the data center. Different from most existing works on UAV-enabled data collection, we assume that the UAV’s collection point, i.e., the location where the UAV stays during the data collection process, can be deployed anywhere within the communication range of each IoT device, rather than being assumed to be in a fixed position. This new assumption is motivated by the fact that the collection point has a great impact on both time and energy consumption of the UAV during its data collection tour. Thus, in this work, we focus on minimizing the UAV’s task completion time and energy consumption during a data collection tour, by jointly optimizing the UAV’s collection point for each IoT device, flight trajectory and flight speed. We formulate this problem as a multiobjective optimization problem, which is solved by executing the following three successive steps: 1) we first employ the ant colony optimization (ACO) algorithm to decide the UAV’s visiting order of all IoT devices; 2) we then reduce the searching space of the collection point for each visited IoT device by using geometric theory and reformulate the original problem; and 3) we finally develop an enhanced multiobjective particle swarm optimization (EMOPSO) algorithm by incorporating a novel gbest selection strategy to identify the optimal collection point for each visited IoT device, based on which the corresponding flight trajectory as well as the flight speed is calculated. We refer to the above three-step hybrid algorithm as ACO-EMOPSO-G. Extensive evaluations validate the superiority of ACO-EMOPSO-G in terms of the tradeoff between the UAV’s task completion time and energy consumption, compared with some other data collection approaches.

To realize carbon emission reduction, restricting regional carbon emissions while meeting electricity usage is a critical but not trivial problem. In this paper, we propose a game-based pricing scheme for joint carbon emission rights (CER) and electricity trading between the electricity prosumers within a microgrid. For modeling and theoretical analysis, we first introduce the utility functions of electricity producers and consumers, which are determined by CER and electricity prices in a coupled way. Then, the multi-leader multi-follower (MLMF) Stackelberg game and non-cooperative game are employed to formulate the electricity and CER pricing and trading, respectively. The game equilibriums convince that optimal prices for both electricity and CER exist to satisfy electricity usage while meeting the carbon emission restriction. For implementation, the blockchain with smart contracts is developed to undertake the CER and electricity trading in a transparent and credible way. A prototype system based on Fabric blockchain verifies the feasibility of the proposed scheme, which demonstrated a five-fold increase in the economics and electricity generation utility of the microgrid and achieved a 2% reduction in carbon emissions compared to the baseline model.

Linking medical data silos for medical model learning and sharing makes for better healthcare for humanity. Before that, two critical issues must be solved, i.e., patient privacy protection and data contributors’ rights and interests. This paper proposes an evolutionary medical data modeling and sharing (EMDMS) framework. Specifically, EMDMS adopts a federated learning scheme to coordinate the decentralized medical model learning and model aggregation without the leakage of raw data. A dual-loop federated learning mechanism with a tailored control strategy is developed for the realization of evolutionary model learning with the consideration of the ever-growing medical data. Then, a long-term pricing and revenue distribution strategy is designed for evolutionary model sharing, thus to make the medical model self-growth. It not only ensures fair benefits for data contributors but also enables low-cost sharing of models for public welfare. EMDMS runs on the sharded blockchain to support parallel tasks where dedicated smart contracts are implemented for EMDMS to guarantee security and trustworthiness. A prototype system with simulations on the Fed-ISIC2019 dataset demonstrates the effectiveness of EMDMS and its advantages over some existing typical solutions.

Modern Siamese trackers mainly rely on classifying and regressing pre-defined anchor boxes or per-pixel points, which are assigned as positive and negative samples based on box intersection-over-union (IoU) or point distance with corresponding ground-truth for training. However, this rigid configuration potentially involves some noisy and ambiguous positive samples, leading to an inconsistency problem between classification and regression, which limits the tracking performance. In this paper, we propose a novel probabilistic assignment approach that dynamically determines positive/negative samples for each instance. To be specific, we first customize the confidence scores of positive candidates by comprehensively exploring the outputs from both classification and regression heads, and fit these scores as a probability distribution. Therefore, it is intuitive to conduct adaptive label assignment according to their probabilities. Then, we also consider dynamic re-weighting factor for each positive sample, jointly optimizing the classification and regression losses in a synchronized manner. Moreover, we introduce a decoupled IoU prediction branch to bridge the gap between the training and inference objectives for accurate tracking. Thanks to well-aligned procedures, our method significantly improves the performance of both CNN-based and Transformer-based trackers. Extensive experiments conducted on several tracking benchmarks including LaSOT and GOT-10k, demonstrate the effectiveness and efficiency of the proposed probabilistic assignment tracker.

Wireless rechargeable sensor networks (WRSNs) are promising in maintaining sustainable large-area monitoring tasks. Mobile chargers (MCs) are commonly used in WRSNs to replenish energy to nodes due to its flexibility and easy maintenance. Most existing works on WRSNs focus on designing offline or model-based online charging methods, which need the exact system information to conduct the optimization. However, in practical WRSNs, the exact system information such as the nodes' locations and energy consumption rates may not be easily accessible to the optimizer due to their unpredictability and high dynamics. Thus, in this work, we jointly optimize the MC's trajectory design and charging scheduling in a general and practical WRSN with inaccessibility to the exact system information, such that the charging utility of the MC is maximized. To address this problem, we introduce the model-free reinforcement learning (RL) technique, which enables the MC to learn to jointly optimize its moving trajectory and charging scheduling by interacting with the environment and tracking feedback signals from nodes and obstacles in real time. Specifically, we develop a soft actor-critic based mobile security policy intervened algorithm (SAC-MSPI) based on a novel safe RL framework, which maximizes the MC's charging utility while maintaining the safe movement (not hitting obstacles) for the MC during the entire charging period. Extensive evaluation results show that the proposed SAC-MSPI algorithm outperforms existing main RL solutions and traditional algorithms with respect to the charging utility maximization as well as the collision avoidance.

In this work, we study the problem of dispatching multiple unmanned aerial vehicles (UAVs) for data collection in internet of things (IoT), where each UAV departs from its start point, visits some IoT devices for data collection and returns to its destination point. Considering the UAV’s limited onboard energy and the time required to collect data from all IoT devices, it is essential to appropriately assign the data collection task for each UAV, such that none of the dispatched UAVs consumes excessive energy and the maximum task completion time among all UAVs is minimized. To optimize those two conflicting objectives, we focus on minimizing the maximum task completion time and the maximum energy consumption among all UAVs, by jointly designing the flight trajectory, hovering positions for data collection and flight speed of each UAV. We formulate this problem as a multi-objective optimization problem with the aim of obtaining a set of Pareto-optimal solutions in terms of time or energy dominance. Due to the NP-hardness and complexity of the formulated problem, we propose a multi-strategy multi-objective ant colony optimization algorithm (MSMOACO), which is developed based on a constrained ant colony optimization algorithm with a fitnessguided mutation strategy and an adaptive hovering strategy being delicately incorporated, to solve the problem. To accommodate the practical scenario, we also design a novel geometry-based collision avoidance strategy to reduce the possibility of collisions among UAVs. Extensive evaluations validate the effectiveness and superiority of the proposed MSMOACO, compared with previous approaches.

For software-defined networking (SDN), multi-field packet classification plays a key role in the processing of flows, mainly involving fast packet classification and dynamic rule updates. Due to the increasing complexity and size of rulesets, it is becoming more difficult to design a packet classification algorithm which achieves fast lookup and update. In this paper, we propose a novel structure, PT-Tree, for packet classification with high overall performance. PT-Tree cascades the prefixes of multiple discriminatory bytes to achieve efficient partitioning of the ruleset, thereby reducing the search space and ensuring the performance of both lookup and update. Meanwhile, a multi-granularity priority-aware pruning mechanism (MPPM) based on PT-Tree filters out most of the candidate subsets, which further improves the lookup speed. In addition, we propose an auxiliary tree-based optimization method (ATOM) to cope with severely overlapping rules in the search space. Therefore, PT-Tree can better handle the case where the rules in certain fields are skewed. We conduct comprehensive experiments to evaluate the performance of PT-Tree. The results show that compared with the state-of-the-art, the lookup time of PT-Tree is reduced by at least 49.95% on average. Moreover, PT-Tree is also at least 7.13x and 33x faster than the baselines in terms of the update and construction speed on average, respectively. Meanwhile, the performance stability of PT-Tree on multiple rulesets improves by up to 13.68 times.

Packet classification, as a crucial function of networks, has been extensively investigated. In recent years, the rapid advancement of software-defined networking (SDN) has introduced new demands for packet classification, particularly in supporting dynamic rule updates and fast lookup. This paper presents a novel structure called DBTable for efficient packet classification to achieve high overall performance. DBTable integrates the strengths of conventional packet classification methods and neural network concepts. Within DBTable, a straightforward indexing scheme is proposed to eliminate rule replication, thereby ensuring high update performance. Additionally, we propose an iterative method for generating a discriminative bitset (DBS) to evenly partition rules. By utilizing the DBS, rules can be efficiently mapped in a hash table, thus achieving exceptional lookup performance. Moreover, DBTable incorporates a hybrid structure to further optimize the worst-case lookup performance, primarily caused by data skewness. The experiment results on 12 256k rulesets show that, compared to seven state-of-the-art schemes, DBTable achieves an overall lookup speed improvement ranging from 1.53x to 7.29x, while maintaining the fastest update speed.

High-quality underwater images are a vital source of modern marine vision and multimedia applications. But low visibility with color and contrast distortions in uneven underwater illumination conditions poses several challenges to these applications (e.g., visual servoing, long-range navigation, unmanned underwater vehicles, and SONAR imaging, etc.) working in robust conditions from dawn to dusk. Direct enhancement deteriorates the structure and texture with objectionable color casts due to distance-dependent attenuation and light scattering. This paper presents an adaptive self-supervised network for underwater image enhancement (ASSU-Net), which can work without relying on the type and quantity of training images, rather, it is capable of working with only a few input images. In this network, we split the image into reflection and illumination components to simplify the solution space, allowing us to handle the artifacts associated with each component independently. A structure and texture awareness scheme is introduced while following the mutual consistency of decomposition in combination with the histogram distribution. This scheme is embedded in the network to constrain objectionable artifacts (i.e., structure texture and edge distortions). The network loss is optimized to force the network to learn with a few shots of unpaired data, where we preserve visual details for low-lit underwater images. Extensive experiments are performed to demonstrate the superiority of the proposed method.

Content-based publish/subscribe systems are widely used in many fields.Event matching is the core component to achieve fine-grained content-based data distribution.Many efficient algorithms have been proposed to improve event matching performance.However, in large-scale content-based publish/subscribe systems, event matching is still the performance bottleneck of the entire system due to the need to perform a lot of operations, such as additions, comparisons and bitmarkings.In this paper, we explore to convert various nonlogical operations into efficient logical ones, and propose a bitsetbased optimization paradigm (BOP) for matching algorithms.On the one hand, BOP can eliminate expensive operations in the matching process, greatly improving matching performance.On the other hand, BOP can stabilize the performance of matching algorithms, ensuring the quality of service of data distribution.We apply BOP to optimize two existing matching algorithms, namely TAMA and REIN.The experimental results show that BOP shortens the matching time of TAMA and REIN by more than 60%.In addition, the performance of optimized versions is more stable than the original matching algorithms.

In this paper, we study an unmanned aerial vehicle (UAV)-enabled wireless rechargeable sensor network (WRSN), where a rotary-wing UAV travels along a fixed trajectory while providing wireless charging services for a set of sensor nodes deployed on the ground. Given the practical speed-related flight energy model, we focus on minimizing the UAV’s flight energy during a time-bounded charging tour by appropriately controlling the UAV’s travelling speed, such that the charging demand of each node is satisfied. We first investigate the optimal speed control with the minimized flight energy on arbitrarily-shaped trajectories in a 2D space. We adopt the spatial discretization to tackle the non-convexity of the formulated problem, which is then solved by interior-point method with the provable upper bound of the UAV’s flight energy. Next, we develop the optimal speed control for the UAV to travel along a 1D trajectory, i.e., a straight line, which is commonly seen in many UAV applications. Extensive evaluations validate the effectiveness of our speed control design in terms of the UAV’s flight energy minimization.

Blockchain has gained significant adoption in energy trading, offering benefits for both economy and environment. Consensus, in particular, is a decisive factor for blockchain-based energy trading systems to operate efficiently and securely. However, the consensuses currently applied have been criticized for being too energy intensive or not sufficiently decentralized, which counteracts the positive effect of energy trading. Besides, consensus and energy trading are treated separately in many energy trading blockchain-based studies. In this article, we propose a green and efficient consortium blockchain-enabled transaction system for energy trading, meeting the requirement of low energy consumption under security. We then design a two-stage consensus mechanism called proof-of-energy that is coupled to trading through “energy” and naturally uses the monetary rewards to stimulate prosumer participation. Specifically, it retains a strong degree of decentralization, which selects a dynamic delegation with high historical energy generation and motivates delegates to compete for new blocks by solving a meaningful puzzle. Furthermore, a variable block reward is investigated as the incentive to regulate trading and consensus behavior within a reasonable range of energy consumption. Finally, we design a two-layer iterative algorithm to obtain the optimal consensus strategy and block rewards, taking the noncooperative game approach with the consideration of the strategy effect on the pricing model. Our simulation results show that the proposed blockchain-enabled system has a high energy efficiency ratio that improves the social welfare and reduces the consensus overhead.

Energy harvesting technology enables wireless sensor networks (WSNs) to be self-sustainable, for maintaining long-term key performance indicators, such as the data throughput and sensing coverage. Due to the highly dynamic and complex environment, energy sources (ES) cannot provide stable energy supply, which needs the efficient learning algorithm to enable system adaptations. This article reports on the development of reinforcement learning (RL) methodology to long-term data collection in self-sustainable WSNs. Specifically, we consider the WSN as a 2-D rectangular region, where a mobile sensor (MS) can harvest energy from ambient environments while transmitting the collected data to a fixed sink. Due to the changing environment and the mobility of the MS, the harvested energy by the MS at each slot presents spatiotemporal dynamics within the network, which severely affects the performance of data throughput from the MS to the sink. The MS’s trajectory is investigated to maximize the long-term average MS-to-sink data throughput. Due to the unknown energy arrival information as well as the locations of ESs, we formulate the problem as a Markov decision process, which is then solved with model-free RL. In particular, the deep deterministic policy gradient (DDPG) is applied to tackle the continuous and deterministic movement space. Results show that the MS can learn and optimize the moving trajectory by intelligently tracking the aggregated received energy over slots. Finally, the MS can identify and move to the optimal location where the maximized long-term average MS-to-sink data throughput is achieved. Extensive numerical evaluations are conducted to investigate the impact of various system parameters on the network performance.

Mobile chargers (MCs) are usually dispatched to deliver energy to sensors in wireless rechargeable sensor networks (WRSNs) due to its flexibility and easy maintenance. This paper concerns the fundamental issue of charging path DEsign with the Minimized energy cOst (DEMO), i.e., given a set of rechargeable sensors, we appropriately design the MC’s charging path to minimize the energy cost which is due to the wireless charging and the MC’s movement, such that the different charging demand of each sensor is satisfied. Solving DEMO is NP-hard and involves handling the tradeoff between the charging efficiency and the moving cost. To address DEMO, we first investigate how to identify a single charging position where the MC could stay to charge a set of sensors distributed within a small area with the maximized charging efficiency. Then, based on the result obtained in the case of optimizing a single charging position, we develop a computational geometry-based algorithm to deploy multiple charging positions within the whole network, by considering the fixed and finite charging range of the MC. We prove that the designed algorithm has the approximation ratio of$O\!\left ({\ln \!N}\right)$, where$N$is the number of sensors. Then we construct the charging path by calculating the shortest Hamiltonian cycle passing through all the deployed charging positions within the network. In addition, we investigate the impact of the network topology as well as the distribution of charging demands among sensors on the MC’s energy cost during a charging tour. Extensive evaluations validate the superiority of our path design in terms of the MC’s energy cost minimization, compared with existing main algorithms.

Visual object tracking is basically formulated as target classification and bounding box estimation. Recent anchor-free Siamese trackers rely on predicting the distances to four sides for efficient regression but fail to estimate accurate bounding box in complex scenes. We argue that these approaches lack a clear probabilistic explanation, so it is desirable to model the uncertainty and ambiguity representation of target estimation. To address this issue, this paper presents an Uncertainty-Aware Siamese Tracker (UAST) by developing a novel distribution-based regression formulation with localization uncertainty. We exploit regression vectors to directly represent the discretized probability distribution for four offsets of boxes, which is general, flexible and informative. Based on the resulting distributed representation, our method is able to provide a probabilistic value of uncertainty. Furthermore, considering the high correlation between the uncertainty and regression accuracy, we propose to learn a joint representation head of classification and localization quality for reliable tracking, which also avoids the inconsistency of classification and quality estimation between training and inference. Extensive experiments on several challenging tracking benchmarks demonstrate the effectiveness of UAST and its superiority over other Siamese trackers.

Mobile chargers (MCs) are usually dispatched to deliver energy to sensors in wireless rechargeable sensor networks (WRSNs) due to its flexibility and easy maintenance. This paper concerns the fundamental issue of charging path DEsign with the Minimized energy cOst (DEMO), i.e., given a set of rechargeable sensors, we appropriately design the MC’s charging path to minimize the energy cost which is due to the wireless charging and the MC’s movement, such that the different charging demand of each sensor is satisfied. Solving DEMO is NP-hard and involves handling the tradeoff between the charging efficiency and the moving cost. To address DEMO, we first develop a computational geometry-based algorithm to deploy multiple charging positions where the MC stays to charge nearby sensors. We prove that the designed algorithm has the approximation ratio of O(lnN), where N is the number of sensors. Then we construct the charging path by calculating the shortest Hamiltonian cycle passing through all the deployed charging positions within the network. Extensive evaluations validate the effectiveness of our path design in terms of the MC’s energy cost minimization.

In recent years, cross-modal hashing (CMH) has attracted considerable attention due to its ability to learn across different modalities and its high efficiency for similarity retrieval applications. This procedure is computationally inexpensive when dealing with large-scale multi-modalities datasets. However, they do not form the ideal representative model to fully exploit multi-modal data’s underlying properties despite their successful performance. We identify that: (i) most CMH models in their current forms transform the real data points into discrete compact binary codes, which can limit their ability to prevent the loss of important information and thereby produce suboptimal results. (ii) the discrete-binary constraint model is hard to implement, and relaxing the binary constraints is a common property in most existing methods, which often leads to significant quantization errors. (iii) handling the CMH in a symmetry domain leads to a complex and inefficient optimization problem. This paper addresses the above challenges and proposes a novel Asymmetric Correlation Quantization Hashing (ACQH) method. ACQH learns a projection matrix for each heterogeneous modality to map the data point into a low-dimensional semantic space and constructs a compositional quantization to generate hash codes, using the pairwise semantic similarity preservation and the pointwise label regression. As a specific instantiation of our model, we use discrete iterative optimization to obtain the unified hash codes across different modalities. Extensive experiments show that ACQH outperforms state-of-the-art methods on several diverse datasets.

Visual tracking has achieved great progress due to numerous different algorithms. However, deep trackers based on classification or Siamese network still have their specific limitations. In this work, we show how to teach machines to track a generic object in videos like humans, who can use a few search steps to perform tracking. By constructing a Markov decision process in Deep Reinforcement Learning (DRL), our agents can learn to determine hierarchical decisions on tracking mode and motion estimation. To be specific, our Hierarchical DRL framework is composed of a Siamese-based observation network which models the motion information of an arbitrary target, a policy network for mode switch and an actor-critic network for box regression. This tracking strategy is more in line with human behavior paradigm, and is effective and efficient to cope with fast motion, background clutter and large deformations. Extensive experiments on the GOT-10k, OTB-100, UAV-123, VOT and LaSOT tracking benchmarks, demonstrate that the proposed tracker achieves state-of-the-art performance while running in real-time.

In the last few years, single image super-resolution (SISR) has benefited a lot from the rapid development of deep convolutional neural networks (CNNs), and the introduction of attention mechanisms further improves the performance of SISR. However, previous methods use one or more types of attention independently in multiple stages and ignore the correlations between different layers in the network. To address these issues, we propose a novel end-to-end architecture named global-context attention network (GCAN) for SISR, which consists of several residual global-context attention blocks (RGCABs) and an inter-group fusion module (IGFM). Specifically, the proposed RGCAB extracts representative features that capture non-local spatial interdependencies and multiple channel relations. Then the IGFM aggregates and fuses hierarchical features of multi-layers discriminatively by considering correlations among layers. Extensive experimental results demonstrate that our method achieves superior results against other state-of-the-art methods on publicly available datasets.

Wireless power transfer (WPT) enables a reliable and convenient charging paradigm. This article concerns the fundamental issue of energy saving in wireless rechargeable sensor networks (WRSNs), i.e., given a fixed number of rechargeable sensors (RSs) with their locations and charging demands, we focus on a minimal charging expenditure (MAP) problem with directional WPT to decrease the energy expenditure of the charger, on condition that the charging demands of all sensors are satisfied. In particular, we consider the anisotropic energy receiving property of RSs, which is closely related to the distance and the angle between the sensor and the charger antenna's orientation in directional WPT. We transform the MAP problem into an optimal function placement (OFA) problem, which can be geometrically analyzed in a rectangular coordinate system and is NP-hard. First, we study the OFA problem in the case of uniformly distributed sensors with identical charging demands, we develop the uniform charging strategy (UCS) to bound the total charging expenditure as Θ(1) for any number of sensors N. Based on the acquired insights, we further studied the OFA problem when the distribution of charging demands is Gaussian. We bound the total charging expenditure as Θ(1) for any number of sensors N, by developing the layered charging strategy (LCS). Extensive simulation results confirmed the performance of our design compared with two baseline algorithms. Both of the theoretical and simulations results reveal that the total energy expenditure of the charger is strongly related to the sensors' charging demands, however, is less affected by the number of sensors in the network.

This article reports on the development of a deep Q-learning approach to long-term energy collection in self-sustainable sensor networks, which consists of two static chargers (SCs) and one rechargeable mobile sensor (MS). In particular, we assume that the SCs can harvest energy from the ambient environment and charge the MS via electromagnetic (EM) radiation. As the energy harvesting (EH) process is random and the radiated energy fades over distance, the achievable energy by the MS at each slot demonstrates spatiotemporal dynamics in a certain area. Thus, we focus on the problem of trajectory optimization for an autonomous MS to maximize the long-term average achievable energy per slot from both chargers. Due to the inaccessible charger-side information, such as the EH profile and locations of SCs as well as the transmit power, we introduce deep Q-learning, a model-free reinforcement learning approach, based on which the MS can learn and optimize the moving trajectory by intelligently tracking the aggregated received EM signal without any other explicit external information. Simulation results show that the MS can identify the best energy collecting location and finally moves there along the learned trajectory. We also investigate the impact of system parameters, such as initial position and moving cost per unit distance on the performance of the proposed training algorithm, such as convergence rate and stability via extensive numerical evaluations.

Object tracking is one of the fundamental tasks of computer vision and it is still a major challenge that trackers can balance between real-time speed and high performance. In this paper, a novel Siamese Actor-Critic network (SiamAC) is proposed to improve the accuracy and robustness of tracking while performing with real-time. Specifically, SiamAC consists of a fully convolutional siamese matching network for similarity learning and an Actor-Critic framework trained by reinforcement learning. The Actor is aimed to infer the optimal action in continuous space, while the Critic produces a Q-value to guide effectively the offline training of both Actor and Critic networks. During inference, according to the response map produced by the matching network, the most similar positions and scaled candidate patches are selected as the input of Actor-Critic. Subsequently, Actor can effectively search more precise location of these candidates and the Critic acts as a validator to decide the final tracking results with the highest confidence. Benefiting from this refinement, traditional multi-scale test and certain hyper-parameters in Siamese trackers can be discarded. Evaluations on popular benchmarks demonstrate that the proposed SiamAC achieves state-of-the-art performance with a real-time speed.

Recently, trackers based on Siamese networks have attracted spread attention in the field of tracking because of a balance between accuracy and speed. Learning powerful representation via effective offline training strategy is critical for constructing high performance Siamese trackers. However, features extracted in most networks cannot accurately distinguish a tracked target from the background with semantic information in some challenging scenes. In this paper, we develop a Fully-Convolutional deep Quadruple Network (QuadFC) to learn more expressive representation via a novel multi-task loss function composed of a differential pairwise loss for tracking and a constructed triplet loss for similarity learning, which can be trained offline in an end-to-end mode. During inference, the proposed deep architecture does not need to update model and the positive-negative branches are removed to avoid unnecessary calculations. In particular, our approach is able to extract more discriminative features and perform robust visual tracking, due to joint representation learning and taking full use of original samples via the combination of positive-negative pairs. Furthermore, theoretical analysis of QuadFC is carried out through comparing the gradients of different loss functions. Extensive experiments on several tracking benchmarks, show that the proposed tracker achieves the state-of-the-art tracking performance while running at 68 FPS. The code can be available at https://github.com/DavidZhangdw/QuadFC.

Recently, siamese trackers have been increasingly popular in visual tracking community. Despite great success, it is still difficult to perform robust tracking in various challenging scenarios. In this paper, we propose a novel similarity matching network, that effectively extracts fine-grained semantic features by adding a Classification branch and a Category-Aware module into the classical Siamese framework (CCASiam). More specifically, the supervision module can fully utilize the class information to obtain a loss for classification and the whole network performs tracking loss, so that the network can extract more discriminative features for each specific target. During online tracking, the classification branch is removed and the category-aware module is designed to guide the selection of target-active features using a ridge regression network, which avoids unnecessary calculations and over-fitting. Furthermore, we introduce different types of attention mechanisms to selectively emphasize important semantic information. Due to the fine-grained and category-aware features, CCASiam can perform high performance tracking efficiently. Extensive experimental results on several tracking benchmarks, show that the proposed tracker obtains the state-of-the-art performance with a real-time speed.

Recently, Siamese networks based tracking algorithms have shown favorable performance. Latest work focuses on better feature embedding and target state estimation, which greatly improves the accuracy. Nevertheless, the simple cross-correlation operation of the features between a fixed template and the search region limits their robustness and discrimination capability. In this paper, we pay more attention to learn an outstanding similarity measure for robust tracking. We propose a novel relation network that can be integrated on top of previous trackers without any need for further training of the siamese networks, which achieves a superior discriminative ability. During online inference, we utilize the feedback from high-confidence tracking results to obtain an additional template and update it, which improves the robustness and generalization. We implement two versions of the proposed approach with the SiamFC-based tracker and SiamRPN-based tracker to validate the strong compatibility of our algorithm. Extensive experimental results on several tracking benchmarks indicate that the proposed method can effectively improve the performance and robustness of the underlying trackers without reducing speed too much, and performs superiorly against the state-of-the-art trackers.

The abuse of personal identity information is one of the most serious problems worldwide. Most social services or businesses use the identity authorization to confirm their validity and legality and the copies of users' identity certification are usually recorded by the service providers. It is easy to leak the users' identity information due to the untrustworthy service provider or single-point security failure, and various social problems are then caused. To deal with such problems, this paper proposes a Blockchain-based Identity Authorization mechanism (BIA). First, an Identity Authorization Module (IAM) is devised, which reads the identity certificate and transform the identity plaintext to ciphertext under the authorization by the user's identity certificate entity and password. IAM guarantees the security of identity information by keeping its plaintext offline. Second, a Business Contract Module (BCM) is designed, which provides a general smart contract framework for identity authorization that can be adopted by most of social services or businesses. Third, a double-chain blockchain infrastructure is developed, whereby the encrypted identity information and service smart contracts are respectively recorded in the tamper-resistant, non-repudiable, and publicly verifiable way. Finally, a prototype system has been developed to verify the security, feasibility and effectiveness of the proposed BIA.

In proof-of-work (PoW)-based blockchain networks, the miners contribute their distributed computation in solving a crypto-puzzle competition to win the reward. To secure stable profits, some miners organize mining pools and share the rewards from the pool in proportion to each miner's contribution. However, some miners may exhibit malicious behaviors which cause a waste of distributed computation resource, even posing a threat on the efficiency of blockchain networks. In this paper, we propose a new game-theoretic framework to incentivize miners mining honestly and help to bring about a higher total welfare of blockchain networks. We first formulate the mining process as a noncooperative iterated game. We then propose a mechanism in terms of zero-determinant strategies (ZD strategies) to encourage the cooperative mining and improve the efficiency of mining in PoW-based blockchain networks. In addition, we theoretically analyze the maximum system welfare of the target pool through the method of optimization. Numerical illustrations are also presented to support our theoretical results.

Spectral clustering (SC) is a fundamental technique in the field of data mining and information processing. The similarity matrix of the input data set plays a vital role in SC methods. Since the similarity matrix computation is independent of the clustering procedure, the final results may be suboptimal if the learned similarity is not optimal in SC methods. In this paper, we proposed a novel data Clustering based on Locality Embedding And Reconstruction, CLEAR for short. The proposed CLEAR model combines the graph similarity matrix computation and data clustering procedure together by assigning adaptive weights to the local neighbors of each data point based on locally linear embedding and reconstruction. It is worth noting that CLEAR imposes a rank constraint to the graph Laplacian matrix of the similarity matrix, which leads to a favorable number of graph components in the final clustering. We formulate the proposed CLEAR model in a efficient way which can be solved easily, and show the theoretical relationship to K-means and SC methods. Extensive results on both synthetic data and real-world data show the effectiveness of our method.

Recently, hash algorithms catch amounts of sights in the field of machine learning. Most existing hash methods directly utilize a vector, which can be piped by the column of image matrix, as a unit and adopt some feature extraction functions to project the original data into generally shorter fixed-length values or characters. Then each of these projected real values is quantized or hashed into zero-one bit by a thresholding, such as locality sensitive hashing (LSH) and principal component analysis hashing (PCAH). However, the plain elongation of images may cause the curse of dimensionality. In this paper, different with PCAH method, the two dimensional (2D) images are directly used to extract the feature by two-dimensional principal component analysis (2DPCA) and 2DPCAH performs hashing using these 2DPCA-extracted data. Furthermore, starting with 2DPCA-extracted data, we apply iterative quantization (ITQ) technique, which aims to finding a rotation matrix so as to minimize the quantization error of mapping these data to a zero-centered binary hypercube. The experimental results indicate that 2DPCAH, 2DPCA-RR and 2DPCA-ITQ are competitive compared with traditional PCAH and other classic methods.

In this paper, three new algorithms are presented by applying group idea and collaborative thought to projective dictionary pair learning (DPL). These algorithms further extend the framework of discriminative dictionary learning (DL). Based on projective dictionary pair learning which realizes the goals of signal representation and pattern classification by learning a synthesis dictionary and an analysis dictionary at the same time, this paper successfully facilitates group idea and collaborative thought into projective dictionary pair learning. The application of these methods not only leads to very competitive accuracies in face recognition tasks compared with DPL, but also greatly reduces the time complexity in training and test stages, compared with conventional DL methods.

Multi-label learning has attracted an increasing attention from many domains, because of its great potential applications. Although many learning methods have been witnessed, two major challenges are still not handled very well. They are the correlations and the high dimensionality of data. In this paper, we exploit the inherent property of the multi-label data and propose an effective sparse multi-label learning algorithm. Specifically, it handles the high-dimensional multi-label data by using a regularized partial least squares discriminant analysis with a l1-norm penalty. Consequently, the proposed method can not only capture the label correlations effectively, but also perform the operation of dimensionality reduction at the same time. The experimental results conducted on eight public data sets show that our method is promising and outperformed the state-of-the-art multi-label classifiers in most cases.