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

Automated lesion segmentation through breast ultrasound (BUS) images is an essential prerequisite in computer-aided diagnosis. However, the task of breast segmentation remains challenging, due to the time-consuming and labor-intensive process of acquiring precise labeled data, as well as severely ambiguous lesion boundaries and low contrast in BUS images. In this article, we propose a novel semi-supervised breast segmentation framework based on confidence-ranked features and bi-level prototypes (CoBiNet) to alleviate these issues. Our outputs are derived from two branches: classifier and projector. In the projector branch, we first rank the features by multilevel sampling to obtain multiple feature sets with different confidence levels. Then, these sets are progressed in two directions. One is to acquire local prototypes at each level by local sampling and perform trans-confidence level (TCL) contrastive learning. This encourages the low-confidence features to converge to the high-confidence features, which enhances the model's ability to recognize ambiguous regions. The other process is to generate more representative global prototypes by global sampling, followed by generating more reliable predictions and performing cross-guidance (CG) consistency learning with the classifier output predictions, facilitating knowledge transfer between the structure-aware projector and the category-discriminative classifier branches. Extensive experiments on two well-known public datasets, BUSI and UDIAT, demonstrate the superiority of our method over state-of-the-art approaches. Codes will be released upon publication.

Multi-Task Learning (MTL) in Neural Combinatorial Optimization (NCO) is a promising approach for training a unified model capable of solving multiple Vehicle Routing Problem (VRP) variants. However, existing Reinforcement Learning (RL)-based multi-task methods can only train light decoder models on small-scale problems, exhibiting limited generalization ability when solving large-scale problems. To overcome this limitation, this work introduces a novel multi-task learning method driven by knowledge distillation (MTL-KD), which enables efficient training of heavy decoder models with strong generalization ability. The proposed MTL-KD method transfers policy knowledge from multiple distinct RL-based single-task models to a single heavy decoder model, facilitating label-free training and effectively improving the model's generalization ability across diverse tasks. In addition, we introduce a flexible inference strategy termed Random Reordering Re-Construction (R3C), which is specifically adapted for diverse VRP tasks and further boosts the performance of the multi-task model. Experimental results on 6 seen and 10 unseen VRP variants with up to 1,000 nodes indicate that our proposed method consistently achieves superior performance on both uniform and real-world benchmarks, demonstrating robust generalization abilities. The code is available at [https://github.com/CIAM-Group/MTLKD](https://github.com/CIAM-Group/MTLKD).

In traditional binary classification tasks, learning algorithms conventionally distinguish positive and negative samples by leveraging fully labeled training data. However, in practical applications, there frequently arises a scenario where only a small number of positive samples and a large volume of unlabeled data exist, with the latter potentially containing a mix of positive and negative instances. This situation is known as positive-unlabeled learning (PUL) and has drawn considerable interest across various domains, such as text categorization. Despite numerous studies addressing PUL issues, few have focused on improving the two-step methodology in the data partitioning process, and even fewer have explored the application of genetic programming (GP) to PUL challenges. This article introduces a GP-based embedded unlabeled data partitioning method (EPGP) tailored for the PUL problem, particularly in the context of few-shot learning scenarios. The approach adopts a multiphase data partitioning strategy, integrating the partitioning process into the evolutionary cycle of the GP population, progressively isolating positive samples from the unlabeled data to yield a PU dataset closer to the real-world distribution. To achieve smoother data partitioning, a dynamically adjusted partitioning threshold strategy is incorporated. Finally, an ensemble method is devised, capitalizing on the high confidence associated with the originally labeled positive samples to generate the final classification outcome via weighted voting. Experimental evaluations of EPGP against other state-of-the-art PUL methods on 22 datasets show significant advantages in terms of balanced accuracy and macro-F1 scores on 17 datasets. Moreover, a case study on text data classification tasks demonstrates that EPGP consistently delivers substantial performance enhancements under varying proportions of labeled positive samples.

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

At present, deep face recognition models working on millions of images are confronted with the challenge that such large-scale datasets are often corrupted with noises and mislabeled identities yet most deep models are primarily designed for clean datasets. In this paper, we propose a robust deep face recognition model by exploiting the advantage of integrating the strength of margin-based learning models with the strength of mining-based approaches to effectively mitigate the impact of noises during training. By monitoring the recognition performances at a batch level to provide optimization-oriented feedback, we introduce a noise-adaptive mining strategy to dynamically adjust the emphasis balance between hard and noise samples, enabling direct training on noisy datasets without the requirement of pre-training. With a novel anti-noise loss function, learning is empowered for direct and robust training on noisy datasets yet its effectiveness over clean datasets is still preserved, sustaining effective mining of both clean and noisy samples whilst weakening its learning intensiveness over noisy samples. Extensive experiments reveal that: (i) our proposed achieves competitive performances in comparison with representative existing SoTA models when trained with clean datasets; (ii) when trained with both real-world and synthesized noisy datasets, our proposed significantly outperforms the existing models, especially when the synthesized datasets are corrupted with both close-set and open-set noises; (iii) while the existing deep models suffer from an average performance drop of around 20% over noise-corrupted large scale datasets, our proposed still delivers accuracy rates of more than 95%. Our source codes are publicly available on GitHub.

In the ever-evolving landscape of media and entertainment, where trends like short-form video content and new media platforms reign supreme, the need for innovative approaches across various industries becomes increasingly apparent. One such industry deeply impacted by these shifts is the film industry, where the creation and dissemination of film trailers stand as pivotal promotional strategies. Making a film trailer by hand is time consuming. However, the emerging artificial intelligence generated content (AIGC) technique has shown significant potential to enhance the efficiency. This article presents a novel model named TVMTrailer, which consists of a text-video generation network (TVGNet) and a video-music generation network (VMGNet). TVGNet employs an encoder–decoder framework, utilizing movie footage and synopses to generate movie trailers. Besides, VMGNet is proposed to generate sound track of our trailer. It combines video and audio features, and uses a transformer model for associative learning to adaptively generate audio clips with features, such as emotion, rhythm and beat. The effectiveness of TVMTrailer is demonstrated through experiment conducted on the proposed dataset and a comprehensive collection of over two thousand video-audio pairs from classic movies.

Brain tumor segmentation models have aided diagnosis in recent years. However, they face MRI complexity and variability challenges, including irregular shapes and unclear boundaries, leading to noise, misclassification, and incomplete segmentation, thereby limiting accuracy. To address these issues, we adhere to an outstanding Convolutional Neural Networks (CNNs) design paradigm and propose a novel network named A4-Unet. In A4-Unet, Deformable Large Kernel Attention (DLKA) is incorporated in the encoder, allowing for improved capture of multi-scale tumors. Swin Spatial Pyramid Pooling (SSPP) with cross-channel attention is employed in a bottleneck further to study long-distance dependencies within images and channel relationships. To enhance accuracy, a Combined Attention Module (CAM) with Discrete Cosine Transform (DCT) orthogonality for channel weighting and convolutional element-wise multiplication is introduced for spatial weighting in the decoder. Attention gates (AG) are added in the skip connection to highlight the foreground while suppressing irrelevant background information. The proposed network is evaluated on three authoritative MRI brain tumor benchmarks and a proprietary dataset, and it achieves a 94.4% Dice score on the BraTS 2020 dataset, thereby establishing multiple new state-of-the-art benchmarks. The code is available here: https://github.com/WendyWAAAAANG/A4-Unet.

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

While margin-based deep face recognition models, such as ArcFace and AdaFace, have achieved remarkable successes over recent years, they may suffer from degraded performances when encountering training sets corrupted with noises. This is often inevitable when massively large scale datasets need to be dealt with, yet it remains difficult to construct clean enough face datasets under these circumstances. In this paper, we propose a robust deep face recognition model, RobustFace, by combining the advantages of margin-based learning models with the strength of mining-based approaches to effectively mitigate the impact of noises during trainings. Specifically, we introduce a noise-adaptive mining strategy to dynamically adjust the emphasis balance between hard and noise samples by monitoring the model's recognition performances at the batch level to provide optimization-oriented feedback, enabling direct training on noisy datasets without the requirement of pre-training. Extensive experiments validate that our proposed RobustFace achieves competitive performances in comparison with the existing SoTA models when trained with clean datasets. When trained with both real-world and synthetic noisy datasets, RobustFace significantly outperforms the existing models, especially when the synthetic noisy datasets are corrupted with both close-set and open-set noises. While the existing baseline models suffer from an average performance drop of around 40%, under these circumstances, our proposed still delivers accuracy rates of more than 90%.

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

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

Most of the existing semantic segmentation approaches with image-level class labels as supervision, highly rely on the initial class activation map (CAM) generated from the standard classification network. In this paper, a novel “Progressive Patch Learning” approach is proposed to improve the local details extraction of the classification, producing the CAM better covering the whole object rather than only the most discriminative regions as in CAMs obtained in conventional classification models. “Patch Learning” destructs the feature maps into patches and independently processes each local patch in parallel before the final aggregation. Such a mechanism enforces the network to find weak information from the scattered discriminative local parts, achieving enhanced local details sensitivity. “Progressive Patch Learning” further extends the feature destruction and patch learning to multi-level granularities in a progressive manner. Cooperating with a multi-stage optimization strategy, such a “Progressive Patch Learning” mechanism implicitly provides the model with the feature extraction ability across different locality-granularities. As an alternative to the implicit multi-granularity progressive fusion approach, we additionally propose an explicit method to simultaneously fuse features from different granularities in a single model, further enhancing the CAM quality on the full object coverage. Our proposed method achieves outstanding performance on the PASCAL VOC 2012 dataset (e.g., with 69.6$\%$mIoU on thetestset), which surpasses most existing weakly supervised semantic segmentation methods.

Recent years have witnessed increasingly more exercises and uses of deep unfolding network (DUN) in image compressed sensing (CS) due to its high performance and interpretability. However, the existing DUN does not make full use of more flexible regularization methods. Besides, the intermediate information generated during the iterations of the DUN, which is crucial for the quality improvement of image reconstruction, has been largely overlooked in the existing methods. To alleviate this problem, we propose a novel DUN for image CS with regularization by denoising which casts half quadratic splitting (HQS) algorithm into the neural network. Further, we design an information collection strategy to leverage the useful information generated during the iterations. The information is provided to the image denoiser of the proposed network, which could enhance the image processing ability of the denoiser. The extensive experiments demonstrate that the proposed method is more efficient and achieves state-of-the-art reconstruction quality.

Abstract Pixel‐based generative image inpainting has been widely researched over recent years and certain level of success via deep learning of feature representations and hallucinations of missing pixel values from surrounding backgrounds have also been reported in the literature. However, existing approaches rely on context‐based attentions and progressive inferences to capture the pixel correlations yet such pixel‐based approaches often fail to adapt to the constantly varying ranges and distances among surrounding background pixels. On the other hand, the modelling cost is also increasingly expensive whenever correlations of those pixels at longer distance away are to be exploited. To resolve the problem, we implement the principle of learning and hallucinating frequency components rather than pixel values. Therefore, we can avoid the dilemma that, on one hand the wish is to exploit all correlated pixels inside the image no matter how far away they are spatially located, but on the other, the price of increasing the modelling cost incurred by those pixels far away from the missing regions has to be paid. Extensive experiments carried out verify the effectiveness of the proposed method, which outperforms the representative existing state of the arts in terms of all assessment metrics.

With the popularity and development of Internet of Things (IoT) technology, human activity recognition using IoT devices such as wearable sensors can be implemented for various applications. Due to the complexity of activity recognition, multiple homogeneous or heterogeneous sensors are used to obtain excessive information in most wearable activity recognition systems. However, the increased number of sensors and the way of multichannel signal data bring huge challenges to human activity recognition tasks. How to select suitable sensor channels to balance the computational complexity and recognition accuracy has become a major issue. In this article, we extend the sparse group Lasso mechanism to human activity recognition tasks and propose a hybrid attention-based multi-sensor pruning and feature selection deep neural network, called HAP-DNN. This architecture is able to further perform feature selection on the basis of sensor pruning. HAP-DNN consists of three detachable modules: 1) a feature compression & reconstruction module for sensor feature information fusion and restoration; 2) a feature weight calculation module for calculating sensor channel weights and feature weights; and 3) a learning module for classification, which can be regarded as a filter feature selection method. Four public activity recognition data sets are used to verify our proposed architecture, and the experimental results show that HAP-DNN achieves the best classification performance with the least number of retained feature channels.

DNA microarray data contain valuable biological information, which makes it of great importance in disease analysis and cancer diagnosis. However, the classification of microarray data is still a challenging task because of the high dimension and small sample size, especially for multiclass data accompanied by class imbalance. In this paper, we propose a cooperative coevolutionary multiobjective genetic programming (CC-MOGP) for microarray data classification. It converts a multiclass problem into a set of tractable binary problems and coevolves the corresponding population. And a cooperative coevolutionary Pareto archived evolution strategy (CC-PAES) is employed to approximate the Pareto front. During this procedure, we propose a synergy test method to assist in guiding the coevolution between populations. Experimental results on 8 multiclass microarray data show that CC-MOGP can obtain competitive prediction accuracy compared with several state-of-art evolutionary computation and traditional methods.

Recent years have witnessed increasingly more uses of drone networks for providing wireless coverage to ground users. Each drone is constrained in its energy storage and wireless coverage, and it consumes most energy when flying to the top of the target area, leaving limited leftover energy for hovering at its deployed position and providing wireless coverage. The literature largely overlooks this sustainability issue of drones’ energy consumption during deployment, and we aim to minimize the maximum energy consumption among all drones after their deployment. This min-max drone deployment problem solving requires drones to cooperate with each other in deployment distance and altitude to evenly use up their energy, which is shown to be NP-hard. Thus, we propose a hybrid genetic algorithm to solve the min-max drone deployment problem. In our proposal, the integer code scheme is used to encode the sequence of drones’ deployment. The energy consumption determined by the horizontal and vertical flying distance is adopted as the fitness value. With the determined order of the drones sequence by coding process, we introduce a feasibility checking operator with binary search to archive the optimum. Experimental study shows that the algorithm has capability and superiority to find good solutions under different drones’ characteristics distribution and outperforms solutions from existing competitors by extensive simulations.

In this paper, we propose a deep learning based framework for point cloud geometry lossy compression via hybrid representation of point cloud. First, the input raw 3D point cloud data is adaptively decomposed into non-overlapping local patches through adaptive Octree decomposition and clustering. Second, a framework of point cloud auto-encoder network with quantization layer is proposed for learning compact latent feature representation from each patch. Specifically, the proposed point cloud auto-encoder networks with different input size are trained for achieving optimal rate-distortion (RD) performance. Final, bitstream specifications of proposed compression systems with additional signaled meta-data and header information are designed to support parallel decoding and successive reconstruction. Experimental results shows that our proposed method can achieve 40.20% bitrate saving in average than the existing standard Geometry based Point Cloud Compression (G-PCC) codec.

For high-dimensional data classification, feature selection has played a significant role in removing the redundant or irrelevant features and improving the performances of classifiers. Particle Swarm Optimization (PSO), an evolutionary computational tool, has been widely and successfully applied in the field of feature selection. A recent pioneer work, Potential PSO (PPSO) which utilizes feature discretization process based on cut-points, provides better overall performance in classification and lower amount of selected features compared with some existing approaches. In this paper, we proposed an adaptive PPSO (APPSO) to reduce the number of features further and increase the classification accuracy. In APPSO, the pre-filtering method, ReliefF, is incorporated into the discretization process to help screen the potential cut-points effectively, and a new updating strategy is proposed to strengthen the searching scope of particles and avoid being trapped into local optima. Also, APPSO follows an adaptive way to alter the random level of the selection of cutpoints. The random level depends on the mean instance number per class of each dataset. Experiments on 10 datasets are carried out, and APPSO is proven to select less than 2% of the number of features while maintaining a very competitive accuracy compared with some state-of-the-art methods.

Barrier coverage with wireless sensors aims at detecting intruders who attempt to cross a specific area, where wireless sensors are distributed remotely at random. This paper considers limited-power sensors with adjustable ranges deployed along a linear domain to form a barrier to detect intruding incidents. We introduce three objectives to minimize: 1) total power consumption while satisfying full coverage; 2) the number of active sensors to improve the reliability; and 3) the active sensor nodes' maximum sensing range to maintain fairness. We refer to the problem as the tradeoff barrier coverage (TBC) problem. With the aim of obtaining a better tradeoff among the three objectives, we present a multiobjective optimization framework based on multiobjective evolutionary algorithm (MOEA)/D, which is called problem specific MOEA/D (PS-MOEA/D). Specifically, we define a 2-tuple encoding scheme and introduce a cover-shrink algorithm to produce feasible and relatively optimal solutions. Subsequently, we incorporate problem-specific knowledge into local search, which allows search procedures for neighboring subproblems collaborate each other. By considering the problem characteristics, we analyze the complexity and incorporate a strategy of computational resource allocation into our algorithm. We validate our approach by comparing with four competitors through several most-used metrics. The experimental results demonstrate that PS-MOEA/D is effective and outperforms the four competitors in all the cases, which indicates that our approach is promising in dealing with TBC.

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

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

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

Designing a reliable and generic perceptual quality metric is a challenging issue in three-dimensional (3D) visual signal processing. Due to the limited knowledge on 3D perceptual, it is difficult to fuse the visual information of left and right views in an effective way. In this paper, we propose a complex singular value decomposition (CSVD) based stereoscopic image quality assessment (SIQA) metric. First, the corresponding blocks of the left/right view are grouped into complex representation (CR) block through the scale-invariant feature transform (SIFT) view matching process. Then we compute the CSVD coefficients of each CR block. Final, a CSVD based quality pooling stage is employed to predict the final visual quality of the distorted 3D image. Experimental results demonstrate that the proposed metric has good consistency with 3D perception of human.

A structural similarity (SSIM)-based game theory (GT) approach is proposed for rate-distortion (R-D) optimized CTU-level bit allocation in high efficiency video coding (HEVC). First, a SSIM-based bargaining game is formulated and the Nash bargaining solution (NBS) is proposed, in which a SSIM-based initial minimum utility is defined. Second, we propose a two-stage remaining bit refinement-based bit allocation scheme. The optimization scheme of the SSIM-based bargaining game sufficiently considers the different R-D characteristics of coding tree units (CTUs), in which the feasible utility set is proved to be convex based on the proposed SSIM-based utility and R-SSIM model. Compared with the other state-of-the-art CTU-level bit allocation methods, the R-D performance improvements on Bjøntegaard delta bit-rate (BD-BR), Bjøntegaard delta peak-signal-to-noise-ratio (BD-PSNR), and BD-SSIM metrics of the proposed method can averagely achieve significant gains, respectively. The achieved R-D performance gains have been very close to the coding performance limits from the FixedQP method. Moreover, the proposed SSIM-GT method also maintains good performances on quality smoothness, bit rate accuracy, and encoding complexity.

We consider the problem of organizing a scattered group of n robots in two-dimensional space. The communication graph of the swarm is connected, but there is no central authority for organizing it. We want to arrange them into a sorted and equally-spaced array between the robots with lowest and highest label, while maintaining a connected communication network. In this paper, we describe a distributed method to accomplish these goals, without using central control, while also keeping time, travel distance and communication cost at a minimum. We proceed in a number of stages (leader election, initial path construction, subtree contraction, geometric straightening, and distributed sorting), none of which requires a central authority, but still accomplishes best possible parallelization. The overall arraying is performed in O(n) time, O(n2) individual messages, and O(n) travel distance per robot. Implementation of the sorting and navigation use communication messages of fixed size, and are a practical solution for large populations of low-cost robots.

View level bit allocation is an fundamental optimization problem in multiview video plus depth (MVD) based 3D video coding (3DVC). In this paper, we propose a smooth view quality oriented view level bit allocation framework for MVD based 3DVC. The Cauchy-density based rate-distortion model of the texture video and depth map are employed to represent the rate distortion properties. The relationship between the distortion of synthesized view and quantization step size of texture videos and depth maps is approximately fitted as linear model. Final, the bit allocation problem is solved by convex optimization algorithms. Experimental results demonstrated that our proposed algorithm can achieve good performance with acceptable computational complexity comparing to the full search scheme.

Multi-robot manipulation allows for scalable environmental interaction, which is critical for multi-robot systems to have an impact on our world. A successful manipulation model requires cost-effective robots, robust hardware, and proper system feedback and control. This paper details key sensing and manipulator capabilities of the r-one robot. The r-one robot is an advanced, open source, low-cost platform for multi-robot manipulation and sensing that meets all of these requirements. The parts cost is around $250 per robot. The r-one has a rich sensor suite, including a flexible IR communication/localization/obstacle detection system, high-precision quadrature encoders, gyroscope, accelerometer, integrated bump sensor, and light sensors. Two years of working with these robots inspired the development of an external manipulator that gives the robots the ability to interact with their environment. This paper presents an overview of the r-one, the r-one manipulator, and basic manipulation experiments to illustrate the efficacy our design. The advanced design, low cost, and small size can support university research with large populations of robots and multi-robot curriculum in computer science, electrical engineering, and mechanical engineering. We conclude with remarks on the future implementation of the manipulators and expected work to follow.