Understanding how functional dynamics emerge from the brain’s underlying structural architecture remains a fundamental challenge in neuroscience. Conventional graph diffusion (GD) models are limited by sparse anatomical connectivity, leading to a failure to capture indirect connectivity and negatively correlated relationships. To overcome these challenges, we introduce hypergraphs and deep neural networks to enhance the representation of brain connectivity. Specifically, graphs and hypergraphs are integrated to construct a connected-graph, providing a comprehensive representation of inter-regional brain connectivity. The Fourier-induced deep neural network is employed to infer latent inter-regional relationships from structural connectivity by leveraging spectral features, effectively capturing both low- and high-frequency components. These deduced relationships are incorporated into the connected-graph, giving rise to a connected-graph diffusion (CD) model, which is further refined via eigen-decomposition to form an eigen-based connected-graph diffusion (ECD) model. Evaluated on 1012 subjects from the Human Connectome Project (HCP) S1200 release, the ECD model achieves a mean Pearson correlation coefficients of 0.7230 in functional connectivity (FC) prediction, outperforming the GD model (0.5513) and CD model (0.6518). The stability analysis demonstrates that the prediction of the ECD model is reliable. This work demonstrates that integrating biological mechanisms with machine learning methods can accurately model complex brain networks, with implications for neural signal processing, brain-inspired computing, and neuropsychiatric diagnosis.

Optical remote sensing images have extensive application value, but cloud contamination greatly limits their potential use in the field of geographic information. Cloud removal aims to restore clear, unobstructed images from cloud-covered ones for subsequent in-depth analysis. Due to severe cloud cover problems such as thick clouds in some areas of remote sensing images, cloud removal tasks have become challenging. Recently, many methods have attempted to incrementally fill in obscured regions by fusing cloud-free information from multitemporal data. However, most of these methods fail to effectively utilize the interaction among different temporal data, and some information of data is easily lost in the process of deep transmission, this causes problems such as inadequate cloud removal and blurred recovery of ground under the clouds. Therefore, we propose a multistream complementary generative adversarial network (MSC-GAN) for cloud removal using multitemporal data. First, it employs a multistream complementary (MSC) architecture in the down-sampling feature encoding stage to effectively promote the interaction of feature information across multitemporal data, alleviating information loss as network depth increases. Second, to reduce the feature blur, we design a group feature reweighting (GFR) module as a complementary connection of long-distance information, in which the grouping learning and multidimensional parallel architecture can cost-effectively enhance semantic fusion between low-level and high-level features. Moreover, a channel enhancement method is introduced to assist in processing the underlying transition information, minimizing the interference of invalid information. Experimental results on multiple benchmark datasets under a series of image quality assessment metrics demonstrate the effectiveness of the proposed method.

Abstract Few-shot learning has achieved satisfactory progress over the years, but these methods implicitly hypothesize that the data in the base (source) classes and novel (target) classes are sampled from the same data distribution (domain), which is often invalid in reality. The purpose of cross-domain few-shot learning (CD-FSL) is to successfully identify novel target classes with a small quantity of labeled instances on the target domain under the circumstance of domain shift between the source domain and the target domain. However, in CD-FSL, the knowledge learned by the network on the source domain often suffers from the situation of inadaptation when it is transferred to the target domain, since the instances on the source and target domains do not obey the same data distribution. To surmount this problem, we propose a Target Oriented Dynamic Adaption (TODA) model, which uses a tiny amount of target data to orient the network to dynamically adjust and adapt during training. Specifically, this work proposes a domain-specific adapter to ameliorate the network inadaptability issues in transfer to the target domain. The domain-specific adapter can make the extracted features more specific to the tasks in the target domain and reduce the impact of tasks in the source domain by combining them with the mainstream backbone network. In addition, we propose an adaptive optimization method in the network optimization process, which assigns different weights according to the importance of different optimization tasks. Extensive experiments on several benchmark datasets demonstrate the effectiveness of our TODA method.

Collecting a substantial number of labeled samples is infeasible in many real-world scenarios, thereby bringing out challenges for supervised classification. The research on Few-Shot Classification (FSC) aims to address this issue. Current FSC methods mainly leverage ideas such as meta-learning, self-supervised learning, and data augmentation. Among them, data augmentation appears to be an extremely efficient approach to alleviate the aforementioned data-deficiency problem. Here, we propose a novel data augmentation based FSC method termed Fourier-Augmentation based Data-Shunting (FADS). FADS mainly contains two operations, namely Fourier-based data augmentation (FDA) and data shunting. (i) Fourier transform has a desirable property for classification tasks: the image’s phase and amplitude components in the frequency domain correspond to its high-level structure (i.e., semantic) and low-level style (i.e., statistic) information, which do not interfere with each other. Inspired by this observation, we design the FDA operation, which changes the amplitude spectrum of the to-be-augmented images to obtain new images of the same category. (ii) Then we design the data shunting operation to cooperate with the FDA to accomplish FSC. Specifically, it splits the augmented data into different groups to get independent, weak decisions and then fuses them to obtain a unified, strong decision. We conduct experiments on four benchmark datasets. Results show that utilizing our method brings a performance gain of 0.3%-2% in terms of classification accuracy, compared with the classical methods.

Hyperspectral image (HSI) classification technology has continuously made breakthroughs. Especially with the emergence of convolutional neural networks (CNN), its performance has been rapidly enhanced. However, CNN uses kernels with fixed sizes, which cannot flexibly handle data with irregular patterns, affecting the HSI classification results. Therefore, the paper introduces a graph convolutional network (GCN) to assist CNN in further optimizing the HSI representation and proposes a pixel-superpixel level multiscale graph and spectral-spatial representations fusion network (Ps-MGSRF) that mainly includes a pixel-level feature representation module (PFRM) formed with multiple multiscale feature refiltering blocks and a superpixel-level feature representation module (SFRM) composed of different orders’ residual GCN (ResGCN) blocks. Finally, the loss of the PFRM branch (loss1), the loss of the SFRM branch (loss2), and the loss of the merging of the two branches (loss3) are calculated separately, and the Ps-MGSRF network is updated by adaptive weighting three losses. The test results indicate that the proposed Ps-MGSRF model could achieve better experimental performance than the advanced comparison methods.

Decoupled Few-shot learning (FSL) is an effective methodology that deals with the problem of data-scarce. Its standard paradigm includes two phases: (1) Pre-train. Generating a CNN-based feature extraction model (FEM) via base data. (2) Meta-test. Employing the frozen FEM to obtain the novel data features, then classifying them. Obviously, one crucial factor, the category gap, prevents the development of FSL, i.e., it is challenging for the pre-trained FEM to adapt to the novel class flawlessly. Inspired by a common-sense theory: the FEMs based on different strategies focus on different priorities, we attempt to address this problem from the multi-view feature collaboration (MVFC) perspective. Specifically, we first denoise the multi-view features by subspace learning method, then design three attention blocks (loss-attention block, self-attention block and graph-attention block) to balance the representation between different views. The proposed method is evaluated on four benchmark datasets and achieves significant improvements of 0.9%-5.6% compared with SOTAs.

Recently, many existing fully supervised methods for point cloud classification have strongly promoted the development of point cloud learning. However, these methods require a lot of labeled data as support, which is challenging to obtain. To alleviate this problem, we propose a novel few-shot point cloud classification method to classify new categories given a few labeled samples. Specifically, we apply the feature supplement module to enrich the geometric information of points and then aggregate multi-scale features through the channel-wise attention module while reducing the computational complexity. Finally, we introduce a classifier to classify the point cloud features under the few-shot learning setup to predict its label. We carry out experimental verification on the benchmark dataset and achieve state-of-the-art performance.

Underwater image restoration is a fundamental problem in image processing and computer vision. It has broad application prospects for underwater operations, especially underwater robot operations. The challenging work is how to keep the color authenticity of the captured underwater image. In this paper, we propose a novel network architecture based on CycleGAN. Specifically, in the generator part, we adopt the U-Net structure because the long skip connection of U-Net will obtain more detailed information. Besides, we append the pixel-level attention block to provide greater flexibility for detail structure modeling. It assigns different weights to each channel to pay more attention to the critical feature. We also verify its generalization performance on several benchmark datasets. The extensive experiments with comparisons to state-of-the-art approaches demonstrate the superiority of the proposed model.

Facial Expression Recognition (FER) in the wild is a significant yet challenging classification task due to the inter-class similarities and intra-class variations. Recently, a large number of methods can extract expression features effectively. However, the intra-class variations mainly caused by various uncertainties (such as identity, pose, and occlusion) are difficult to capture in advance, and the cost of labeling these uncertainties is high. To tackle this challenge, we propose a novel Mirrored Self-supervised Learning FER (MSL-FER) method. The ground truth of self-supervised learning comes from the data itself rather than from human annotations, and horizontal inversion preserves emotional information without altering the facial structure. Specifically, MSL-FER introduces a binary classification task to recognize the 2D mirror operation in a self-supervised learning method. And we also combine our MSL-FER with an attention network to discriminate features along its dimensions selectively. Experiments on two public wild FER datasets show that our MSL-FER approach outperforms the baseline and other state-of-the-art methods with 87.92% on RAF-DB and 70.68% on FER2013.

Abstract Skeleton‐based action recognition is an inspired yet challenging task in computer vision. Recently, the latest graph convolutional network (GCN), which generalises well‐established convolutional neural networks to non‐Euclidean structures, is proven to be highly successful for action recognition from body skeleton data. However, the GCN architecture has not been fully studied. In this work, a Fisher vector (FV) encoding based GCN architecture (FV‐GCN) is proposed, which exceeds the limitations of existing GCN‐based methods by combining the GCN model with FV encoding. A channel‐wise spatial–temporal aggregation function to preserve spatial–temporal information in the whole action clip and integrate it into the FV‐GCN architecture is also presented. Since FV is different from the GCN structure, this hybrid architecture that incorporates the advantages of both algorithms can discover complementary information of feature representation effectively. On two challenging human action datasets, kinetics, and NTU‐RGBD, improved performance is demonstrated over the baseline method, and the FV‐GCN is better or comparable to some state‐of‐the‐art methods.

Convolutional neural networks (CNNs) are widely utilized in hyperspectral image (HSI) classification due to their powerful capability to automatically learn features. However, ordinary CNN mainly captures the spatial characteristics of HSI and ignores the spectral information. To alleviate the issue, this work proposes a CNN-enhanced multi-level Haar wavelet features fusion network (CNN-MHWF2N), which combines the spatial features obtained through 2-D-CNN with the Haar wavelet decomposition features to obtain sufficient spectral–spatial features. Specifically, factor analysis is first used to reduce the HSI dimension. Then, four-level decomposition features are obtained through the Haar wavelet decomposition algorithm, which of them are, respectively, concatenated with four-layer convolution features for combining spatial with spectral information. In this way, spectral–spatial features achieve better information interaction. Besides, a double filtrating feature fusion module is designed, which is operated following each level spectral–spatial features to obtain finer characteristics. Finally, those recognizable features are merged via a fusion operator. The whole designed model is conducive to enhancing the final HSI classification performance. In addition, experiments also reveal that the designed model is superior on three benchmark databases compared with the state-of-the-art approaches.

In recent years, deep learning-based remote-sensing image super-resolution (SR) methods have made significant progress, and these methods require a large number of synthetic data for training. To obtain sufficient training data, researchers often generate synthetic data via fixed bicubic downsampling methods. However, the synthesized data cannot reflect the complex degradation process of real remote-sensing images. Thus, performance will dramatically reduce when these methods work in real low-resolution (LR) remote-sensing images. This letter proposes a U-shaped attention connection network (US-ACN) for remote-sensing image SR to solve this issue. Our US-ACN does not rely on any synthetic external dataset for training and merely requires one LR image to complete the training. The US-ACN utilizes remote-sensing images’ strong internal feature repetitiveness and fully learns this internal repetitive feature through a well-designed US-ACN to achieve the remote-sensing image SR. In addition, we design a 3-D attention module to generate effective 3-D weights by modeling channel and spatial attention weights, which is more helpful for the learning of internal features. Through the U-shaped connection among attention modules, context information propagation and attention weights learning are fully utilized. Many experiments show that our US-ACN adequately adapts to the remote-sensing image SR in various situations and performs advanced performance.

In recent years, convolutional neural networks (CNNs) have been widely used in hyperspectral images (HSIs) classification. However, 2-D CNN, 3-D CNN, and even the newly emerged hybrid CNN (HCNN) all require multiple or deep CNN layers to obtain excellent classification performance, which inevitably results in the high complexity and the need for a large number of training samples. Moreover, as a local operator, convolution is challenging to fully use global information. To solve the above two issues, we design a HCNN based on global reasoning (GloRe-HCNN) for HSI classification. On the one hand, the GloRe-HCNN uses only one layer of 3-D CNN and one layer of 2-D CNN to jointly extract the spatial–spectral features of HSI. On the other hand, we contrive a spatial–spectral global reasoning unit (SS-GloRe-Unit) to take the place of stacked multilayer 3-D CNN for extracting global features fully. We select small training samples in three standard datasets and compare them with state-of-the-art CNN methods. Numerous experiments show that our GloRe-HCNN performs advanced performance.

Recently, remote-sensing scene classification has become an essential primary research topic. Nowadays, scholars have proposed various few-shot remote-sensing scene classification methods to achieve superior performance with few labeled data. Most of the prior work utilized a meta-learning strategy, which suffered from too little data affecting performance. In this letter, we apply the pre-trained feature extractor for image embedding. Meanwhile, because of the negative transfer problem caused by the inadaptability of the pre-trained feature extractor to remote-sensing data, we propose to exploit two pre-trained models to classify the remote-sensing scene, respectively. Then we fuse the decision to obtain the final classification category. We design a decision attention module to automatically update combination weights for each decision. It comprehensively considers the contribution of various decisions and further improves the discrimination of features. We conduct comprehensive experiments to validate the method and achieve state-of-the-art performance on two benchmark remote-sensing scene datasets, namely NWPU-RESISC45 and UC Merced.

In recent years, researchers pay growing attention to the few-shot learning (FSL) task to address the data-scarce problem. A standard FSL framework is composed of two components: i) Pre-train. Employ the base data to generate a CNN-based feature extraction model (FEM). ii) Meta-test. Apply the trained FEM to the novel data (category is different from base data) to acquire the feature embeddings and recognize them. Although researchers have made remarkable breakthroughs in FSL, there still exists a fundamental problem. Since the trained FEM with base data usually cannot adapt to the novel class flawlessly, the novel data’s feature may lead to the distribution shift problem. To address this challenge, we hypothesize that even if most of the decisions based on different FEMs are viewed asweak decisions, which are not available for all classes, they still perform decent in some specific categories. Inspired by this assumption, we propose a novel method Multi-Decision Fusing Model (MDFM), which comprehensively considers the decisions based on multiple FEMs to enhance the efficacy and robustness of the model. MDFM is a simple, flexible, non-parametric method that can directly apply to the existing FEMs. Besides, we extend the proposed MDFM to two FSL settings (e.g., supervised and semi-supervised settings). We evaluate the proposed method on five benchmark datasets and achieve significant improvements of 3.4%-7.3% compared with state-of-the-arts.

How spontaneous brain neural activities emerge from the underlying anatomical architecture, characterized by structural connectivity (SC), has puzzled researchers for a long time. Over the past decades, much effort has been directed toward the graph modeling of SC, in which the brain SC is generally considered as relatively invariant. However, the graph representation of SC is unable to directly describe the connections between anatomically unconnected brain regions and fail to model the negative functional correlations. Here, we extend the static graph model to a spatiotemporal varying hypergraph Laplacian diffusion (STV-HGLD) model to describe the propagation of the spontaneous neural activity in human brain by incorporating the Laplacian of the hypergraph representation of the structural connectome ( h SC) into the regular wave equation. Theoretical solution shows that the dynamic functional couplings between brain regions fluctuate in the form of an exponential wave regulated by the spatiotemporal varying Laplacian of h SC. Empirical study suggests that the cortical wave might give rise to resonance with SC during the self-organizing interplay between excitation and inhibition among brain regions, which orchestrates the cortical waves propagating with harmonics emanating from the h SC while being bound by the natural frequencies of SC. Besides, the average statistical dependencies between brain regions, normally defined as the functional connectivity (FC), arises just at the moment before the cortical wave reaches the steady state after the wave spreads across all the brain regions. Comprehensive tests on four extensively studied empirical brain connectome datasets with different resolutions confirm our theory and findings.

In this paper, in order to better describe the object, an adaptive multi-feature fusion method is proposed, which makes full use of the advantages of various features. Firstly, hierarchical convolution features and two hand-crafted features are fused linearly, and the weights of different features are adjusted adaptively to obtain the optimal object representation in the tracking process. Secondly, a translation filter and a scale filter are adopted to estimate the object’s exact position and scale, respectively. Finally, in the model update stage, an efficient adaptive model update strategy is used to improve the performance, which can significantly alleviate the model noises. Extensive experimental results on well-known benchmark datasets show that the proposed algorithm performs favorably against the state-of-the-art tracking methods.

The video frame interpolation algorithm can improve temporal resolution by inserting non-existent frames in the video sequence. With the help of skip connections, many kernel-based methods train deep neural networks to accurately establish the complicated spatiotemporal relationship among pixels in adjacent frames. Still, these connections are only performed in the feature dimension. To this end, we introduce the Over-Parameterized Sharing Networks (OPS-Net) to implement weight sharing under different layers, capable of integrating deep and shallow features more directly. Specifically, we over-parameterize each convolutional layer to capture movement information efficiently, where the additional trainable weights from distinct ones will be shared. After the training, the additional weights will be fused into the conventional convolutional layer and do not increase the test phase’s computation. Experimental results show that the proposed method can generate favorable frames compared with several state-of-the-art approaches.

The label-embedded dictionary learning (DL) algorithms generate influential dictionaries by introducing discriminative information. However, there exists a limitation: All the label-embedded DL methods rely on the labels due that this way merely achieves ideal performances in supervised learning. While in semi-supervised and unsupervised learning, it is no longer sufficient to be effective. Inspired by the concept of self-supervised learning (e.g., setting the pretext task to generate a universal model for the downstream task), we propose a Self-Supervised Dictionary Learning (SSDL) framework to address this challenge. Specifically, we first design a p-Laplacian Attention Hypergraph Learning (pAHL) block as the pretext task to generate pseudo soft labels for DL. Then, we adopt the pseudo labels to train a dictionary from a primary label-embedded DL method. We evaluate our SSDL on two human activity recognition datasets. The comparison results with other state-of-the-art methods have demonstrated the efficiency of SSDL.

Few-shot learning (FSL) aims to address the data-scarce problem. A standard FSL framework is composed of two components: (1) Pre-train. Employ the base data to generate a CNN-based feature extraction model (FEM). (2) Meta-test. Apply the trained FEM to acquire the novel data's features and recognize them. FSL relies heavily on the design of the FEM. However, various FEMs have distinct emphases. For example, several may focus more attention on the contour information, whereas others may lay particular emphasis on the texture information. The single-head feature is only a one-sided representation of the sample. Besides the negative influence of cross-domain (e.g., the trained FEM can not adapt to the novel class flawlessly), the distribution of novel data may have a certain degree of deviation compared with the ground truth distribution, which is dubbed as distribution-shift-problem (DSP). To address the DSP, we propose Multi-Head Feature Collaboration (MHFC) algorithm, which attempts to project the multi-head features (e.g., multiple features extracted from a variety of FEMs) to a unified space and fuse them to capture more discriminative information. Typically, first, we introduce a subspace learning method to transform the multi-head features to aligned low-dimensional representations. It corrects the DSP via learning the feature with more powerful discrimination and overcomes the problem of inconsistent measurement scales from different head features. Then, we design an attention block to update combination weights for each head feature automatically. It comprehensively considers the contribution of various perspectives and further improves the discrimination of features. We evaluate the proposed method on five benchmark datasets (including cross-domain experiments) and achieve significant improvements of 2.1%-7.8% compared with state-of-the-arts.

Discriminative correlation filters based algorithms have attracted extensive attention due to their strong tracking capability. However, object tracking still faces many challenges due to object appearance variations, background clutter, occlusion, plane rotation, etc. In this paper, to better express the object, multiple features are integrated to make full use of the advantage of different features. Furthermore, the adaptive eigen-decomposition and reconstruction ("eigenmodes") method is applied to carry out the integrated-feature decomposition, and optimal expression of the object is established through simple eigen-relationships. It has proved experimentally that the predicted value after eigenmodes is closer to the groundtruth than before. Furthermore, to solve the tracking failure caused by interfering objects or background clutters and improve the tracking accuracy, the average peak-correlation energy (APCE) method is utilized as an optimized update strategy in this paper. A large number of experimental results on the known reference datasets indicate that our algorithm has good performance compared to the existing tracking methods.

Abstract The application of graph convolutional networks (GCN) in hyperspectral image (HSI) classification has become a promising method, thanks to its flexible convolution operation in any irregular image region. For the classification of HSI, GCN can extract more superpixel‐level features with a topological structure, in comparison to the traditional convolutional neural networks (CNNs) using fixed square kernels distilling pixel‐level features. To fully leverage the different levels of features, this study proposes a novel deep network referred to as a CNN‐combined graph residual network (GRN), which integrates the multilevel graph residual module and spectral‐spatial features continuous learning module. During the extraction of topology information using the former module, HSI pixels are divided into superpixels and served as input nodes of the module to reduce the computational complexity and obtain the multilevel spatial relevance between adjacent superpixels. Besides, for the latter module, the spectral‐spatial features are learnt continuously, which could obtain the finer pixel‐level features. Finally, the captured spectral‐spatial features of different levels are concatenated. This strategy could not only adequately utilize the correlation and difference of adjacent spatial but also obtain the finer and more valuable spectral‐spatial information, which makes a significant boost in the HSI classification. Additionally, the experiment results demonstrate the superiority and availability of the GRN on three benchmark datasets of HSI, compared with the state‐of‐the‐art methods for the classification of HSI.

In the last few years, the deep learning methods, especially the residual neural network, have achieved impressive performance in remote sensing image recognition tasks. However, there are still specific problems that need to be addressed. It is well known that the first several layers of the network provide much discriminative information, and the ResNet reduces the size of the feature map so quickly that it failed to fully learn the information beneficial to classification in the early stage. Second, insufficient labeling data in remote sensing database may easily lead to overfitting and affect the final classification accuracy. Third, the optimal results cannot be achieved by relying solely on transfer learning. To overcome the problems mentioned earlier, we propose an enhanced residual neural network (ERNet) to improve the classification performance on remote sensing images. We moderately broadened the first several layers of the network, changed the size of the convolution filters, and made it learn more information of image features. Second, we add dropout layer to each residual unit of the proposed network to improve the accuracy and generalization power of ERNet. Finally, an ensemble of learning methods based on ERNet was introduced to improve the classification performance by fusing features of other baseline methods. Extensive experimental results on several benchmark data sets of remote sensing images demonstrate the superior performance of our proposed algorithm.

Recently, dictionary learning based sparse representation algorithm has been widely adopted and achieved satisfying performance in image classification. However, sparse representation based classification (SRC) as well as collaborative representation based classification (CRC) always result in high residual error due to their basic assumption that considers training samples as dictionary directly for each category. And conventional class specific dictionary learning algorithm usually operates in the Euclidean space and fails to capture nonlinear information. To deal with these problems, we propose a classification algorithm which is called class specific dictionary learning based kernel collaborative representation (CSDL-KCRC) to enhance the classification accuracy. Extensive experimental results operated on three fine-grained image datasets, such as Oxford 102-Flowers dataset, Caltech-UCSD Birds-200-2011 (CUB-200-2011) dataset and Stanford Dogs dataset, demonstrate the effectiveness of CSDL-KCRC in image classification.

The current sparse representation framework is to decouple it as two subproblems, i.e., alternate sparse coding and dictionary learning using different optimizers, treating elements in bases and codes separately. In this paper, we treat elements both in bases and codes ho-mogenously. The original optimization is directly decoupled as several blockwise alternate subproblems rather than above two. Hence, sparse coding and bases learning optimizations are coupled together. And the variables involved in the optimization problems are partitioned into several suitable blocks with convexity preserved, making it possible to perform an exact block coordinate descent. For each separable subproblem, based on the convexity and monotonic property of the parabolic function, a closed-form solution is obtained. Thus the algorithm is simple, efficient and effective. Experimental results show that our algorithm significantly accelerates the learning process.

Collaborative representation based classification (CRC) has been successfully used for visual recognition and showed impressive performance recently. However, it directly uses the training samples from each class as the subspaces to calculate the minimum residual error for a given testing sample. This leads to high residual error and instability, which is critical especially for a small number of training samples in each class. In this paper, we propose a class specific subspace learning algorithm for collaborative representation. By introducing the dual form of subspace learning, it presents an explicit relationship between the basis vectors and the original image features, and thus enhances the interpretability. Lagrange multipliers are then applied to optimize the corresponding objective function, i.e., learning the weights used in constructing the subspaces. Extensive experimental results demonstrate that the proposed algorithm has achieved superior performance in several visual recognition tasks.

Inspired by the mechanism of human brain three-stage memory model, this paper develops a spinning tri-layer-circle memory model(STLC-MM) and applies it for template updating during object tracking. Three memory spaces are defined to store and process the object templates used in the tracking framework. Each memory space, which has a fixed input window and a fixed output window, is denoted by a circle and can spin with different speed. With three circle memory spaces spinning, templates in the three memory spaces are updated by imitating the cognitive process of memorization, recall, and forgetting. Then all the templates in the output windows of the three memory spaces are compared with the estimated template respectively, and the most similar template is selected as the final output of the STLC-MM. Finally, STLC-MM is incorporated into a particle filter (PF) framework in order to verify the effect of our proposed model. Experimental results show that the proposed method is more robust to sudden appearance changes and serious occlusions.

Sparse representation based classification (SRC) has attracted much attention in face analysis such as face recognition (FR) and face expression recognition (FER). Currently, most of SRC based methods treated face as a whole component which results in under-utilization of the complementary in different facial parts. In this paper, we present an approach which can effectively explore the complementary of different facial parts to boost the performance of face analysis. In particular, we employ multi-view sparse coding techniques to learn the factorized representation of different facial components. Furthermore, we incorporate label information into the objective function to enforce the discriminability. To evaluate the performance, we conduct face analysis experiments including FR and FER on JAFFE database. Experimental results demonstrate that the proposed method can significantly boost the performance of face analysis.

Sparse representation technique has been widely used in various areas of computer vision over the last decades. Unfortunately, in the current formulations, there are no explicit relationship between the learned dictionary and the original data. By tracing back and connecting sparse representation with the K-means algorithm, a novel variation scheme termed as self-explanatory convex sparse representation (SCSR) has been proposed in this paper. To be specific, the basis vectors of the dictionary are refined as convex combination of the data points. The atoms now would capture a notion of centroids similar to K-means, leading to enhanced interpretability. Sparse representation and K-means are thus unified under the same framework in this sense. Besides, an appealing property also emerges that the weight and code matrices both tend to be naturally sparse without additional constraints. Compared with the standard formulations, SCSR is easier to be extended into the kernel space. To solve the corresponding sparse coding sub problem and dictionary learning sub problem, block-wise coordinate descent and Lagrange multipliers are proposed accordingly. To validate the proposed algorithm, it is implemented in image classification, a successful applications of sparse representation. Experimental results on several benchmark data sets, such as UIUC-Sports, Scene 15, and Caltech-256 demonstrate the effectiveness of our proposed algorithm.

In this paper, we present a facial expression recognition method based on Gabor feature and sparse representation. Sparse Representation based Classification (SRC) has been widely used in computer vision and pattern recognition. And Gabor filter banks can be used to approximately model the signal processing in visual primary cortex. We believe that the nature of the attractive performance of SRC and Gabor feature lies in that they both followed the natures of signal perception of retina and information processing of cortex in human vision. Therefore, we combined the Gabor feature and SRC for facial expression recognition. The comparison experiments of proposed Gabor+SRC algorithm and straightforward SRC application are conducted on JAFFE database. And the experimental results showed the attractive performance of the proposed Gabor+SRC method.

Despite of much research for facial expression recognition, recognizing facial expressions across different persons is still a challenging computer vision task. However, facial expression analysis seems naturally for human visual system. Motivated by visual biology, this paper proposes an invariant feature extraction method for subject-independent facial expression recognition. In particular, we extract the biologically inspired facial features using extended visual cortex model-HMAX which consist of a template matching and a maximum pooling operation. We carefully organized the facial features and achieve subject-independent facial expression recognition using a sparse representation based classifier. The experiments on Yale database and JAFFE database demonstrate the significance of our proposed method for subject-independent facial expression recognition.

Inspired by the cellular differentiation mechanism of organisms, combined with the theory of artificial life and swarm intelligence, a new biomimetic optimization algorithm, cellular differentiation optimization algorithm (CDOA), is proposed in this paper. A certain number of cells are randomly distributed in the search space to find the optimal solution by activating their differential behaviors such as division, growth, migration, adhesion and apoptosis. Experimental results on several benchmark complex functions with high dimensions show that the proposed cellular differentiation optimization algorithm can rapidly converge at high quality solutions and outperform some of the state-of-art in high-dimension numerical function optimization.