Deep multi-view clustering aims to exploit the rich semantic information contained in heterogeneous multi-view data to uncover the underlying relationships among samples. However, existing deep multi-view clustering models often overlook inter-cluster separability and the effective integration of semantic information across views, resulting in insufficient feature discriminability and consequently limited clustering performance. To address the above issues, this paper proposes a novel deep multi-view clustering method via cluster-semantic guidance. We separate clusters to enhance inter-cluster discriminability, while incorporating a knowledge distillation mechanism to ensure cluster stability and facilitate the learning of clustering-friendly representations. Furthermore, by aggregating sample-level semantic information, the model is guided to follow a cluster-oriented learning strategy that promotes the extraction of discriminative features, thereby strengthening the sample representation capability. Our method effectively learns discriminative and clustering-friendly representations, guiding the model to acquire distinctive feature embeddings from a cluster-oriented perspective. Our comprehensive experiments across datasets of varying scales confirm the model's effectiveness, showing superior clustering performance over existing state-of-the-art methods.

Unrestrained palmprint recognition refers to a comprehensive identity authentication technology, that performs personal authentication based on the palmprint images captured in uncontrolled environments, i.e., smartphone cameras, surveillance footage, or near-infrared scenarios. However, unrestrained palmprint recognition faces significant challenges due to the variability in image quality, lighting conditions, and hand poses present in such settings. We observed that many existing methods utilize the subspace structure as a prior, where the block diagonal property of the data has been proved. In this paper, we consider a unified learning model to guarantee the consensus block diagonal property for all views, named high-confident block diagonal analysis for multi-view palmprint recognition (HCBDA_MPR). Particularly, this paper proposed a multi-view block diagonal regularizer to guide that all views learn a consensus block diagonal structure. In such a manner, the main discriminant features from each view can be preserved while the learning of the strict block diagonal structure across all views. Experimental results on a number of real-world unrestrained palmprint databases proved the superiority of the proposed method, where the highest recognition accuracies were obtained in comparison with the other state-of-the-art related methods.

Multi-modal learning is extensively applied to diagnose brain diseases such as epilepsy and Alzheimer's disease. However, incomplete multi-modal data, where some modalities are unavailable or difficult to collect, limits the effectiveness of conventional methods. Additionally, existing approaches often overlook semantic relationships between neighbors with the same-label and latent information in missing modalities. To address these challenges, we propose an adjacent-aware distillation recovery framework designed for incomplete multi-modal learning, with a focus on diagnosing representative brain diseases, i.e. epilepsy and Alzheimer's disease. The key novelty of our framework lies in its joint design of adjacent-aware modality recovery and multi-modal representation learning in a single end-to-end pipeline. Specifically, we introduce a label-guided adjacent-aware recovery module that uses a self-attention mechanism to exploit neighbor semantics and generate distribution-consistent features for high-quality modality reconstruction. The recovered features are then refined through a knowledge distillation pathway into a modality generator, enhancing generalization under severe data incompleteness. For multi-modal representation learning, the recovered modality information is fused with the original incomplete information to enhance feature extraction and representation. Extensive experiments demonstrate the effectiveness of our method in diagnosing epilepsy and Alzheimer's disease.

Palmprint has shown great potential for biometric recognition due to its high user-friendliness and low invasiveness. However, most existing palmprint studies focus solely on feature learning and matching without considering the quality of the images, while the palmprint images collected in contactless scenarios are usually low-quality with complex backgrounds, significantly degrading recognition performance. In this paper, we propose a mask-guided cross palm attention network (MCPAnet) for complex palm-print image super-resolution. It first applies multi-scale pyramid feature aggregation to detect the palm-specific regions from complex palmprint images containing various non-palm backgrounds. With the guidance of the palm-specific region masks, we develop multiple residual-based learning groups to exploit the palmprint intrinsic features through channel-wise and spatial-wise attention interaction for high-resolution palmprint image reconstruction. Moreover, we design palmpix and perceptual losses to make the HR palmprint images realistic at the visual level while simultaneously preserving the identity-aware features as the ground-truth ones. Experimental results on four public palmprint benchmarks clearly show the effectiveness of the proposed method for palmprint image super-resolution.

Adversarial attacks on palmprint recognition are crucial because these attacks can manipulate palmprint images to bypass authentication systems, posing security threats. However, many existing adversarial attacks overlook the unique features of palmprint. In this paper, we propose an enhanced palmprint adversarial attack against visible and invisible features. First, we focus on extracting palmprint main lines that are crucial for targeted adversarial attacks. Second, we introduce a channel attention mechanism that can effectively emphasize the invisible features in the palmprint image. We fuse these two features to achieve a more effective attack, ensuring that both visible and invisible details contribute to the enhancement of the adversarial attack. Finally, adversarial examples generated by our method are incorporated into the training process. The experimental results demonstrate the effectiveness of our enhanced attack.

Current existing clustering methods for handling incomplete multi-view data primarily concentrate on learning a common representation or graph from the available views, while overlooking the latent information contained in the missing views and the imbalance of information among different views. Furthermore, instances with weak discriminative features usually degrading the precision of consistent representation or graph across all views. To address these problems, in this paper, we propose a simple but efficient method, called high-confident local structure guided consensus graph learning for incomplete multi-view clustering (HLSCG_IMC). Specifically, this method can adaptively learn a strict block diagonal structure from the available samples using a block diagonal representation regularizer. Different from the existing methods using a simple pairwise affinity graph for structure construction, we consider the influence of instances located at the edge of two clusters on the construction of graph for each view. By harnessing the proposed high-confident strict block diagonal structures, the approach seeks to directly guide the learning of the robust consensus graph. A number of experiments have been conducted to verify the efficacy of our approach.

Magnetic Flux Leakage (MFL) detection has emerged as a promising nondestructive testing method for identifying defects in ferromagnetic materials, such as the steel cables used in cable-stayed bridges. Focusing on these critical load-bearing components—which are prone to corrosion, cracks, and localized damage under harsh environmental and operational conditions—this study leverages MFL-based point cloud data to enhance defect detection accuracy and reliability. A specialized MFL sensor array was deployed to collect high-resolution three-dimensional leakage magnetic field data, generating dense point clouds that capture the spatial variations in magnetic flux induced by surface and subsurface anomalies. To isolate defect-related signals from background interference, advanced point cloud processing algorithms were developed, encompassing noise filtering, feature extraction, and geometric reconstruction. Crucially, the surface area of the reconstructed 3D point clouds serves as a quantitative metric for defect detection. Furthermore, the local metal loss area of the steel cable can be derived from the cross-sectional surface area of these 3D point clouds. The results demonstrate that integrating point cloud data with automated defect characterization provides a robust framework for the structural health monitoring of stay cables, enabling early intervention and prolonging service life. This work contributes significantly to advancing intelligent inspection technologies for critical steel cable infrastructure.

Three significant challenges have been limiting the stable palmprint recognition via mobile devices: 1) rotations and unconsensus scales of the unconstrait hand; 2) noises generated in the open imaging environments; and 3) low quality images captured in the low-illumination conditions. Current palmprint representation methods rely on rich prior knowledge and lack any adaptability to its environment. In this paper, we propose a multi-view hierarchical graph learning based palmprint recognition (MVHG_PR) method, which comprehensively presents the discriminant palmprint features from multiple views. Fully exploiting different types of characteristics, it aims to adaptively perform multi-view feature description and feature selection. To this end, a novel regularized heterogeneous graph learning strategy is proposed for construction of the intra- and inter-class relationships, learning high-order structures for different views between four tuples, rather than just pair-wise intrinsic structures. In the proposed model, the learned hierarchical graph is given an elastic power from the label information to precisely reflect the intra-class and the inter-class relationships in each view, such that the projected structures can be aligned locally and globally. Besides this, we constructed a mobile palmprint dataset to simulate as many open application circumstance as possible to verify the effectiveness of contactless palmprint recognition methods. Experimental results have proven the superiority of the proposed MVHG_PR by achieving the best recognition performances on a number of real-world palmprint databases. The proposed mobile palmprint database and the code of the proposed MVHG_PR are available athttps://github.com/ShupingZhao/MVHG_PR-for-contactless-palmprint-recognition.

Multi-view clustering typically leverages the consistency and complementarity among views to partition different samples. However, existing deep learning-based methods often face the dilemma between selecting complementary information and capturing essential details: 1) Capturing complementary semantics among views may introduce label-irrelevant redundant information. 2) Only extracting consistent semantic information will cause information loss, hindering the clarity in downstream tasks. To address these issues, we propose a novel method from the perspective of meta-learning to learn clustering-friendly representations with minimal redundancy. Specifically, we train an information compressor to guide the model in describing the original samples as compact as possible with minimal information, thus learning the key semantics with minimized redundancy. Meta-learning bi-level optimization promotes the nested optimization of feature embedding and information compressor. Meanwhile, a semantic puzzle mechanism complements the semantic fragments by exploiting the relationships between low-level features, resulting in a consensus representation with strong discriminative power. We conducted extensive experiments on datasets with various sizes to validate the effectiveness of our model, demonstrating significant performance improvements over several state-of-the-art methods.

Incomplete multiview clustering (IMVC) has received extensive attention in recent years. However, existing works still have several shortcomings: 1) some works ignore the correlation of sample pairs in the global structural distribution; 2) many methods are computational expensive, thus cannot be applicable to the large-scale incomplete data clustering tasks; and 3) some methods ignore the refinement of the bipartite graph structure. To address the above issues, we propose a novel anchor graph network for IMVC, which includes a generative model and a similarity metric network. Concretely, the method uses a generative model to construct bipartite graphs, which can mine latent global structure distributions of sample pairs. Later, we use graph convolution network (GCN) with the constructed bipartite graphs to learn the structural embeddings. Notably, the introduction of bipartite graphs can greatly reduce the computational complexity and thus enable our model to handle large-scale data. Unlike previous works based on bipartite graph, our method employs bipartite graphs to guide the learning process in GCNs. In addition, an innovative adaptive learning strategy that can construct robust bipartite graphs is incorporated into our method. Extensive experiments demonstrate that our method achieves the comparable or superior performance compared with the state-of-the-art methods.

Consensus representation learning is one of the most popular approaches in the field of multi-view clustering. However, most of the existing methods cannot learn discriminative representations with a clustering-friendly structure since these methods ignore the separation among clusters and the compactness within each cluster. To tackle this issue, we propose a new deep multi-view clustering network with a dual contrastive mechanism to learn clustering-friendly representations. Specifically, our method employs dual contrasting losses: a dynamic cluster diffusion loss to maximize the distance between different clusters and a reliable neighbor-guided positive alignment loss to enhance compactness within each cluster. Our approach includes several key components: view-specific encoders to extract high-level features from each view, and an adaptive feature fusion strategy to obtain consensus representations across multiple views. The dynamic cluster diffusion module ensures inter-cluster separation by maximizing distances between different clusters in the consensus feature space. Simultaneously, the reliable neighbor-guided positive alignment module improves within-cluster compactness through a pseudo-label and nearest neighbor structure-driven contrastive loss. Experimental results on several datasets show that our method can acquire clustering-friendly representations with both good properties of inter-cluster separation and within-cluster compactness, and outperforms the existing state-of-the-art approaches in clustering performance. Our source code is available at https://github.com/tweety1028/DCMVC.

In order to reduce the negative effect of missing data on clustering, incomplete multiview clustering (IMVC) has become an important research content in machine learning. At present, graph-based methods are widely used in IMVC, but these methods still have some defects. First, some of the methods overlook potential relationships across views. Second, most of the methods depend on local structure information and ignore the global structure information. Third, most of the methods cannot use both global structure information and potential information across views to adaptively recover the incomplete relationship structure. To address the above issues, we propose a unified optimization framework to learn reasonable affinity relationships, called low-rank graph completion-based IMVC (LRGR_IMVC). 1) Our method introduces adaptive graph embedding to effectively explore the potential relationship among views; 2) we append a low-rank constraint to adequately exploit the global structure information among views; and 3) this method unites related information within views, potential information across views, and global structure information to adaptively recover the incomplete graph structure and obtain complete affinity relationships. Experimental results on several commonly used datasets show that the proposed method achieves better clustering performance significantly than some of the most advanced methods.

Advanced deep multi-view subspace clustering methods are based on the self-expressive model, which has achieved impressive performance. However, most existing works have several limitations: 1) They endure high computational complexity when learning a consistent affinity matrix, impeding their capacity to handle large-scale multi-view data; 2) The global and local structure information of multi-view data remains under-explored. To tackle these challenges, we propose a simplistic but comprehensive framework called Multi-view Self-Expressive Subspace Clustering (MSESC) network. Specifically, we design a deep metric network to replace the conventional self-expressive model, which can directly and efficiently produce the intrinsic similarity values of any instance-pairs of all views. Moreover, our method explores global and local structure information from the connectivity of instance-pairs across views and the nearest neighbors of instance-pairs within the view, respectively. By integrating global and local structure information within a unified framework, MSESC can learn a high-quality shared affinity matrix for better clustering performance. Extensive experimental results indicate the superiority of MSESC compared to several state-of-the-art methods.

Image style transfer has always been a popular topic in the field of computer vision. Many researchers have achieved transfer image texture characteristics, such as converting real photos to painting styles. Different from these style transfer tasks, our target is to colorize the anime line art according to the color scheme of the given reference image. We transfer the color of the anime characters' hair, clothes, skin, etc. to another grayscale anime line art. In this paper, we propose a model based on Spatially-Adaptive (DE) Normalization (SPADE) to achieve anime style transfer. In addition, we use a data augmentation method to solve the "lazy" problem of neural networks.

Linear discriminant analysis (LDA) is a very popular supervised feature extraction method and has been extended to different variants. However, classical LDA has the following problems: 1) The obtained discriminant projection does not have good interpretability for features; 2) LDA is sensitive to noise; and 3) LDA is sensitive to the selection of number of projection directions. In this paper, a novel feature extraction method called robust sparse linear discriminant analysis (RSLDA) is proposed to solve the above problems. Specifically, RSLDA adaptively selects the most discriminative features for discriminant analysis by introducing the$l_{2,1}$norm. An orthogonal matrix and a sparse matrix are also simultaneously introduced to guarantee that the extracted features can hold the main energy of the original data and enhance the robustness to noise, and thus RSLDA has the potential to perform better than other discriminant methods. Extensive experiments on six databases demonstrate that the proposed method achieves the competitive performance compared with other state-of-the-art feature extraction methods. Moreover, the proposed method is robust to the noisy data.

In this paper, we present a generic effective formulation, dubbed discriminative latent linear regression (DLL-R), for multi-category classification. We formulate the DLLR optimization problem as a joint learning framework of discriminative latent feature selection and robust linear regression. Specifically, instead of directly projecting the original high-dimensional features onto a target space, DLLR learns discriminative latent representation by concurrently suppressing the redundant information from original features and constructing a robust latent subspace. To improve the effectiveness of the regression task, a capped lp-norm regression model is formulated for robust linear regression. Furthermore, DLLR incorporates learning latent representation and building regressing prediction into one framework for reducing the classification error of the regression model. An efficient optimization algorithm is developed to solve the resulting optimization problem. Extensive experimental results conducted on diverse databases validate the effectiveness of the proposed DLLR method in comparison with state-of-the-art regression methods.

This paper aims to explore the optimal feature selection with dimensionality reduction and jointly sparse representation scheme for classification. The proposed method is called Optimal Feature Selection Classification (OFSC). Our model simultaneously learns an orthogonal subspace for jointly sparse feature selection and representation via l2,1-norms regularization. To solve the proposed model, an alternately iterative algorithm is proposed to optimize both the jointly sparse projection matrix and representation matrix. Experimental results on three public face datasets and one action dataset validate the quick convergence of our algorithm and show that the proposed method is more competitive than the state-of-the-art methods.