This paper proposes a novel CLIP-driven modality-shared representation learning network named CLIP4VI-ReID for VI-ReID task, which consists of Text Semantic Generation (TSG), Infrared Feature Embedding (IFE), and High-level Semantic Alignment (HSA). Specifically, considering the huge gap in the physical characteristics between natural images and infrared images, the TSG is designed to generate text semantics only for visible images, thereby enabling preliminary visible-text modality alignment. Then, the IFE is proposed to rectify the feature embeddings of infrared images using the generated text semantics. This process injects id-related semantics into the shared image encoder, enhancing its adaptability to the infrared modality. Besides, with text serving as a bridge, it enables indirect visible-infrared modality alignment. Finally, the HSA is established to refine the high-level semantic alignment. This process ensures that the fine-tuned text semantics only contain id-related information, thereby achieving more accurate cross-modal alignment and enhancing the discriminability of the learned modal-shared representations. Extensive experimental results demonstrate that the proposed CLIP4VI-ReID achieves superior performance than other state-of-the-art methods on some widely used VI-ReID datasets.

Fine-grained image clustering (FGIC) is a highly challenging task due to the large intra-class variance, small inter-class variance, and lack of annotation, aiming at grouping images into fine-grained subcategories. Existing FGIC methods generally learn parameterized localization networks to capture key objects for better clustering performance. Despite yielding promising improvements, these methods still have limitations. First, localization networks introduce additional parameters, and not all localized regions are beneficial for clustering. Second, FGIC requires more detailed semantic descriptions, however, current methods only mine supervisory signals from images, making it difficult to meet practical demands. For addressing these limitations, this paper proposes the FGCLIP-based augmented language-driven contrastive clustering (FGCLIP-ALCC) network, which uses frozen FG-CLIP to introduce external knowledge and designs parameter-efficient text branch to accurately locate key objects and learn fine-grained text semantics. More specifically, FGCLIP-ALCC contains two components: the augmented language-driven fine-grained semantic learner (ALFSL) and the multi-modal contrastive clustering heads (MmCCH). First, the ALFSL is designed with a three-stream architecture to enhance robustness, ensure the diversity and accuracy of text descriptions generated subsequently, and utilize image branches to extract visual features. Next, the text branch in ALFSL uses an augmentation-driven diverse text generation module to generate coarse-grained text descriptions, a text fine-graining module to capture key object semantics and refine the text descriptions, and a text filtering module along with a text fusion operation to enhance the intra-class cohesion of text semantics and (to) obtain unique fine-grained text embeddings for each image. Finally, the MmCCH is used to inject text semantics into visual features and obtain clustering results. Experimental results on five fine-grained datasets and four coarse-grained datasets show that FGCLIP-ALCC outperforms state-of-the-art clustering methods on all datasets and metrics, while requiring only 1.2M additional learnable parameters. The code will be released at https://github.com/xjq425/FGCLIP-ALCC.

Subspace clustering (SSC) contributes a lot to the development of unsupervised hyperspectral image (HSI) classification task due to its ability of processing high-dimensional data. In general, SSC suffers from the bottlenecks of high computational cost when dealing with large-scale HSI. Some studies address this problem by using superpixel segmentation. However, the introduction of superpixel segmentation may cause some adverse effects, including interference from nontarget region samples and the oversmoothing of superpixel-level samples. To overcome these issues, we propose a masked superpixel contrastive subspace clustering (MSCSC) for large-scale HSI classification. Specifically, we leverage hyperspectral masked autoencoder (HMAE) rather than conventional autoencoder (CAE) as the backbone to mitigate the interference of nontarget region samples during feature extraction. Then, based on this backbone, we integrate contrastive learning (CL) with self-expressiveness-based SSC to form the superpixel-level contrastive SSC network, which aims to learn the discriminative superpixel-level self-representation. Moreover, we design a novel data augmentation strategy to ensure learn global and local information, improving the distinguishability of superpixel-level features. Experiments on four popular HSI datasets validate the superiority of our proposed method, with a large accuracy improvement compared with state-of-the-art methods.

With the advent of the big data era, there are more and more videos, and video retrieval has gradually become an important research direction in the field of information retrieval. Given that the CLIP model has strong feature learning ability and can fully extract the semantic information contained in image data, introducing CLIP into the field of video retrieval has become a natural choice. However, the standard CLIP can only learn fine-grained spatial features of each frame in videos. How to integrate temporal information on this basis is a major challenge. To address this issue, this paper combines the CLIP with the TimeSformer model and proposes a coarse-fine granularity fusion hashing learning (CFGFHL) method for video retrieval, aiming to obtain more robust spatiotemporal fusion features and more discriminative and compact hash codes. Specifically, CFGFHL consists of three modules: coarse-fine grained feature learning module (CGFLM), video feature fusion module (VFFM) and hash learning module (HLM). CGFLM leverages CLIP for extracting fine-grained spatial features from video frames and TimeSformer for capturing coarse-grained temporal features. Then, these features are fused by VFFM to form a comprehensive video representation. Finally, the HLM is used to refine the fused video representation to generate compact binary hash codes. The combination of contrastive loss and triplet loss ensures effective learning of discriminative and compact hash codes. Experimental evaluations on three benchmark datasets demonstrate that the proposed method achieves superior retrieval accuracy compared to state-of-the-art approaches, while significantly reducing storage requirements and enhancing retrieval efficiency.

Generative attack methods have attracted increasing attention in recent years due to their potential to efficiently deceive black-box models. Among the various attacks, the targeted attacks focus on misleading victim models to produce adversary-desired predictions, which are more challenging and threatening than the untargeted attacks. However, the current methods still exhibit compromised generalization in low-data regimes due to insufficient disentanglement of the instance-level discriminative features from dataset-wide adversarial pattern distributions. To this end, we propose an instance-driven advancing targeted attacks (IATA) framework with transferable pattern embedding. IATA achieves high transferability by integrating dual-branch pattern injection and local patch guided adversarial attacks. Specifically, the instance-driven adversarial generator and the prototype discriminator are designed to fuse instance-level embeddings from a specific target and the prototype-level features of the target class, respectively. The local patch tuning strategy is designed to enhance the dual-substitute model discrepancy attack by stimulating more texture perturbations. Extensive experiments demonstrate that IATA achieves stateof-the-art performance in the black-box setting and significantly outperforms existing targeted attack methods by a margin of 14.98 %, as measured by the targeted transfer attack success rate when Inception-v3 is used as the substitute model.

Zero-shot anomaly detection aims to identify anomalies in unseen classes using knowledge learned from seen classes. Advances in vision-language models like CLIP have demonstrated strong potential for zero-shot anomaly detection tasks. However, CLIP was originally designed to align text with global visual features, focusing on image-level semantics information, making it difficult to capture local anomaly features in pixel-level localization tasks accurately. To address this issue, we propose a CLIP-based Adaptive and Static Prompts learning method for zero-shot anomaly detection (ASP-CLIP). It combines static text prompts and adaptive category prompts to form hybrid text prompts, optimizing text representations. Static text prompts capture general information across categories, while adaptive category prompts are generated by an image adapter module that introduces category-specific information by mapping visual features to the text embedding space. Specifically, we design the Stepwise Adjustment module that improves the alignment between local visual features and text embeddings by utilizing similarity maps identified from shallow local visual features to refine deep local visual features. Experimental results validate the effectiveness of our approach, demonstrating highly competitive performance on the MVTec and VisA datasets.

Anchor-based multi-view subspace clustering is arousing extensive attention due to its capability to handle large-scale high dimensional datasets. They typically first construct anchor graphs, followed by performing spectral clustering to derive the final clustering results. However, the lack of complementary information from multi-view and local structural information in existing methods have resulted in poor anchor graphs, greatly affecting clustering performance. In this paper, we propose a new multi-view subspace clustering algorithm called Multi-view Subspace clustering via Complementary-enhanced Anchor Graphs (MS-CAG) to tackle this challenge. Specifically, MS-CAG first learns a set of consensus anchors for constructing specific anchor graphs. Meanwhile, we propose Anchor Hilbert Schmidt Independence Criterion (AHSIC) term to penalize dependencies of anchor graphs between views, which promotes the learning of effective complementary information. Furthermore, we design Anchor Local Structure Regularization (ALSR) term to enhance the local structure information of the anchor graph, making it more discriminative. Extensive experiments were conducted on five widely used multi-view datasets illustrate the feasibility and effectiveness of MS-CAG.

Multi-view Subspace Clustering (MVSC) effectively aggregating multiple data sources to promise clustering performance. Recently, various anchor-based variants have been introduced to effectively alleviate the computation complexity of MVSC. Although satisfactory advancement has been achieved, existing methods either independently learn anchor matrices and their anchor representations or learn a consensus anchor matrix and unified anchor representation, failing to capture both consistency and complementary information simultaneously. In addition, the time complexity of obtaining clustering results by applying Singular Value Decomposition (SVD) on the anchor representation matrix remains high. To tackle the above problems, we propose an Adaptive Anchor-guided Representation Learning for Efficient Multi-view Subspace Clustering (A2RL-EMVSC) framework, which integrates consensus anchors learning, anchor-guided representation learning and matrix factorization to enhance clustering performance and scalability. Technically, the proposed method learns view-specific anchor representation matrices by consensus anchors guidance, which simultaneously exploit consistency and complementary information. Moreover, by applying matrix decomposition to the view-specific anchor representation matrices, clustering results can be achieved with linear time complexity. Extensive experiments on ten challenging multi-view datasets show that the proposed method can improve the effectiveness and superiority of clustering compared with state-of-the-art methods.

Recently, Referring Image Segmentation (RIS) has gained significant attention for segmenting objects in images based on natural language descriptions. This task integrates computer vision and natural language understanding. Current methods mostly use Transformer as a visual encoder, which is good at modeling long-distance dependencies but easily ignores local details; while CNN can extract rich local features but struggles with capturing global information. For this reason, this paper proposes CNNFormer, a hybrid CNN-Transformer architecture, to fully leverage the complementary advantages of the two to enhance segmentation performance. In the encoding stage, CNN and Transformer extract multimodal features separately and optimize visual and language feature interactions with a well-designed multi-scale cross-modal attention module. Additionally, this paper presents a hierarchical feature fusion module that enhanc-es the integration of local and global information, aiming to improve segmentation performance. The experimental results show that CNNFormer improves 3.91

Face detection is playing a pivotal role for crowd counting and abnormal events detection. However, it is vulnerable to face presentation attacks by printed photos, videos, and 3D masks of real human faces. Although numerous detection techniques based on deep learning have been employed to address the problem of face presentation attacks, there are still several weaknesses in these approaches, such as high algorithm complexity and a lack of detection ability. To overcome these weaknesses, a method based on a multilevel fusion network with Laplacian embedding (MFNet-LE) for the detection of face presentation attacks is proposed. First, a shallow network that contains just three layers was developed, which makes the model faster. Then, an optimised multilevel fusion strategy was developed to combine the input with the output of all previous layers to improve the detection ability of the method. Finally, a Laplacian embedding algorithm is introduced to maintain the inter-class discrimination and penalise the intra-class distance. Under the joint supervision of Laplacian loss and softmax loss, the proposed approach can obtain more discriminative features, which enhance the accuracy of attack detection. Experiments were conducted with three public databases for face presentation attacks: CASIA FASD, Idiap Replay Attack database and MSU USSA. The results demonstrate that the MFNet-LE model can outperform the state-of-the-art methods.

Identity authentication based on face recognition has been significantly improved due to the outstanding ability of face detection, thus it plays an important role in society. However, face recognition system might be deceived by malicious face spoof attacks raising risk from both safety and property. The algorithm to accurately detect face anti-spoofing in identity authentication system is becoming crucial. In this paper, a shallow convolutional neural network with laplacian embedding (shallowCNN-LE) is proposed for face anti-spoofing. Two different types of features are concatenated to accurately detect the face liveness, including depth features and dynamic texture features. First, the developed shallow CNN model contains four layers which make the model faster. Second, we integrate dynamic texture features extracted by using the dual tree complex wavelet transform (DT-CWT) with the depth features as input features to feed into the proposed model. Finally, we propose a laplacian embedding algorithm, which can maintain the inter-class discrimination and penalize the distance of intra-class. When embedding the laplacian loss with the softmax loss, the proposed method can obtain much more discriminative features, which is helpful to detect face anti-spoofing. Experimental results on public databases of CASIA FASD, Replay attack and MSU USSA database demonstrate that our proposed method outperforms the state-of-the-art methods for face anti-spoofing detection.

Tattoos, a soft biometrie trait, are gradually being used to identify suspects in forensic science. Based on LAB color space and K-mean clustering, we propose a novel segmentation algorithm to improve the segmentation accuracy of color tattoos. The process consists of three parts. Firstly, we use K-mean clustering and human skin color segmentation in LAB color space to detect the skin area. Then, we employ the mathematical morphology processing to smooth the clear graphic image of the tattoo segment. Finally, we extract and detect the color tattoos segmentation according to the connectivity of tattoo regions. Compared with the existing methods, this method has low computational complexity. And results of extensive experiments show that the proposed algorithm not only overcomes the limitations of single algorithm, but also improves segmentation accuracy.

By analyzing the difference of facial texture features between living face and photo, we propose a novel face anti-spoofing algorithm based on gray level co-occurrence matrix (GLCM) and dual-tree complex wavelet tree (DT-CWT). Firstly, inspired by the co-occurrence matrix, we extract five texture features including angle second moment, entropy, contrast, correlation and local uniformity to represent the gray direction, interval and amplitude information for the face texture information. Secondly, DT-CWT has the advantages of approximate translation invariance and good direction selectivity. Therefore, the coefficients of DT-CWT can enhance the texture information and edge information in the frequency domain. At last, the SVM classification is used to distinguish between true and fake face. Our algorithm is demonstrated on the published NUAA database. Compared with the existing methods, the feature dimension is reduced. The experimental results show that the proposed algorithm improves the detection accuracy.

Biometric applications have been used globally in everyday life. However, conventional biometrics is created and optimized for high-security scenarios. Being used in daily life by ordinary untrained people is a new challenge. Facing this challenge, designing a biometric system with prior constraints of ergonomics, we propose ergonomic biometrics design model, which attains the physiological factors, the psychological factors, and the conventional security characteristics. With this model, a novel hand-based biometric system, door knob hand recognition system (DKHRS), is proposed. DKHRS has the identical appearance of a conventional door knob, which is an optimum solution in both physiological factors and psychological factors. In this system, a hand image is captured by door knob imaging scheme, which is a tailored omnivision imaging structure and is optimized for this predetermined door knob appearance. Then features are extracted by local Gabor binary pattern histogram sequence method and classified by projective dictionary pair learning. In the experiment on a large data set including 12 000 images from 200 people, the proposed system achieves competitive recognition performance comparing with conventional biometrics like face and fingerprint recognition systems, with an equal error rate of 0.091%. This paper shows that a biometric system could be built with a reliable recognition performance under the ergonomic constraints.

Biometric recognition systems have been widely used globally. However, one effective and highly accurate biometric authentication method, palmprint recognition, has not been popularly applied as it should have been, which could be due to the lack of small, flexible and user-friendly acquisition systems. To expand the use of palmprint biometrics, we propose a novel palmprint acquisition system based on the line-scan image sensor. The proposed system consists of a customized and highly integrated line-scan sensor, a self-adaptive synchronizing unit, and a field-programmable gate array controller with a cross-platform interface. The volume of the proposed system is over 94% smaller than the volume of existing palmprint systems, without compromising its verification performance. The verification performance of the proposed system was tested on a database of 8000 samples collected from 250 people, and the equal error rate is 0.048%, which is comparable to the best area camera-based systems.

Dumbbell is common training equipment in upper body strength,widely used in the strength training and bodybuilding training.Competitive sports,especially ball games project.Fingers,wrists,and upper body strength is indispensable to ball games and it is also play an important guarantee in defense and attack techniques and game stability.Through use of dedicated dumbbell for ball project,it can be focus on the ball,passing, defense,shooting and a series of special strength training techniques,can greatly strengthen the athletes technical movement,also improve the quality of training.This article is a research and development by aiming at a new dumbbell,used for some ball games players′ fingers,wrists and upper body strength training;it is an innovation and improvement of the traditional dumbbell and makes ball games athletes have better training effect in fingers,wrist strength training and it already access to national patents.

潮汕地处广东东部,是我国对外贸易的重要口岸之一,由于潮汕地区特殊的地理位置和人文、自然环境,虽然改革开放后,经济有所发展,但农业人口仍占大多数。通过对潮汕地区农民健身和农村体育活动现状的调查分析,针对存在问题为政府相关部门提出改进对策。

Human hand back skin texture (HBST) is often consistent for a person and distinctive from person to person. In this paper, we study the HBST pattern recognition problem with applications to personal identification and gender classification. A specially designed system is developed to capture HBST images, and an HBST image database was established, which consists of 1,920 images from 80 persons (160 hands). An efficient texton learning based method is then presented to classify the HBST patterns. First, textons are learned in the space of filter bank responses from a set of training images using the l(1) -minimization based sparse representation (SR) technique. Then, under the SR framework, we represent the feature vector at each pixel over the learned dictionary to construct a representation coefficient histogram. Finally, the coefficient histogram is used as skin texture feature for classification. Experiments on personal identification and gender classification are performed by using the established HBST database. The results show that HBST can be used to assist human identification and gender classification.