IEEE Transactions on Circuits and Systems for Video Technology最新文献_第2页

FreqMamba: Frequency Enhancement and Mamba-Driven Representation Learning for Pedestrian Attribute Recognition FreqMamba：频率增强和mamba驱动的行人属性识别表征学习

IF 10.8 1区工程技术

IEEE Transactions on Circuits and Systems for Video Technology Pub Date : 2026-10-01 Epub Date: 2026-06-10 DOI: 10.1109/TCSVT.2026.3702340

Junyi Wu;Yan Huang;Min Gao;Yuzhen Niu;Fusheng Li;Yuzhong Chen;Zhang Zhang;Qiang Wu

{"title":"FreqMamba: Frequency Enhancement and Mamba-Driven Representation Learning for Pedestrian Attribute Recognition","authors":"Junyi Wu;Yan Huang;Min Gao;Yuzhen Niu;Fusheng Li;Yuzhong Chen;Zhang Zhang;Qiang Wu","doi":"10.1109/TCSVT.2026.3702340","DOIUrl":"https://doi.org/10.1109/TCSVT.2026.3702340","url":null,"abstract":"This paper focuses on research into multimodal pedestrian attribute recognition (PAR). Existing multimodal PAR methods face three major challenges: 1) reliance on fixed prompt templates that limit refined textual attribute descriptions, 2) neglect of essential visual details, such as textures and contours, which are crucial for distinguishing subtle attributes, and 3) insufficient interaction between visual and textual modalities, resulting in suboptimal recognition performance. To address these challenges, we propose a Frequency Enhancement and Mamba-Driven Representation Learning (FreqMamba) framework. Specifically, we design a Dynamic Prompt Strategy (DPS) that dynamically adapts textual descriptions based on visual features, resulting in refined textual descriptions. Additionally, a Frequency-Enhanced Module (FEM) is introduced to capture texture and contour details in the frequency domain, enriching visual features and further enhancing the generation of dynamic prompts. Finally, we propose a Mamba-Driven Modality Interaction (MDMI) method combined with a Bidirectional Modality Contrastive Loss (BMCLoss) to facilitate effective interaction between modalities, integrating visual and textual information comprehensively. Extensive experiments on multiple PAR datasets, including PETA, PA100K, RAPv1, and RAPv2, demonstrate the superiority of our FreqMamba approach over existing methods.","PeriodicalId":13082,"journal":{"name":"IEEE Transactions on Circuits and Systems for Video Technology","volume":"36 10","pages":"14504-14519"},"PeriodicalIF":10.8,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097368","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Cross-Database Micro-Expression Recognition via Domain-Collaborative Disentanglement Network 基于领域协同解纠缠网络的跨数据库微表情识别

IF 10.8 1区工程技术

IEEE Transactions on Circuits and Systems for Video Technology Pub Date : 2026-10-01 Epub Date: 2026-07-06 DOI: 10.1109/TCSVT.2026.3710504

Shiting Xu;C. L. Philip Chen;Tong Zhang

{"title":"Cross-Database Micro-Expression Recognition via Domain-Collaborative Disentanglement Network","authors":"Shiting Xu;C. L. Philip Chen;Tong Zhang","doi":"10.1109/TCSVT.2026.3710504","DOIUrl":"https://doi.org/10.1109/TCSVT.2026.3710504","url":null,"abstract":"Micro-expression recognition (MER) has made significant advancements in recent years. Most methods focus on individual-database task, which poses significant challenges when attempting to generalize to complex scenarios. To address this limitation, cross-database micro-expression recognition (CDMER) has garnered increasing attention due to its robustness and generalizability. This work presents a domain-collaborative disentanglement network (DCDN) that leverages domain collaboration to facilitate learning domain-invariant and discriminative emotion representations. DCDN employs a dual-branch disentanglement mechanism to explicitly decouple emotion and domain information. On this basis, a domain information filtering module (DIFM) based on graph neural network adopts multi-granularity and feature relation learning, which can capture potential relations to remove the domain component from the emotional features. Furthermore, a disentanglement regularization module (DRM) introduces information-theoretic constraints to enhance the completeness and robustness of the disentanglement. The experimental results demonstrate that DCDN achieves state-of-the-art performance on twelve CDMER tasks, validating the effectiveness of each component and the overall disentanglement strategy.","PeriodicalId":13082,"journal":{"name":"IEEE Transactions on Circuits and Systems for Video Technology","volume":"36 10","pages":"14813-14825"},"PeriodicalIF":10.8,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097478","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

SMRFHash: Semantic-Guided Multi-Representation Fusion Hashing for Fine-Grained Image Retrieval SMRFHash：用于细粒度图像检索的语义引导多表示融合哈希

IF 10.8 1区工程技术

IEEE Transactions on Circuits and Systems for Video Technology Pub Date : 2026-10-01 Epub Date: 2026-07-02 DOI: 10.1109/TCSVT.2026.3709470

Hanyun Zhang;Yihua Chen;Xiaoping Liang;Xianquan Zhang;Zhenjun Tang

{"title":"SMRFHash: Semantic-Guided Multi-Representation Fusion Hashing for Fine-Grained Image Retrieval","authors":"Hanyun Zhang;Yihua Chen;Xiaoping Liang;Xianquan Zhang;Zhenjun Tang","doi":"10.1109/TCSVT.2026.3709470","DOIUrl":"https://doi.org/10.1109/TCSVT.2026.3709470","url":null,"abstract":"Fine-Grained Image Retrieval (FGIR) is an important visual task. Most existing hash-based FGIR methods have difficulty in sufficiently leveraging low-level attributes and effectively associating high-level semantic information with these low-level attributes, thereby limiting their ability to accurately discriminate fine-grained images. To address this issue, we propose a Semantic-Guided Multi-Representation Fusion Hashing (hereafter SMRFHash), which uses semantic features as an anchor to guide and align color and frequency features, thereby enhancing fine-grained retrieval. Specifically, a multi-branch feature extraction module is proposed to separately capture frequency, color, and semantic features of images by attention mechanisms. Then, we further develop a semantic-guided attention fusion module that guides the model to focus on frequency and color regions relevant to the target object. In addition, we propose a confidence-weighted hash loss, which jointly exploits the triplet loss and cross-entropy loss to constrain network training. The proposed loss dynamically re-weights training samples according to the model’s prediction confidence. It improves early-stage training stability and enhances discriminative learning from hard samples. Experimental results show that the SMRFHash outperforms several state-of-the-art methods in retrieval performance.","PeriodicalId":13082,"journal":{"name":"IEEE Transactions on Circuits and Systems for Video Technology","volume":"36 10","pages":"15581-15597"},"PeriodicalIF":10.8,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11593866","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097576","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Robust AI-Generated Video Detection via Color-Agnostic Contrastive Curriculum Learning With Color-Aware Feature Modulation 基于颜色感知特征调制的颜色不可知对比课程学习的鲁棒人工智能生成视频检测

IF 10.8 1区工程技术

IEEE Transactions on Circuits and Systems for Video Technology Pub Date : 2026-10-01 Epub Date: 2026-06-09 DOI: 10.1109/TCSVT.2026.3701354

Leyao Zhu;Peisong He;Liyue Ming;Ji-Zhe Zhou;Tanfeng Sun;Xinghao Jiang

{"title":"Robust AI-Generated Video Detection via Color-Agnostic Contrastive Curriculum Learning With Color-Aware Feature Modulation","authors":"Leyao Zhu;Peisong He;Liyue Ming;Ji-Zhe Zhou;Tanfeng Sun;Xinghao Jiang","doi":"10.1109/TCSVT.2026.3701354","DOIUrl":"https://doi.org/10.1109/TCSVT.2026.3701354","url":null,"abstract":"The rapid development of video generation technologies has benefited multiple fields, but has also introduced substantial security risks and raised public concerns. A series of AI-generated video detection methods have been proposed, but they exhibit vulnerability against lossy operations, especially for color-related editing, which is widely used to improve visual appeal by common users, and even abused by attackers for anti-forensics purposes. To address this issue, we propose a robust AI-generated video detection framework via gradient-guided color-agnostic contrastive curriculum learning. Specifically, the key idea of our color-agnostic contrastive learning is to construct sample pairs adaptively and progressively, where curriculum-style iterative augmentation guided by gradient attention is developed to enrich the diversity of augmented samples and stabilize the training process. Besides, inspired by color constancy, a multi-scale color histogram pyramid is extracted with soft voting as robust auxiliary knowledge, which is injected into the visual encoder by token-wise alignment to perform feature modulation, alleviating the impact of color-related disturbance. Finally, frame-wise features are aggregated using temporal Transformer layers to identify generated videos. Extensive experiments are conducted on various generative models under common and real-world color-editing operations, where results demonstrate the superiority and flexibility of our framework compared with existing methods.","PeriodicalId":13082,"journal":{"name":"IEEE Transactions on Circuits and Systems for Video Technology","volume":"36 10","pages":"15669-15684"},"PeriodicalIF":10.8,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097580","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Learning Shallow-Robust Vision Transformers With Selective Distillation for Real-Time UAV Tracking 基于选择性蒸馏学习的浅鲁棒视觉变压器用于无人机实时跟踪

IF 10.8 1区工程技术

IEEE Transactions on Circuits and Systems for Video Technology Pub Date : 2026-10-01 Epub Date: 2026-06-24 DOI: 10.1109/TCSVT.2026.3706810

Fansheng Zeng;Qihua Liang;Bineng Zhong;Chaocan Xue;Yufei Tan;Zhiyi Mo;Shuxiang Song

{"title":"Learning Shallow-Robust Vision Transformers With Selective Distillation for Real-Time UAV Tracking","authors":"Fansheng Zeng;Qihua Liang;Bineng Zhong;Chaocan Xue;Yufei Tan;Zhiyi Mo;Shuxiang Song","doi":"10.1109/TCSVT.2026.3706810","DOIUrl":"https://doi.org/10.1109/TCSVT.2026.3706810","url":null,"abstract":"To deploy high-performance vision transformer on resource-constrained uncrewed aerial vehicles, existing methods often adopt dynamic layer activation or layer selection mechanisms to reduce the depth of ViT and accelerate model inference. However, these mechanisms disrupt the inherent sequential feature modeling path, which can limit the modeling capacity of ViT. To alleviate this issue, we propose SRTrack, a simple yet robust tracker built upon a novel teacher-student framework. For the teacher model, we introduce a random exit training strategy that randomly terminates forward process at different ViT layers, encouraging shallow layers to undertake more modeling tasks and enhancing their discriminative capacity while preserving the sequential modeling path. For the student model, we design a selective distillation strategy to achieve effective compression. Instead of blindly relying on the conventional last-layer features, this strategy adaptively selects the most discriminative features from the enhanced teacher model as the distillation target, enabling more robust feature modeling. By combining these two strategies, SRTrack exhibits strong modeling capability even with only a few ViT layers. Extensive experiments on multiple UAV benchmarks demonstrate that SRTrack achieves a superior trade-off between tracking precision and efficiency. Our code is available at <uri>https://github.com/GXNU-ZhongLab/SRTrack</uri>","PeriodicalId":13082,"journal":{"name":"IEEE Transactions on Circuits and Systems for Video Technology","volume":"36 10","pages":"16025-16035"},"PeriodicalIF":10.8,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097718","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Corrections to "Generative Latent Coding for Ultra-Low Bitrate Image and Video Compression" 对“超低比特率图像和视频压缩的生成隐编码”的修正

IF 10.8 1区工程技术

IEEE Transactions on Circuits and Systems for Video Technology Pub Date : 2026-10-01 Epub Date: 2026-10-05 DOI: 10.1109/TCSVT.2026.3705274

Linfeng Qi;Zhaoyang Jia;Jiahao Li;Bin Li;Houqiang Li;Yan Lu

引用次数: 0

Segment Any Vehicle: Semantic and Visual Context Driven SAM and a Benchmark 任何车辆分段：语义和视觉上下文驱动的SAM和基准

IF 10.8 1区工程技术

IEEE Transactions on Circuits and Systems for Video Technology Pub Date : 2026-10-01 Epub Date: 2026-07-01 DOI: 10.1109/TCSVT.2026.3708475

Xiao Wang;Ziwen Wang;Wentao Wu;Anjie Wang;Jiashu Wu;Yantao Pan;Chenglong Li

{"title":"Segment Any Vehicle: Semantic and Visual Context Driven SAM and a Benchmark","authors":"Xiao Wang;Ziwen Wang;Wentao Wu;Anjie Wang;Jiashu Wu;Yantao Pan;Chenglong Li","doi":"10.1109/TCSVT.2026.3708475","DOIUrl":"https://doi.org/10.1109/TCSVT.2026.3708475","url":null,"abstract":"With the rapid advancement of autonomous driving, vehicle perception, particularly detection and segmentation, demands increasingly sophisticated algorithmic performance. Pre-trained large segmentation models, especially the Segment Anything Model (SAM), have sparked significant interest and inspired new research directions in artificial intelligence. However, SAM cannot be directly applied to fine-grained vehicle part segmentation tasks. Its text-prompted segmentation functionality is not publicly accessible, and the mask regions generated in its default mode lack semantic labels, limiting its utility in structured, category-specific segmentation tasks. To address these limitations, we propose SAV (Segment Anything Vehicle), a novel framework comprising three core components: a SAM-based encoder-decoder, a vehicle part knowledge graph, and a context sample retrieval encoding module. The knowledge graph explicitly models the spatial and geometric relationships among vehicle parts through structured ontology, effectively encoding prior structural knowledge. Meanwhile, the context retrieval module enhances segmentation by identifying and leveraging visually similar vehicle instances from training data, providing rich contextual priors for improved generalization. Furthermore, we introduce VehicleSeg10K, a new large-scale benchmark dataset for vehicle part segmentation containing 11,665 high-quality images and 97,471 annotated part instances across diverse scenes and viewpoints. We conduct comprehensive experiments on this dataset and two other benchmark datasets, evaluating multiple representative baseline methods to establish a solid foundation for future research and comparison. Both the dataset and source code are available at <uri>https://github.com/Event-AHU/SAV</uri>","PeriodicalId":13082,"journal":{"name":"IEEE Transactions on Circuits and Systems for Video Technology","volume":"36 10","pages":"15230-15243"},"PeriodicalIF":10.8,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097755","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

MGCA-Net: Multi-Grained Category-Aware Network for Open-Vocabulary Temporal Action Localization MGCA-Net：面向开放词汇时态动作定位的多粒度类别感知网络

IF 10.8 1区工程技术

IEEE Transactions on Circuits and Systems for Video Technology Pub Date : 2026-10-01 Epub Date: 2026-07-06 DOI: 10.1109/TCSVT.2026.3710560

Zhenying Fang;Richang Hong

{"title":"MGCA-Net: Multi-Grained Category-Aware Network for Open-Vocabulary Temporal Action Localization","authors":"Zhenying Fang;Richang Hong","doi":"10.1109/TCSVT.2026.3710560","DOIUrl":"https://doi.org/10.1109/TCSVT.2026.3710560","url":null,"abstract":"Open-Vocabulary Temporal Action Localization (OV-TAL) aims to recognize and localize instances of any desired action categories in videos without explicitly curating training data for all categories. Existing methods mostly recognize action categories at a single granularity, which degrades localization performance. To address this issue, we propose a Multi-Grained Category-Aware Network (MGCA-Net) comprising a localizer, an action presence predictor, a base classifier, and a coarse-to-fine classifier. Specifically, the localizer generates category-agnostic action proposals. For these proposals, the action presence predictor and base classifier estimate the action presence score and probabilities over base categories, respectively. Based on these predictions, proposals are partitioned into base action instances, novel proposals, or discarded ones. The category of each base action instance is determined by the class with the highest probability from the base classifier. In contrast, the categories of novel proposals are inferred by a coarse-to-fine classifier, which first identifies action presence at the video level—i.e., all action categories occurring in the input video—to obtain coarse categories, and then assigns each proposal to one category from them at the proposal level. Through coarse-to-fine awareness from video to proposal granularity for novel actions, and base classifier awareness of base actions at snippet granularity, MGCA-Net achieves multi-grained category modeling, effectively improving localization performance. Comprehensive evaluations on the THUMOS’14, ActivityNet-1.3, and FineAction benchmarks demonstrate competitive performance. Moreover, MGCA-Net also yields strong results under the Zero-Shot Temporal Action Localization (ZS-TAL) setting, with its advantage becoming more pronounced at higher tIoU thresholds. Our code is available at <uri>https://github.com/zhenyingfang/MGCA-Net</uri>","PeriodicalId":13082,"journal":{"name":"IEEE Transactions on Circuits and Systems for Video Technology","volume":"36 10","pages":"14578-14589"},"PeriodicalIF":10.8,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097870","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Functionality Separation: Rethinking Dual-Stream Networks for Class-Incremental Learning 功能分离：重新思考类增量学习的双流网络

IF 10.8 1区工程技术

IEEE Transactions on Circuits and Systems for Video Technology Pub Date : 2026-10-01 Epub Date: 2026-07-07 DOI: 10.1109/TCSVT.2026.3710882

Qingqing Gao;Xiaoyan Li;Zhongfan Sun;Boyue Wang;Zexi Zhang;Yongli Hu;Baocai Yin;Wen Gao

{"title":"Functionality Separation: Rethinking Dual-Stream Networks for Class-Incremental Learning","authors":"Qingqing Gao;Xiaoyan Li;Zhongfan Sun;Boyue Wang;Zexi Zhang;Yongli Hu;Baocai Yin;Wen Gao","doi":"10.1109/TCSVT.2026.3710882","DOIUrl":"https://doi.org/10.1109/TCSVT.2026.3710882","url":null,"abstract":"Class-incremental learning (CIL) aims to enable models to continually learn new classes without forgetting previously learned ones, often struggling with the stability-plasticity dilemma. The dual-stream architectures adopt one stream with limited learning ability for storing the learned knowledge, and the other stream with high plasticity for learning new information, achieving success in CIL. However, different methods involve completely different components and the design principles for dual-stream architectures remain unclear. In this paper, in contrast to the previous methods that focus on a specific point of dual-stream network design, we conduct a large number of experiments across the board to figure out the principles. It is found that the key to designing dual-stream methods is making each component complete a specific function, namely functionality separation, instead of placing hope in one component to accomplish multiple functions as in many previous works. These crucial functions for dual-stream networks are the widely studied stability-maintaining and plasticity-enhancing, together with the generally overlooked knowledge integration introduced in this work. Additionally, despite a large number of investigations on regularization methods, a simple combination of classification loss and distillation loss is sufficient for the regularization of dual-stream networks. Based on all these experiments and analyses, it is natural to acquire the dual-stream model combined with the compression training paradigm, which effectively separates the functions of stability, plasticity, and the integration of new and old knowledge, achieving the state-of-the-art results on CIFAR-100 and ImageNet-Subset CIL benchmarks. Code is available at <uri>https://github.com/gaoqingqing77/DualFS</uri>","PeriodicalId":13082,"journal":{"name":"IEEE Transactions on Circuits and Systems for Video Technology","volume":"36 10","pages":"15977-15995"},"PeriodicalIF":10.8,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097950","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Nonconvex Low-Rank Tensor Representation With Self-Enhanced Structure Penalty for Multi-View Subspace Clustering 基于自增强结构惩罚的多视图子空间聚类非凸低秩张量表示

IF 10.8 1区工程技术

IEEE Transactions on Circuits and Systems for Video Technology Pub Date : 2026-10-01 Epub Date: 2026-06-05 DOI: 10.1109/TCSVT.2026.3700127

Zhuo Liu;Dong Hu;Zhi Wang

{"title":"Nonconvex Low-Rank Tensor Representation With Self-Enhanced Structure Penalty for Multi-View Subspace Clustering","authors":"Zhuo Liu;Dong Hu;Zhi Wang","doi":"10.1109/TCSVT.2026.3700127","DOIUrl":"https://doi.org/10.1109/TCSVT.2026.3700127","url":null,"abstract":"In addition to the high dimensionality and heterogeneity of multi-view data, its underlying subspaces contain a wealth of intrinsic correlation information. However, existing MvSC models still remain struggling in effectively exploiting the high-order complementary information and handling the confusing points in disjoint subspaces. To this end, we propose a novel tensorized MvSC model by integrating the nonconvex tensor Schatten-<inline-formula> <tex-math>$2/3$ </tex-math></inline-formula> quasi-norm with a self-enhanced structure penalty constraint. The proposed model can not only characterize high-order correlation through adaptive subspace components encoding, but also manipulate the confusing points meticulously by capturing the refined geometric structure of multiple disjoint subspaces. As a result, a promising representation can be learned for the authentic subspaces revealment. More importantly, an effective algorithm has been proposed to solve the challenging nonconvex optimization problem of the proposed model, and the resulting solution sequence is theoretically guaranteed to converge to a Karush-Kuhn-Tucker (KKT) point. Furthermore, it can be proven that several key variable sequences are Cauchy ones. Extensive experiments conducted on various datasets demonstrate the superiority of our proposed model in comparison with many state-of-the-art models. MATLAB code is available at <uri>https://github.com/wangzhi-swu/SeT-MvSC</uri>","PeriodicalId":13082,"journal":{"name":"IEEE Transactions on Circuits and Systems for Video Technology","volume":"36 10","pages":"15507-15522"},"PeriodicalIF":10.8,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149097100","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0