检索结果-内蒙古大学图书馆

pedestrian attribute recognition via CLIP-Based Prompt Vision-Language Fusion

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2025年第1期35卷 148-161页

作者： Wang, Xiao Jin, Jiandong Li, Chenglong Tang, Jin Zhang, Cheng Wang, Wei Anhui Univ Hefei Comprehens Natl Sci Ctr Sch Comp Sci & Technol Inst Artificial Intelligence Hefei 230601 Peoples R China Anhui Univ Anhui Prov Key Lab Multimodal Cognit Computat Informat Mat & Intelligent Sensing Lab Anhui Prov Hefei 230601 Peoples R China Anhui Univ Sch Artificial Intelligence Hefei 230601 Peoples R China Video Invest Detachment Hefei Publ Secur Bur Hefei 230031 Peoples R China

Existing pedestrian attribute recognition (PAR) algorithms adopt pre-trained CNN (e.g., ResNet) as their backbone network for visual feature learning, which might obtain sub-optimal results due to the insufficient employment of the relations between pedestrian images and attribute labels. In this paper, we formulate PAR as a vision-language fusion problem and fully exploit the relations between pedestrian images and attribute labels. Specifically, the attribute phrases are first expanded into sentences, and then the pre-trained vision-language model CLIP is adopted as our backbone for feature embedding of visual images and attribute descriptions. The contrastive learning objective connects the vision and language modalities well in the CLIP-based feature space, and the Transformer layers used in CLIP can capture the long-range relations between pixels. Then, a multi-modal Transformer is adopted to fuse the dual features effectively and feed-forward network is used to predict attributes. To optimize our network efficiently, we propose the region-aware prompt tuning technique to adjust very few parameters (i.e., only the prompt vectors and classification heads) and fix both the pre-trained VL model and multi-modal Transformer. Our proposed PAR algorithm only adjusts 0.75% learnable parameters compared with the fine-tuning strategy. It also achieves new state-of-the-art performance on both standard and zero-shot settings for PAR, including RAPv1, RAPv2, WIDER, PA100K, and PETA-ZS, RAP-ZS datasets. The source code and pre-trained models will be released on https://***/Event-AHU/OpenPAR.

关键词： pedestrians Transformers Visualization Semantics Feature extraction Tuning Circuits and systems pedestrian attribute recognition pre-trained big models prompt learning multi-modal fusion vision-language

来源：评论

学校读者我要写书评

暂无评论

pedestrian attribute recognition Based on Multimodal Transformer 6th

Pedestrian Attribute Recognition Based on Multimodal Transfo...

引用

6th Chinese Conference on Pattern recognition and Computer Vision (PRCV)

作者： Liu, Dan Song, Wei Zhao, Xiaobing Minzu Univ China Sch Informat Engn Beijing 100081 Peoples R China Minzu Univ China Key Lab Ethn Language Intelligent Anal & Secur Go MOE Beijing 100081 Peoples R China Minzu Univ China Natl Lauguage Resource Monitoring & Res Ctr Minor Beijing 100081 Peoples R China

ISBN: (纸本)9789819984282;9789819984299

pedestrian attribute recognition (PAR) is susceptible to variable shooting angles, lighting, and occlusions. Improving recognition accuracy to suit its application in various complex scenarios is one of the most important tasks. In this paper, based on the Image-Text Multimodal Transformer, the intra-modal and inter-modal correlations are learned from pedestrian images and attribute labels. The applicability of six different multimodal fusion frameworks for attribute recognition is explored. The impact of different frameworks' fused feature division methods on recognition accuracy is compared and analyzed. The comparative experiments verify the robustness and efficiency of the Early Concatenate framework, which has achieved multiple best metric scores on the two major public PAR datasets, PA100k and RAP. This paper not only proposes a new Transformer-based high-accuracy multimodal network, but also provides feasible ideas and directions for further research on PAR. The comparative discussion based on various multimodal frame-works also provides a perspective that can be learned for other multimodal tasks.

关键词： pedestrian attribute recognition Multimodal Learning Transformer

来源：评论

学校读者我要写书评

暂无评论

pedestrian attribute recognition in Video Surveillance Scenarios Based on View-attribute Attention Localization

引用

Machine Intelligence Research 2022年第2期19卷 153-168页

作者： Wei-Chen Chen Xin-Yi Yu Lin-Lin Ou College of Information Engineering Zhejiang University of TechnologyHangzhou 310023China

pedestrian attribute recognition in surveillance scenarios is still a challenging task due to the inaccurate localization of specific attributes. In this paper, we propose a novel view-attribute localization method based on attention(VALA), which utilizes view information to guide the recognition process to focus on specific attributes and attention mechanism to localize specific attribute-corresponding areas. Concretely, view information is leveraged by the view prediction branch to generate four view weights that represent the confidences for attributes from different views. View weights are then delivered back to compose specific view-attributes, which will participate and supervise deep feature extraction. In order to explore the spatial location of a view-attribute, regional attention is introduced to aggregate spatial information and encode inter-channel dependencies of the view feature. Subsequently, a fine attentive attribute-specific region is localized, and regional weights for the view-attribute from different spatial locations are gained by the regional attention. The final view-attribute recognition outcome is obtained by combining the view weights with the regional weights. Experiments on three wide datasets(richly annotated pedestrian(RAP), annotated pedestrian v2(RAPv2), and PA-100 K) demonstrate the effectiveness of our approach compared with state-of-the-art methods.

关键词： pedestrian attribute recognition surveillance scenarios view-attribute attention mechanism localization

来源：评论

学校读者我要写书评

暂无评论

pedestrian attribute recognition based on attribute correlation

引用

MULTIMEDIA SYSTEMS 2022年第3期28卷 1069-1081页

作者： Zhao, Ruijie Lang, Congyan Li, Zun Liang, Liqian Wei, Lili Feng, Songhe Wang, Tao Beijing Jiaotong Univ Beijing 100044 Peoples R China

pedestrian attribute recognition is widely used in pedestrian tracking and pedestrian re-identification. This task confronts two fundamental challenges. One comes from its multi-label nature;the other one comes from the characteristics of data samples, such as the class imbalance and the partial occlusion. In this work, we propose a Cross attribute and Feature Network (CAFN) that fully exploits the correlations between any pair of attributes for the pedestrian attribute recognition to tackle these challenges. Concretely, CAFN contains two modules: Cross-attribute Attention Module (C2AM) and Cross-feature Attention Module (CFAM). C2AM enables the network to automatically learn the relation matrix during the training process which can quantify the correlations between any pair of attributes in the attribute set, and CFAM is introduced to fuse different attribute features to generate more accurate and robust attribute features. Extensive experiments demonstrate that the proposed CAFN performs favorably compared with state-of-the-art approaches.

关键词： pedestrian attribute recognition Attention mechanism Multi-label classification attribute correlation Visual feature correlation

来源：评论

学校读者我要写书评

暂无评论

pedestrian attribute recognition: A survey

引用

PATTERN recognition 2022年 121卷 108220-108220页

作者： Wang, Xiao Zheng, Shaofei Yang, Rui Zheng, Aihua Chen, Zhe Tang, Jin Luo, Bin Anhui Univ Sch Comp Sci & Technol Hefei Peoples R China Anhui Univ Sch Artificial Intelligence Hefei Peoples R China Peng Cheng Lab Shenzhen Peoples R China Univ Sydney Sch Comp Sci Fac Engn Sydney NSW Australia

pedestrian attribute recognition (PAR) is an important task in computer vision community and plays an important role in practical video surveillance. The goal of this paper is to review existing works using traditional methods or based on deep learning networks. Firstly, we introduce the background of pedestrian attribute recognition, including the fundamental concepts and formulation of pedestrian attributes and corresponding challenges. Secondly, we analyze popular solutions for this task from eight perspectives. Thirdly, we discuss the specific attribute recognition, then, give a comparison between deep learning and traditional algorithm based PAR methods. After that, we show the connections between PAR and other computer vision tasks. Fourthly, we introduce the benchmark datasets, evaluation metrics in this community, and give a brief performance comparison. Finally, we summarize this paper and give several possible research directions for PAR. The project page of this paper can be found at: https://***/view/ahu-pedestrianattributes/ . (c) 2021 Elsevier Ltd. All rights reserved.

关键词： pedestrian attribute recognition Multi-label learning Multi-task learning Deep learning CNN-RNN

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous Feature Re-Sampling for Balanced pedestrian attribute recognition

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2025年第4期47卷 2706-2722页

作者： Zhou, Yibo Li, Bo Hu, Hai-Miao Zhang, Xiaokang Zhang, Dongping Wang, Hanzi Beihang Univ Sch Comp Sci & Engn State Key Lab Virtual Real Technol & Syst Beijing 100191 Peoples R China Beihang Univ Hangzhou Innovat Inst Hangzhou 310051 Peoples R China China Jiliang Univ Coll Informat Engn Hangzhou 310018 Peoples R China Xiamen Univ Fujian Key Lab Sensing & Comp Smart City Xiamen 361005 Peoples R China

In pedestrian attribute recognition (PAR), the loose umbrella term 'attribute' ranges from human soft-biometrics to wearing accessory, and even extending to various subjective body descriptors. As a result, the vast coverage of 'attributes' implies that, instead of being over-specialized to limited attributes with exclusive characteristic, PAR should be approached from a much fundamental perspective. To this end, given that most attributes are greatly under-represented in real-world datasets, we simply distill PAR into a visual task of multi-label recognition under significant data imbalance. Accordingly, we introduce feature re-sampled detached learning (FRDL) to decouple label-balanced learning from the curse of attributes co-occurrence. Specifically, FRDL is able to balance the sampling distribution of an attribute without biasing the label prior of co-occurring others. As a complementary method, we also propose gradient-oriented augment translating (GOAT) to alleviate the feature noise and semantics imbalance aggravated in FRDL. Integrated in a highly unified framework, FRDL and GOAT substantially refresh the state-of-the-art performance on various realistic benchmarks, while maintaining a minimal computational budget. Further analytical discussion and experimental evidence corroborate the veracity of our advancement: this is the first work that establishes labels-independent and impartial balanced learning for PAR.

关键词： Training Semantics pedestrians Eigenvalues and eigenfunctions Noise Computational modeling Accuracy Visualization Noise reduction Feature extraction pedestrian attribute recognition multi-label image classification label imbalance balanced feature re-sampling heterogeneous feature augmentation

来源：评论

学校读者我要写书评

暂无评论

attribute correlation mask fusion network for pedestrian attribute recognition

引用

VISUAL COMPUTER 2025年第6期41卷 3719-3734页

作者： Li, Baoan Zhang, Long Teng, Shangzhi Lyu, Xueqiang Beijing Informat Sci & Technol Univ Beijing Key Lab Internet Culture Digital Dissemina Beijing 100101 Peoples R China

The main goal of pedestrian attribute recognition is to identify various attributes of pedestrians captured in video surveillance. Due to the numerous categories of pedestrian attribute labels, the complex and easily overlooked correlations among attributes, PAR is a challenging task. Traditional methods usually treat each attribute independently, ignoring the possible intrinsic correlations between attributes. We design a pedestrian attribute recognition network ACMFNet which can fuse pedestrian attributes uniqueness features and attribute correlation features. Specifically, we propose an attribute correlation query module, which are used to learn discriminative attribute features. Then, we construct a mask fusion module to automatically learn the importance of the image feature and attribute correlation feature. To better distinguish the modality differences between images and attribute texts, we propose modality prompt. Experimental results show that our method can significantly enhance the network's ability to recognize pedestrian attributes. On three pedestrian attribute recognition datasets PA100K, PETA, and UAV-Human, our proposed method shows competitive performance compared to the state-of-the-art methods. Our source code is available at https://***/luffy-op/ACMFNet.

关键词： pedestrian attribute recognition Modality fusion Mask fusion

来源：评论

学校读者我要写书评

暂无评论

Rethinking attention mechanism for enhanced pedestrian attribute recognition

引用

NEUROCOMPUTING 2025年 639卷

作者： Wu, Junyi Huang, Yan Gao, Min Niu, Yuzhen Chen, Yuzhong Wu, Qiang Fuzhou Univ Fujian Key Lab Network Comp & Intelligent Informat Coll Comp & Data Sci Fuzhou 350108 Fujian Peoples R China Minist Educ Engn Res Ctr BigData Intelligence Fuzhou 350108 Fujian Peoples R China Univ Technol Sydney Australian Artificial Intelligence Inst Sydney NSW 2007 Australia Fuzhou Univ Coll Phys & Informat Engn Fujian Key Lab Intelligent Proc & Wireless Transmi Fuzhou 350108 Fujian Peoples R China Univ Technol Sydney Sch Elect & Data Engn Sydney NSW 2007 Australia

pedestrian attribute recognition (PAR) plays a crucial role in various computer vision applications, demanding precise and reliable identification of attributes from pedestrian images. Traditional PAR methods, though effective in leveraging attention mechanisms, often suffer from the lack of direct supervision on attention, leading to potential overfitting and misallocation. This paper introduces a novel and model-agnostic approach, Attention-Aware Regularization (AAR), which rethinks the attention mechanism by integrating causal reasoning to provide direct supervision of attention maps. AAR employs perturbation techniques and a unique optimization objective to assess and refine attention quality, encouraging the model to prioritize attribute-specific regions. Our method demonstrates significant improvement in PAR performance by mitigating the effects of incorrect attention and fostering a more effective attention mechanism. Experiments on standard datasets showcase the superiority of our approach over existing methods, setting a new benchmark for attention-driven PAR models.

关键词： pedestrian attribute recognition Attention mechanism Attention-aware regularization

来源：评论

学校读者我要写书评

暂无评论

Vision Transformer With Relation Exploration for pedestrian attribute recognition

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2025年 27卷 198-208页

作者： Tan, Hao Tan, Zichang Weng, Dunfang Liu, Ajian Wan, Jun Lei, Zhen Li, Stan Z. Inst Automat Chinese Acad Sci CASIA State Key Lab Multimodal Artificial Intelligence S Beijing 100190 Peoples R China Univ Chinese Acad Sci UCAS Sch Artificial Intelligence Beijing 100049 Peoples R China Sangfor Technol Inc Shenzhen 518055 Peoples R China Chinese Acad Sci Shenzhen Inst Adv Technol SIAT Shenzhen 518067 Peoples R China AI PRIME Shanghai 200082 Peoples R China Macau Univ Sci & Technol Sch Comp Sci & Engn Macau Peoples R China Chinese Acad Sci Hong Kong Inst Sci & Innovat Ctr Artificial Intelligence & Robot Hong Kong Peoples R China Westlake Univ Hangzhou 310024 Zhejiang Peoples R China

pedestrian attribute recognition has achieved high accuracy by exploring the relations between image regions and attributes. However, existing methods typically adopt features directly extracted from the backbone or utilize a single structure (e.g., transformer) to explore the relations, leading to inefficient and incomplete relation mining. To overcome these limitations, this paper proposes a comprehensive relationship framework called Vision Transformer with Relation Exploration (ViT-RE) for pedestrian attribute recognition, which includes two novel modules, namely attribute and Contextual Feature Projection (ACFP) and Relation Exploration Module (REM). In ACFP, attribute-specific features and contextual-aware features are learned individually to capture discriminative information tailored for attributes and image regions, respectively. Then, REM employs Graph Convolutional Network (GCN) Blocks and Transformer Blocks to concurrently explore attribute, contextual, and attribute-contextual relations. To enable fine-grained relation mining, a Dynamic Adjacency Module (DAM) is further proposed to construct instance-wise adjacency matrix for the GCN Block. Equipped with comprehensive relation information, ViT-RE achieves promising performance on three popular benchmarks, including PETA, RAP, and PA-100 K datasets. Moreover, ViT-RE achieves the first place in the WACV 2023 UPAR Challenge.

关键词： Feature extraction Transformers pedestrians Visualization Periodic structures Correlation Semantics Data mining Recurrent neural networks Computer vision pedestrian attribute recognition vision transformer feature projection relation exploration

来源：评论

学校读者我要写书评

暂无评论

Orientation-Aware pedestrian attribute recognition Based on Graph Convolution Network

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2024年 26卷 28-40页

作者： Lu, Wei-Qing Hu, Hai-Miao Yu, Jinzuo Zhou, Yibo Wang, Hanzi Li, Bo Beihang Univ Sch Comp Sci & Engn Beijing Key Lab Digital Media Beijing 100191 Peoples R China Beihang Univ Hangzhou Innovat Inst Hangzhou 310051 Peoples R China Beihang Univ State Key Lab Virtual Real Technol & Syst Beijing 100191 Peoples R China Xiamen Univ Sch Informat Fujian Key Lab Sensing & Comp Smart City Xiamen 361005 Peoples R China

pedestrian attribute recognition (PAR) aims to generate a structured description of pedestrians and plays an important role in surveillance. Current work focusing on 2D images can achieve decent performance when there is no variation in the captured pedestrian orientation. However, the performance of these works cannot be maintained in scenarios when the orientation of pedestrians is ignored. To mitigate this problem, this paper proposes orientation-aware pedestrian attribute recognition based on graph convolution network (GCN), which is composed of an orientation-aware spatial attention (OSA) module and an orientation-guided attribute-relation learning (OAL) module. Since some attributes can be invisible for certain orientations, OSA is proposed for orientation-aware feature extraction to enhance the learned representation of the visual attributes. Moreover, since different orientations result in different relations among attributes, OAL is proposed to achieve distinguishable and impactful attribute relations by eliminating the confusion of attribute relations in different orientations. Experiments on three challenging datasets (PETA, RAP, and PA100 K) demonstrate that the proposed PAR outperforms the state-of-the-art methods by considerable margins.

关键词： pedestrian attribute recognition pedestrian-orientation graph convolution network

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：