A Semantic-aware Attention and Visual Shielding Network for Cloth-changing Person Re-identification
Key Laboratory of Computer Vision and System, Ministry of Education, Tianjin University of Technology(天津理工大学计算机视觉与系统教育部重点实验室);School of Computer Science and Information Engineering, Hefei University of Technology(合肥工业大学计算机与信息工程学院)
Zan Gao, Hongwei Wei, Weili Guan, Jie Nie, Meng Wang, Shenyong Chen
备注:
arXiv admin note: text overlap with arXiv:2108.04527
Cloth-changing person reidentification (ReID) is a newly emerging research topic that aims to retrieve pedestrians whose clothes are changed. Since the human appearance with different clothes exhibits large variations, it is very difficult for existing approaches to extract discriminative and robust feature representations. Current works mainly focus on body shape or contour sketches, but the human semantic information and the potential consistency of pedestrian features before and after changing clothes are not fully explored or are ignored. To solve these issues, in this work, a novel semantic-aware attention and visual shielding network for cloth-changing person ReID (abbreviated as SAVS) is proposed where the key idea is to shield clues related to the appearance of clothes and only focus on visual semantic information that is not sensitive to view/posture changes. Specifically, a visual semantic encoder is first employed to locate the human body and clothing regions based on human semantic segmentation information. Then, a human semantic attention module (HSA) is proposed to highlight the human semantic information and reweight the visual feature map. In addition, a visual clothes shielding module (VCS) is also designed to extract a more robust feature representation for the cloth-changing task by covering the clothing regions and focusing the model on the visual semantic information unrelated to the clothes. Most importantly, these two modules are jointly explored in an end-to-end unified framework. Extensive experiments demonstrate that the proposed method can significantly outperform state-of-the-art methods, and more robust features can be extracted for cloth-changing persons. Compared with FSAM (published in CVPR 2021), this method can achieve improvements of 32.7% (16.5%) and 14.9% (-) on the LTCC and PRCC datasets in terms of mAP (rank-1), respectively.
COCAS: A Large-Scale Clothes Changing Person Dataset for Re-identification
Shenzhen Institutes of Advanced Technology, Chinese Academy of Science(中国科学院深圳先进技术研究院);University of Chinese Academy of Sciences(中国科学院大学);Institute of Microelectronics of the Chinese Academy of Sciences(中国科学院微电子研究所)
近年来,在个人身份重新识别(re-id)方面取得了很大进展。Market 1501、CUHK 03和DukeMTMC等学术基准对促进re-id研究起到了重要作用。据我们所知,所有现有的基准都假设同一个人会有同样的衣服。而在现实世界中,人们经常会换衣服。为了解决换衣服的人的真实身份问题,我们构建了一个新的大规模的真实身份基准命名为Clothes Changing Person Set(COCAS),它提供了多个图像的同一身份与不同的衣服。COCAS共包含5,266人的62,382张身体图像。在COCAS的基础上,我们引入了一个新的人re-id设置的衣服更换问题,其中的查询既包括一个衣服模板和一个人的形象采取另一件衣服。此外,我们提出了一个名为生物特征服装网络(BC-Net)的两个分支网络,它可以有效地集成生物特征和服装特征,以实现在我们的设置下的身份识别。实验表明,利用服装模板进行服装换装识别是可行的。
Content and Salient Semantics Collaboration for Cloth-Changing Person Re-Identification
School of Computer Science, Fudan University(复旦大学计算机科学学院);School of Automation, Northwestern Polytechnical University(西北工业大学自动化学院);School of Data Science, Fudan University(复旦大学数据科学学院)
SCORE: SubDistribution-aware Collaborative Knowledge Reinforcing for Cloth-Hybrid Lifelong Person Re-Identification
Wangxuan Institute of Computer Technology, Peking University(北京大学王选计算机研究所);University of Chinese Academy of Sciences(中国科学院大学);Intelligent Science & Technology Academy of CASIC(中国航天科工集团智能科技研究院)
Unsupervised Long-Term Person Re-Identification with Clothes Change
China Academy of Aerospace Science and Innovation(中国航天科技创新研究院);Tsinghua University(清华大学);University of Surrey(萨里大学);Beijing University of Posts and Telecommunications(北京邮电大学)
Causal Clothes-Invariant Feature Learning for Cloth-Changing Person Re-ID
School of Cyber Science and Technology, University of Science and Technology of China(中国科学技术大学网络安全学院);Anhui Province Key Laboratory of Digital Security(安徽省数字安全重点实验室);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);School of Data Science, University of Science and Technology of China(中国科学技术大学数据科学学院);Wuhan University(武汉大学)
Identity-Guided Collaborative Learning for Cloth-Changing Person Reidentification
Shandong Artificial Intelligence Institute(山东人工智能研究院);Qilu University of Technology (Shandong Academy of Sciences)(齐鲁工业大学(山东省科学院));Tianjin University of Technology(天津理工大学);Monash University(莫纳什大学);Tongji University(同济大学);Hefei University of Technology(合肥工业大学)
Discriminative Pedestrian Features and Gated Channel Attention for Clothes-Changing Person Re-Identification
College of Computer Science;Technology Nanjing University of Aeronautics;School of Information;Artificial Intelligence Anhui Agriculture University Hefei, China
Cloning Outfits from Real-World Images to 3D Characters for Generalizable Person Re-Identification
Inception Institute of Artificial Intelligence (IIAI)(Inception人工智能研究院(IIAI));Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)
OC4-ReID: Occluded Cloth-Changing Person Re-Identification
Beijing University of Posts and Telecommunications(北京邮电大学);South China University of Technology(华南理工大学);Nanjing University of Information Science & Technology(南京信息科学技术大学);University of Oxford(牛津大学);Nanjing University(南京大学)
Exploring Fine-Grained Representation and Recomposition for Cloth-Changing Person Re-Identification
Shanghai Key Lab of Intelligent Information Processing, Fudan University(复旦大学上海市智能信息处理重点实验室);School of Automation, Northwestern Polytechnical University(西北工业大学自动化学院);Fudan ISTBI—ZJNU Algorithm Centre for Brain-inspired Intelligence, Fudan University(复旦大学ISTBI-浙江师范大学类脑智能算法中心)
PGDS: Pose-Guidance Deep Supervision for Mitigating Clothes-Changing in Person Re-Identification
University of Science, Vietnam National University, Ho Chi Minh City(越南国家大学胡志明市校区科学大学);John von Neumann Institute, Vietnam National University, Ho Chi Minh City(越南国家大学胡志明市校区约翰·冯·诺依曼研究所);University of Arkansas(阿肯色大学);Northwestern University(西北大学)
Image-Text-Image Knowledge Transfer for Lifelong Person Re-Identification with Hybrid Clothing States
School of Automation, Northwestern Polytechnical University(自动化学院,西北工业大学);School of Computer Science, Shanghai Key Lab of Intelligent Information Processing, Fudan University(计算机学院,上海智能信息处理重点实验室,复旦大学);Shenzhen Research Institute of Northwestern Polytechnical University(西北工业大学深圳研究院)
See What You Seek: Semantic Contextual Integration for Cloth-Changing Person Re-Identification
Sanya Science and Education Innovation Park, Wuhan University of Technology(武汉理工大学三亚科学教育创新园);Hubei Key Laboratory of Transportation Internet of Things, School of Computer Science and Artificial Intelligence, Wuhan University of Technology(武汉理工大学交通运输物联网重点实验室);Hubei Key Laboratory of Big Data Intelligent Analysis and Application, School of Computer Science and Information Engineering, Hubei University(湖北大数据智能分析与应用重点实验室);National Engineering Research Center for Multimedia Software, School of Computer Science, Wuhan University(国家多媒体软件工程研究中心);School of Computing, Macquarie University(麦考瑞大学计算机学院);Rapid-Rich Object Search Lab, School of Electrical and Electronic Engineering, Nanyang Technological University(快速富对象搜索实验室)
Try Harder: Hard Sample Generation and Learning for Clothes-Changing Person Re-ID
School of Computer Science and Engineering, Beihang University(北航计算机科学与工程学院);School of Artificial Intelligence, Beihang University(北航人工智能学院);Zhongguancun Academy(中关村学院)
QA-ReID: Quality-Aware Query-Adaptive Convolution Leveraging Fused Global and Structural Cues for Clothes-Changing ReID
School of Business, Stevens Institute of Technology(斯蒂文斯理工学院商学院);Electrical and Computer Engineering, University of California, San Diego(加州大学圣地亚哥分校电子与计算机工程系);Tandon School of Engineering, New York University(纽约大学塔恩工学院);Institute of Operations Research and Analytics, National University of Singapore(新加坡国立大学运筹与分析研究所)