SANet: Statistic Attention Network for Video-Based Person Re-Identification

doi:10.1109/TCSVT.2021.3119983

	SANet: Statistic Attention Network for Video-Based Person Re-Identification
	Bai, Shutao 1,2; Ma, Bingpeng 2; Chang, Hong 1,2; Huang, Rui 3,4; Shan, Shiguang 1,2; Chen, Xilin 1,2
	2022-06-01
发表期刊	IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
ISSN	1051-8215
卷号	32 期号:6 页码:3866-3879
摘要	Capturing long-range dependencies during feature extraction is crucial for video-based person re-identification (re-id) since it would help to tackle many challenging problems such as occlusion and dramatic pose variation. Moreover, capturing subtle differences, such as bags and glasses, is indispensable to distinguish similar pedestrians. In this paper, we propose a novel and efficacious Statistic Attention (SA) block which can capture both the long-range dependencies and subtle differences. SA block leverages high-order statistics of feature maps, which contain both long-range and high-order information. By modeling relations with these statistics, SA block can explicitly capture long-range dependencies with less time complexity. In addition, high-order statistics usually concentrate on details of feature maps and can perceive the subtle differences between pedestrians. In this way, SA block is capable of discriminating pedestrians with subtle differences. Furthermore, this lightweight block can be conveniently inserted into existing deep neural networks at any depth to form Statistic Attention Network (SANet). To evaluate its performance, we conduct extensive experiments on two challenging video re-id datasets, showing that our SANet outperforms the state-of-the-art methods. Furthermore, to show the generalizability of SANet, we evaluate it on three image re-id datasets and two more general image classification datasets, including ImageNet. The source code is available at http://vipl.ict.ac.cn/resources/codes/code/SANet_code.zip.
关键词	Feature extraction Task analysis Computational modeling Visualization Video sequences Fuses Computer science Person re-identification self-attention long-range dependencies high-order statistics
DOI	10.1109/TCSVT.2021.3119983
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2017YFA0700800] ; Natural Science Foundation of China (NSFC)[61876171] ; Natural Science Foundation of China (NSFC)[61976203]
WOS研究方向	Engineering
WOS类目	Engineering, Electrical & Electronic
WOS记录号	WOS:000805833400046
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：8[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/19605
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Ma, Bingpeng
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 100049, Peoples R China 3.Chinese Univ Hong Kong, Sch Sci & Engn, Shenzhen 518172, Guangdong, Peoples R China 4.Shenzhen Inst Artificial Intelligence & Robot, Shenzhen 518172, Guangdong, Peoples R China
推荐引用方式 GB/T 7714	Bai, Shutao,Ma, Bingpeng,Chang, Hong,et al. SANet: Statistic Attention Network for Video-Based Person Re-Identification[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2022,32(6):3866-3879.
APA	Bai, Shutao,Ma, Bingpeng,Chang, Hong,Huang, Rui,Shan, Shiguang,&Chen, Xilin.(2022).SANet: Statistic Attention Network for Video-Based Person Re-Identification.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,32(6),3866-3879.
MLA	Bai, Shutao,et al."SANet: Statistic Attention Network for Video-Based Person Re-Identification".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 32.6(2022):3866-3879.