Color-Unrelated Head-Shoulder Networks for Fine-Grained Person Re-identification

doi:10.1145/3599730

	Color-Unrelated Head-Shoulder Networks for Fine-Grained Person Re-identification
	Xu, Boqiang1 ; Liang, Jian 2,3; He, Lingxiao4 ; Wu, Jinlin3,5 ; Fan, Chao 6; Sun, Zhenan2,3
发表期刊	ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS
ISSN	1551-6857
	2023-11-01
卷号	19 期号:6 页码:21
通讯作者	Liang, Jian()
摘要	Person re-identification (re-id) attempts to match pedestrian images with the same identity across non-overlapping cameras. Existing methods usually study person re-id by learning discriminative features based on the clothing attributes (e.g., color, texture). However, the clothing appearance is not sufficient to distinguish different persons especially when they are in similar clothes, which is known as the fine-grained (FG) person re-id problem. By contrast, this paper proposes to exploit the color-unrelated feature along with the head-shoulder feature for FG person re-id. Specifically, a color-unrelated head-shoulder network (CUHS) is developed, which is featured in three aspects: (1) It consists of a lightweight head-shoulder segmentation layer for localizing the head-shoulder region and learning the corresponding feature. (2) It exploits instance normalization (IN) for learning color-unrelated features. (3) As IN inevitably reduces inter-class differences, we propose to explore richer visual cues for IN by an attention exploration mechanism to ensure high discrimination. We evaluate our model on the FG-reID, Market1501, and DukeMTMC-reID datasets, and the results show that CUHS surpasses previous methods on both the FG and conventional person re-id problems.
关键词	Person re-identification fine-grained matching visual surveillance
DOI	10.1145/3599730
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[62276256] ; Beijing Nova 435 Program[Z211100002121108]
项目资助者	National Natural Science Foundation of China ; Beijing Nova 435 Program
WOS研究方向	Computer Science
WOS类目	Computer Science, Information Systems ; Computer Science, Software Engineering ; Computer Science, Theory & Methods
WOS记录号	WOS:001035785200033
出版者	ASSOC COMPUTING MACHINERY
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/53961
专题	多模态人工智能系统全国重点实验室
通讯作者	Liang, Jian
作者单位	1.Univ Chinese Acad Sci, 95 Zhongguancun East Rd, Beijing, Peoples R China 2.Chinese Acad Sci, Inst Automat, CRIPAC, 95 Zhongguancun East Rd, Beijing, Peoples R China 3.Chinese Acad Sci, Inst Automat, MAIS, 95 Zhongguancun East Rd, Beijing, Peoples R China 4.AI Res JD, 95 Zhongguancun East Rd, Beijing, Peoples R China 5.Chinese Acad Sci, Ctr Artificial Intelligence & Robot, HKISI, 95 Zhongguancun East Rd, Beijing, Peoples R China 6.Chengdu Discaray Technol Co Ltd, 95 Zhongguancun East Rd, Beijing, Peoples R China
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Xu, Boqiang,Liang, Jian,He, Lingxiao,et al. Color-Unrelated Head-Shoulder Networks for Fine-Grained Person Re-identification[J]. ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS,2023,19(6):21.
APA	Xu, Boqiang,Liang, Jian,He, Lingxiao,Wu, Jinlin,Fan, Chao,&Sun, Zhenan.(2023).Color-Unrelated Head-Shoulder Networks for Fine-Grained Person Re-identification.ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS,19(6),21.
MLA	Xu, Boqiang,et al."Color-Unrelated Head-Shoulder Networks for Fine-Grained Person Re-identification".ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS 19.6(2023):21.