Hybrid Modality Metric Learning for Visible-Infrared Person Re-Identification

doi:10.1145/3473341

	Hybrid Modality Metric Learning for Visible-Infrared Person Re-Identification
	Zhang, La 1; Guo, Haiyun2 ; Zhu, Kuan2 ; Qiao, Honglin 3; Huang, Gaopan 4; Zhang, Sen5 ; Zhang, Huichen 5; Sun, Jian 1; Wang, Jinqiao2
发表期刊	ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS
ISSN	1551-6857
	2022-02-01
卷号	18 期号:1 页码:15
通讯作者	Guo, Haiyun(haiyun.guo@nlpr.ia.ac.cn)
摘要	Visible-infrared person re-identification (Re-ID) has received increasing research attention for its great practical value in night-time surveillance scenarios. Due to the large variations in person pose, viewpoint, and occlusion in the same modality, as well as the domain gap brought by heterogeneous modality, this hybrid modality person matching task is quite challenging. Different from the metric learning methods for visible person re-ID, which only pose similarity constraints on class level, an efficient metric learning approach for visible-infrared person Re-ID should take both the class-level and modality-level similarity constraints into full consideration to learn sufficiently discriminative and robust features. In this article, the hybrid modality is divided into two types, within modality and cross modality. We first fully explore the variations that hinder the ranking results of visible-infrared person re-ID and roughly summarize them into three types: within-modality variation, cross-modality modality-related variation, and cross-modality modality-unrelated variation. Then, we propose a comprehensive metric learning framework based on four kinds of paired-based similarity constraints to address all the variations within and cross modality. This framework focuses on both class-level and modality-level similarity relationships between person images. Furthermore, we demonstrate the compatibility of our framework with any paired-based loss functions by giving detailed implementation of combing it with triplet loss and contrastive loss separately. Finally, extensive experiments of our approach on SYSIJ-MM01 and RegDB demonstrate the effectiveness and superiority of our proposed metric learning framework for visible-infrared person Re-ID.
关键词	Visible-infrared person re-identification cross-modality metric learning
DOI	10.1145/3473341
收录类别	SCI
语种	英语
资助项目	Key-Area Research and Development Program of Guangdong Province[2020B010165001] ; National Natural Science Foundation of China[61772527] ; National Natural Science Foundation of China[62002356] ; National Natural Science Foundation of China[61925303] ; Open Project of Key Laboratory of Ministry of Public Security for Road Traffic Safety[2020ZDSYSKFKT04]
项目资助者	Key-Area Research and Development Program of Guangdong Province ; National Natural Science Foundation of China ; Open Project of Key Laboratory of Ministry of Public Security for Road Traffic Safety
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:000772639300002
出版者	ASSOC COMPUTING MACHINERY
七大方向——子方向分类	图像视频处理与分析
引用统计	被引频次：12[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/48181
专题	紫东太初大模型研究中心_图像与视频分析
通讯作者	Guo, Haiyun
作者单位	1.Beijing Inst Technol, 5 South St, Beijing 100081, Peoples R China 2.Chinese Acad Sci, Inst Automat, 95 Zhongguancun East Rd, Beijing, Peoples R China 3.Alibaba Cloud, Radiance JinHui Tower,Bldg 6,4th Dist, Beijing, Peoples R China 4.Alibaba Cloud, Ali Ctr, Nanjing, Jiangsu, Peoples R China 5.Minist Publ Secur, Traff Management Res Inst, 88 Qianrong Rd, Wuxi, Jiangsu, 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	Zhang, La,Guo, Haiyun,Zhu, Kuan,et al. Hybrid Modality Metric Learning for Visible-Infrared Person Re-Identification[J]. ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS,2022,18(1):15.
APA	Zhang, La.,Guo, Haiyun.,Zhu, Kuan.,Qiao, Honglin.,Huang, Gaopan.,...&Wang, Jinqiao.(2022).Hybrid Modality Metric Learning for Visible-Infrared Person Re-Identification.ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS,18(1),15.
MLA	Zhang, La,et al."Hybrid Modality Metric Learning for Visible-Infrared Person Re-Identification".ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS 18.1(2022):15.