Part-based Structured Representation Learning for Person Re-identification
文献类型:期刊论文
作者 | Li, Yaoyu3,4; Yao, Hantao3,4; Zhang, Tianzhu1; Xu, Changsheng2,3,4 |
刊名 | ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS |
出版日期 | 2020-12-01 |
卷号 | 16期号:4页码:22 |
ISSN号 | 1551-6857 |
关键词 | Person re-identification representation learning graph convolutional network |
DOI | 10.1145/3412384 |
英文摘要 | Person re-identification aims to match person of interest under non-overlapping camera views. Therefore, how to generate a robust and discriminative representation is crucial for person re-identification. Mining local clues from human body parts to describe pedestrians has been extensively studied in existing methods. However, existing methods locate human body parts coarsely and do not consider the relations among different local parts. To address the above problem, we propose a Part-based Structured Representation Learning (PSRL) for better exploiting local clues to improve the person representation. There are two important modules in our architecture: Local Semantic Feature Extraction and Structured Person Representation Learning. The Local Semantic Feature Extraction module is designed to extract local features from human body semantic regions. After obtaining the local features, the Structured Person Representation Learning is proposed to fuse the local features by considering the person structure. To model the underlying person structure, a graph convolutional network is employed to capture the relations of different semantic regions. The generated structured feature encodes underlying person structure information, and local semantic feature can solve the misalignment problem caused by pose variations in feature matching. By combining them together, we can improve the descriptive ability of the generated representation. Extensive evaluations on four standard benchmarks show that our proposed method achieves competitive performance against state-of-the-art methods. |
资助项目 | National Key Research and Development Program of China[2018AAA0102200] ; National Natural Science Foundation of China[61902399] ; National Natural Science Foundation of China[61721004] ; National Natural Science Foundation of China[U1705262] ; National Natural Science Foundation of China[61532009] ; National Natural Science Foundation of China[61832002] ; National Natural Science Foundation of China[61720106006] ; Key Research Program of Frontier Sciences, CAS[QYZDJ-SSW-JSC039] ; National Postdoctoral Programme for Innovative Talents[BX20180358] |
WOS研究方向 | Computer Science |
语种 | 英语 |
出版者 | ASSOC COMPUTING MACHINERY |
WOS记录号 | WOS:000614096700018 |
资助机构 | National Key Research and Development Program of China ; National Natural Science Foundation of China ; Key Research Program of Frontier Sciences, CAS ; National Postdoctoral Programme for Innovative Talents |
源URL | [http://ir.ia.ac.cn/handle/173211/42861] |
专题 | 自动化研究所_模式识别国家重点实验室_多媒体计算与图形学团队 |
通讯作者 | Xu, Changsheng |
作者单位 | 1.Univ Sci & Technol China, 1202 Room Sci & Technol West Bldg,Huangshan Rd, Hefei, Anhui, Peoples R China 2.Peng Cheng Lab, Shenzhen, Peoples R China 3.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, 95 Zhongguancun East Rd, Beijing, Peoples R China 4.Univ Chinese Acad Sci, Sch Artificial Intelligence, 95 Zhongguancun East Rd, Beijing, Peoples R China |
推荐引用方式 GB/T 7714 | Li, Yaoyu,Yao, Hantao,Zhang, Tianzhu,et al. Part-based Structured Representation Learning for Person Re-identification[J]. ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS,2020,16(4):22. |
APA | Li, Yaoyu,Yao, Hantao,Zhang, Tianzhu,&Xu, Changsheng.(2020).Part-based Structured Representation Learning for Person Re-identification.ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS,16(4),22. |
MLA | Li, Yaoyu,et al."Part-based Structured Representation Learning for Person Re-identification".ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS 16.4(2020):22. |
入库方式: OAI收割
来源:自动化研究所
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。