中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Motion Feature Aggregation for Video-Based Person Re-Identification

文献类型：期刊论文

作者Gu, Xinqian1,2; Chang, Hong1,2; Ma, Bingpeng3; Shan, Shiguang3,4,5
刊名IEEE TRANSACTIONS ON IMAGE PROCESSING
出版日期2022
卷号31页码:3908-3919
关键词Feature extraction Optical imaging Computational modeling Spatiotemporal phenomena Data mining Training Tracking Video-based person re-identification temporal information modeling motion feature extraction
ISSN号1057-7149
DOI10.1109/TIP.2022.3175593
英文摘要Most video-based person re-identification (re-id) methods only focus on appearance features but neglect motion features. In fact, motion features can help to distinguish the target persons that are hard to be identified only by appearance features. However, most existing temporal information modeling methods cannot extract motion features effectively or efficiently for v ideo-based re-id. In this paper, we propose a more efficient Motion Feature Aggregation (MFA) method to model and aggregate motion information in the feature map level for video-based re-id. The proposed MFA consists of (i) a coarse-grained motion learning module, which extracts coarse-grained motion features based on the position changes of body parts over time, and (ii) a fine-grained motion learning module, which extracts fine-grained motion features based on the appearance changes of body parts over time. These two modules can model motion information from different granularities and are complementary to each other. It is easy to combine the proposed method with existing network architectures for end-to-end training. Extensive experiments on four widely used datasets demonstrate that the motion features extracted by MFA are crucial complements to appearance features for video-based re-id, especially for the scenario with large appearance changes. Besides, the results on LS-VID, the current largest publicly available video-based re-id dataset, surpass the state-of-the-art methods by a large margin. The code is available at: https://github.com/guxinqian/Simple-ReID.
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Computer Science ; Engineering
语种英语
WOS记录号WOS:000809404700003
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
源URL[http://119.78.100.204/handle/2XEOYT63/19610]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Chang, Hong
作者单位1.Univ Chinese Acad Sci UCAS, Sch Comp Sci & Technol, Beijing, Peoples R China
2.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China
3.UCAS, Sch Comp Sci & Technol, Beijing 100049, Peoples R China
4.Chinese Acad Sci, Key Lab Intelligent Informat Proc, Inst Comp Technol, Beijing 100190, Peoples R China
5.Peng Chong Lab, Shenzhen 518055, Peoples R China
推荐引用方式
GB/T 7714		 Gu, Xinqian,Chang, Hong,Ma, Bingpeng,et al. Motion Feature Aggregation for Video-Based Person Re-Identification[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2022,31:3908-3919.
APA Gu, Xinqian,Chang, Hong,Ma, Bingpeng,&Shan, Shiguang.(2022).Motion Feature Aggregation for Video-Based Person Re-Identification.IEEE TRANSACTIONS ON IMAGE PROCESSING,31,3908-3919.
MLA Gu, Xinqian,et al."Motion Feature Aggregation for Video-Based Person Re-Identification".IEEE TRANSACTIONS ON IMAGE PROCESSING 31(2022):3908-3919.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
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。