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. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
Enhancing Person Re-Identification Performance Through In Vivo Learning

文献类型：期刊论文

作者Huang, Yan1; Huang, Yan1; Zhang, Zhang1; Wu, Qiang2; Zhong, Yi3; Wang, Liang1
刊名IEEE TRANSACTIONS ON IMAGE PROCESSING
出版日期2024
卷号33页码:639-654
ISSN号1057-7149
关键词Person re-identification in vivo learning boosting performance
DOI10.1109/TIP.2023.3341762
通讯作者Huang, Yan(yhuang@nlpr.ia.ac.cn) ; Wang, Liang(wangliang@nlpr.ia.ac.cn)
英文摘要This research investigates the potential of in vivo learning to enhance visual representation learning for image-based person re-identification (re-ID). Compared to traditional self-supervised learning (which require external data), the introduced in vivo learning utilizes supervisory labels generated from pedestrian images to improve re-ID accuracy without relying on external data sources. Three carefully designed in vivo learning tasks, leveraging statistical regularities within images, are proposed without the need for laborious manual annotations. These tasks enable feature extractors to learn more comprehensive and discriminative person representations by jointly modeling various aspects of human biological structure information, contributing to enhanced re-ID performance. Notably, the method seamlessly integrates with existing re-ID frameworks, requiring minimal modifications and no additional data beyond the existing training set. Extensive experiments on diverse datasets, including Market1501, CUHK03-NP, Celeb-reID, Celeb-reid-light, PRCC, and LTCC, demonstrate substantial enhancements in rank-1 precision compared to state-of-the-art methods.
资助项目National Natural Science Foundation of China
WOS研究方向Computer Science ; Engineering
语种英语
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号WOS:001140427400002
资助机构National Natural Science Foundation of China
源URL[http://ir.ia.ac.cn/handle/173211/54780]  
专题多模态人工智能系统全国重点实验室
通讯作者Huang, Yan; Wang, Liang
作者单位1.Chinese Acad Sci CASIA, Inst Automat, Ctr Res Intelligent Percept & Comp, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China
2.Univ Technol Sydney UTS, Sch Elect & Data Engn, Ultimo, NSW 2007, Australia
3.Beijing Inst Technol BIT, Sch Informat & Elect, Beijing 100081, Peoples R China
推荐引用方式
GB/T 7714		 Huang, Yan,Huang, Yan,Zhang, Zhang,et al. Enhancing Person Re-Identification Performance Through In Vivo Learning[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2024,33:639-654.
APA Huang, Yan,Huang, Yan,Zhang, Zhang,Wu, Qiang,Zhong, Yi,&Wang, Liang.(2024).Enhancing Person Re-Identification Performance Through In Vivo Learning.IEEE TRANSACTIONS ON IMAGE PROCESSING,33,639-654.
MLA Huang, Yan,et al."Enhancing Person Re-Identification Performance Through In Vivo Learning".IEEE TRANSACTIONS ON IMAGE PROCESSING 33(2024):639-654.

入库方式： OAI收割

来源：自动化研究所

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。