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
Progressive Sub-Domain Information Mining for Single-Source Generalizable Gait Recognition

文献类型：期刊论文

作者Wang, Yang3; Huang, Yan2; Shan, Caifeng1,3; Wang, Liang2
刊名IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
出版日期2023
卷号18页码:4787-4799
关键词Gait recognition Data models Task analysis Training Computational modeling Feature extraction Pipelines domain generalization clustering domain-invariant feature
ISSN号1556-6013
DOI10.1109/TIFS.2023.3298518
通讯作者Shan, Caifeng(caifeng.shan@gmail.com)
英文摘要Recent years have witnessed the deployment of fully supervised gait recognition. However, due to domain diversity, gait recognition models designed under the fully supervised condition suffer from poor generalization in unseen domains. How to improve the generalization ability of gait recognition models and enhance their performance on unseen domains is unexplored in existing gait recognition approaches. This paper investigates the generalizable gait recognition problem and proposes a Progressive Sub-domain Information Mining (PSIM) framework for single-source generalizable gait recognition. During training, the PSIM can mine sub-domain information from a single large-scale source domain by differentiating gait features extracted from different people through unsupervised clustering. Then, domain information mitigation loss and domain homogenization loss are introduced to regularize those gait features to be domain-insensitive. The above procedures are conducted iteratively until the model converges. The PSIM framework is model-agnostic, which can directly improve the generalization ability of state-of-the-art gait recognition models without significantly increasing the complexity of the model. In experiments, our model-agnostic PSIM framework is adopted on several gait recognition models to show its effectiveness in boosting gait recognition performance for the single-source generalizable gait recognition task.
资助项目Natural Science Foundation of Shandong Province[ZR2022MF322] ; Talent Introduction Program for Youth Innovation Teams of Shandong Province ; National Key Research and Development Program of China[2022ZD0117900] ; National Natural Science Foundation of China[62236010] ; National Natural Science Foundation of China[62276261] ; Key Research Program of Frontier Sciences CAS[ZDBS-LYJSC032] ; Fellowship of China Postdoctoral Science Foundation[2022T150698] ; International Postdoctoral Exchange Fellowship Program (Talent-Introduction Program) of China[YJ20210324]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:001047300900002
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构Natural Science Foundation of Shandong Province ; Talent Introduction Program for Youth Innovation Teams of Shandong Province ; National Key Research and Development Program of China ; National Natural Science Foundation of China ; Key Research Program of Frontier Sciences CAS ; Fellowship of China Postdoctoral Science Foundation ; International Postdoctoral Exchange Fellowship Program (Talent-Introduction Program) of China
源URL[http://ir.ia.ac.cn/handle/173211/54035]  
专题多模态人工智能系统全国重点实验室
通讯作者Shan, Caifeng
作者单位1.Nanjing Univ, Sch Intelligence Sci & Technol, Nanjing 210023, Peoples R China
2.Chinese Acad Sci CASIA, Inst Automat, Ctr Res Intelligent Percept & Comp CRIPAC, Natl Lab Pattern Recognit NLPR, Beijing 100190, Peoples R China
3.Shandong Univ Sci & Technol, Coll Elect Engn & Automat, Qingdao 266590, Peoples R China
推荐引用方式
GB/T 7714		 Wang, Yang,Huang, Yan,Shan, Caifeng,et al. Progressive Sub-Domain Information Mining for Single-Source Generalizable Gait Recognition[J]. IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,2023,18:4787-4799.
APA Wang, Yang,Huang, Yan,Shan, Caifeng,&Wang, Liang.(2023).Progressive Sub-Domain Information Mining for Single-Source Generalizable Gait Recognition.IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY,18,4787-4799.
MLA Wang, Yang,et al."Progressive Sub-Domain Information Mining for Single-Source Generalizable Gait Recognition".IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 18(2023):4787-4799.

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。