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. 复杂系统管理与控制国家重点实验室
Self-attention mechanism in person re-identification models

文献类型：期刊论文

作者Chen, Wenbai1; Lu, Yue1; Ma, Hang1; Chen, Qili1; Wu, Xibao1; Wu, Peiliang2,3
刊名MULTIMEDIA TOOLS AND APPLICATIONS
出版日期2021-02-17
页码19
关键词Person re-identification Deep neural network Self-attention Computer vision
ISSN号1380-7501
DOI10.1007/s11042-020-10494-4
通讯作者Chen, Wenbai(chenwb@bistu.edu.cn)
英文摘要In recent years, person re-identification based on video has become a hot topic in the field of person re-identification. The self-attention mechanism can improve the ability of deep neural networks in computer vision tasks such as image classification, image segmentation and natural language processing tasks. In order to verify whether the self-attention can improve the performance or not in person re-identification tasks, this paper applies two self-attention mechanisms, non-local attention and recurrent criss-cross attention to person re-identification model, and experiments are conducted on Market-1501, DukeMTMC-reID and MSMT17 person re-identification datasets. The results show that the self-attention mechanism can improve the accuracy of the person re-identification model. The accuracy is higher when the self-attention module is inserted into the convolutional layers of the re-identification network.
WOS关键词NETWORK
资助项目National Key R&D Program of China[2018YFB1308300] ; China Postdoctoral Science Foundation[2018M631620] ; CrossTraining Plan of High Level Talents and Training Project of Beijing ; Beijing Natural Science Foundation[4202026]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:000618948700012
出版者SPRINGER
资助机构National Key R&D Program of China ; China Postdoctoral Science Foundation ; CrossTraining Plan of High Level Talents and Training Project of Beijing ; Beijing Natural Science Foundation
源URL[http://ir.ia.ac.cn/handle/173211/43210]  
专题自动化研究所_复杂系统管理与控制国家重点实验室
通讯作者Chen, Wenbai
作者单位1.Beijing Informat Sci & Technol Univ, Sch Automat, Beijing 100192, Peoples R China
2.Yanshan Univ, Sch Informat & Engn, Qinhuangdao 066004, Hebei, Peoples R China
3.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Chen, Wenbai,Lu, Yue,Ma, Hang,et al. Self-attention mechanism in person re-identification models[J]. MULTIMEDIA TOOLS AND APPLICATIONS,2021:19.
APA Chen, Wenbai,Lu, Yue,Ma, Hang,Chen, Qili,Wu, Xibao,&Wu, Peiliang.(2021).Self-attention mechanism in person re-identification models.MULTIMEDIA TOOLS AND APPLICATIONS,19.
MLA Chen, Wenbai,et al."Self-attention mechanism in person re-identification models".MULTIMEDIA TOOLS AND APPLICATIONS (2021):19.

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。