Context-aided unicity matching for person re-identification
文献类型：期刊论文
| 作者 | Cao, Min1 ; Ding, Cong1; Chen, Chen2; Peng, Silong2
|
| 刊名 | JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION
 |
| 出版日期 | 2024-03-01 |
| 卷号 | 99页码:10 |
| 关键词 | Person re-identification Unicity matching Contextual information Graph neural network |
| ISSN号 | 1047-3203 |
| DOI | 10.1016/j.jvcir.2024.104077 |
| 通讯作者 | Chen, Chen(chen.chen@ia.ac.cn) |
| 英文摘要 | Most existing person re -identification methods compute the matching relations between person images based on the similarity ranking. It lacks the global viewpoint and context consideration, inevitably leading to ambiguous matching results and sub-optimal performance. Based on a natural assumption that images belonging to the same identity should not match with images belonging to different identities across views, called the unicity of person matching on the identity level, we propose an end -to -end person unicity matching architecture to learn and refine the person matching relations. We first employ the image samples' context in feature space to generate the initial soft matchings using graph neural networks, and then utilize the samples' global context to refine the soft matchings and reach the matching unicity by bipartite graph matching. Considering real -world applications, we further develop a fast algorithm without losing performance. Experimental results on five public benchmarks show the superiority of the proposed method. |
| WOS关键词 | ALGORITHM ; NETWORK |
| 资助项目 | National Science Foundation of China[NSFC 61906194] ; National Science Foundation of China[NSFC 62002252] ; Collaborative Innovation Center of Novel Software Technology and Industrialization ; Liaoning Collaboration Innovation Center For CSLE, China |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:001185772500001 |
| 出版者 | ACADEMIC PRESS INC ELSEVIER SCIENCE |
| 资助机构 | National Science Foundation of China ; Collaborative Innovation Center of Novel Software Technology and Industrialization ; Liaoning Collaboration Innovation Center For CSLE, China |
| 源URL | [http://ir.ia.ac.cn/handle/173211/58004]  |
| 专题 | 自动化研究所_智能制造技术与系统研究中心_多维数据分析团队 |
| 通讯作者 | Chen, Chen |
| 作者单位 | 1.Soochow Univ, Sch Comp Sci & Technol, Suzhou 215006, Peoples R China 2.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China |
| 推荐引用方式 GB/T 7714 | Cao, Min,Ding, Cong,Chen, Chen,et al. Context-aided unicity matching for person re-identification[J]. JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION,2024,99:10. |
| APA | Cao, Min,Ding, Cong,Chen, Chen,&Peng, Silong.(2024).Context-aided unicity matching for person re-identification.JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION,99,10. |
| MLA | Cao, Min,et al."Context-aided unicity matching for person re-identification".JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION 99(2024):10. |
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。