Cross-Domain Person Re-Identification Using Heterogeneous Convolutional Network
文献类型：期刊论文
| 作者 | Zhang, Zhong3; Wang, Yanan3; Liu, Shuang3; Xiao, Baihua2 ; Durrani, Tariq S.1
|
| 刊名 | IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
 |
| 出版日期 | 2022-03-01 |
| 卷号 | 32期号:3页码:1160-1171 |
| 关键词 | Correlation Feature extraction Couplings Convolution Training Cameras Loss measurement Cross-domain person re-identification graph convolution network dual graph convolution |
| ISSN号 | 1051-8215 |
| DOI | 10.1109/TCSVT.2021.3074745 |
| 通讯作者 | Liu, Shuang(shuangliu.tjnu@gmail.com) |
| 英文摘要 | Person re-identification (Re-ID) is a challenging task due to variations in pedestrian images, especially in cross-domain scenarios. The existing cross-domain person Re-ID approaches extract the feature from single pedestrian image, but they ignore the correlations among pedestrian images. In this paper, we propose Heterogeneous Convolutional Network (HCN) for cross-domain person Re-ID, which learns the appearance information of pedestrian images and the correlations among pedestrian images simultaneously. To this end, we first utilize Convolutional Neural Network (CNN) to extract the appearance features for pedestrian images. Then we construct a graph in the target dataset where the appearance features are treated as the nodes and the similarity represents the linkage between the nodes. Afterwards, we propose Dual Graph Convolution (DGConv) to explicitly learn the correlation information from the similar and dissimilar samples, which could avoid the over-smoothing caused by the fully connected graph. Furthermore, we design HCN as a multi-branch structure to mine the structural information of pedestrians. We conduct extensive evaluations for HCN on three datasets, i.e. Market-1501, DukeMTMC-reID and MSMT17, and the results demonstrate that HCN is superior to the state-of-the-art methods. |
| 资助项目 | National Natural Science Foundation of China[61711530240] ; Natural Science Foundation of Tianjin[20JCZDJC00180] ; Natural Science Foundation of Tianjin[19JCZDJC31500] ; Open Projects Program of National Laboratory of Pattern Recognition[202000002] ; Tianjin Higher Education Creative Team Funds Program |
| WOS研究方向 | Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:000766700400022 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 资助机构 | National Natural Science Foundation of China ; Natural Science Foundation of Tianjin ; Open Projects Program of National Laboratory of Pattern Recognition ; Tianjin Higher Education Creative Team Funds Program |
| 源URL | [http://ir.ia.ac.cn/handle/173211/48138]  |
| 专题 | 自动化研究所_复杂系统管理与控制国家重点实验室_影像分析与机器视觉团队 |
| 通讯作者 | Liu, Shuang |
| 作者单位 | 1.Univ Strathclyde, Dept Elect & Elect Engn, Glasgow G1 1XQ, Lanark, Scotland 2.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 3.Tianjin Normal Univ, Tianjin Key Lab Wireless Mobile Commun & Power Tr, Tianjin 300387, Peoples R China |
| 推荐引用方式 GB/T 7714 | Zhang, Zhong,Wang, Yanan,Liu, Shuang,et al. Cross-Domain Person Re-Identification Using Heterogeneous Convolutional Network[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2022,32(3):1160-1171. |
| APA | Zhang, Zhong,Wang, Yanan,Liu, Shuang,Xiao, Baihua,&Durrani, Tariq S..(2022).Cross-Domain Person Re-Identification Using Heterogeneous Convolutional Network.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,32(3),1160-1171. |
| MLA | Zhang, Zhong,et al."Cross-Domain Person Re-Identification Using Heterogeneous Convolutional Network".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 32.3(2022):1160-1171. |
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。