Bidirectional Interaction Network for Person Re-Identification | |
Chen, Xiumei; Zheng, Xiangtao; Lu, Xiaoqiang | |
作者部门 | 光谱成像技术研究室 |
2021 | |
发表期刊 | IEEE Transactions on Image Processing |
ISSN | 10577149;19410042 |
卷号 | 30页码:1935-1948 |
产权排序 | 1 |
摘要 | Person re-identification (ReID) task aims to retrieve the same person across multiple spatially disjoint camera views. Due to huge image changes caused by various factors such as posture variation and illumination transformation, images of different persons may share the more similar appearances than images of the same one. Learning discriminative representations to distinguish details of different persons is significant for person ReID. Many existing methods learn discriminative representations resorting to a human body part location branch which requires cumbersome expert human annotations or complex network designs. In this article, a novel bidirectional interaction network is proposed to explore discriminative representations for person ReID without any human body part detection. The proposed method regards multiple convolutional features as responses to various body part properties and exploits the inter-layer interaction to mine discriminative representations for person identities. Firstly, an inter-layer bilinear pooling strategy is proposed to feasibly exploit the pairwise feature relations between two convolution layers. Secondly, to explore interaction of multiple layers, an effective bidirectional integration strategy consisting of two different multi-layer interaction processes is designed to aggregate bilinear pooling interaction of multiple convolution layers. The interaction of multiple layers is implemented in a layer-by-layer nesting policy to ensure the two interaction processes are different and complementary. Extensive experiments validate the superiority of the proposed method on four popular person ReID datasets including Market-1501, DukeMTMC-ReID, CUHK03-NP and MSMT17. Specifically, the proposed method achieves a rank-1 accuracy of 95.1% and 88.2% on Market-1501 and DukeMTMC-ReID, respectively. © 1992-2012 IEEE. |
关键词 | Person re-identification convolutional neural network bidirectional integration bilinear pooling |
DOI | 10.1109/TIP.2021.3049943 |
收录类别 | SCI ; EI |
语种 | 英语 |
WOS记录号 | WOS:000611077900010 |
出版者 | Institute of Electrical and Electronics Engineers Inc. |
EI入藏号 | 20210409805908 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.opt.ac.cn/handle/181661/94264 |
专题 | 光谱成像技术研究室 |
作者单位 | CAS Key Laboratory of Spectral Imaging Technology, Xi'An Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi'an; 710119, China |
推荐引用方式 GB/T 7714 | Chen, Xiumei,Zheng, Xiangtao,Lu, Xiaoqiang. Bidirectional Interaction Network for Person Re-Identification[J]. IEEE Transactions on Image Processing,2021,30:1935-1948. |
APA | Chen, Xiumei,Zheng, Xiangtao,&Lu, Xiaoqiang.(2021).Bidirectional Interaction Network for Person Re-Identification.IEEE Transactions on Image Processing,30,1935-1948. |
MLA | Chen, Xiumei,et al."Bidirectional Interaction Network for Person Re-Identification".IEEE Transactions on Image Processing 30(2021):1935-1948. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Bidirectional Intera(2787KB) | 期刊论文 | 出版稿 | 限制开放 | CC BY-NC-SA | 请求全文 |
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。
修改评论