CASIA OpenIR  > 类脑智能研究中心
Relevance Metric Learning for Person Re-Identification by Exploiting Listwise Similarities
Jiaxin Chen; Zhaoxiang Zhang; Yunhong Wang
2015-08-07
发表期刊IEEE Transactions on Image Processing
卷号24期号:12页码:4741-4755
摘要Person re-identification aims to match people across non-overlapping camera views, which is an important but challenging task in video surveillance. In order to obtain a robust metric for matching, metric learning has been introduced recently. Most existing works focus on seeking a Mahalanobis distance by employing sparse pairwise constraints, which utilize image pairs with the same person identity as positive samples, and select a small portion of those with different identities as negative samples. However, this training strategy has abandoned a large amount of discriminative information, and ignored the relative similarities. In this paper, we propose a novel relevance metric learning method with listwise constraints (RMLLCs) by adopting listwise similarities, which consist of the similarity list of each image with respect to all remaining images. By virtue of listwise similarities, RMLLC could capture all pairwise similarities, and consequently learn a more discriminative metric by enforcing the metric to conserve predefined similarity lists in a low-dimensional projection subspace. Despite the performance enhancement, RMLLC using predefined similarity lists fails to capture the relative relevance information, which is often unavailable in practice. To address this problem, we further introduce a rectification term to automatically exploit the relative similarities, and develop an efficient alternating iterative algorithm to jointly learn the optimal metric and the rectification term. Extensive experiments on four publicly available benchmarking data sets are carried out and demonstrate that the proposed method is significantly superior to the state-of-the-art approaches. The results also show that the introduction of the rectification term could further boost the performance of RMLLC.
关键词List-wise Similarities Person Re-identification Metric Learning
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/13210
专题类脑智能研究中心
通讯作者Zhaoxiang Zhang
推荐引用方式
GB/T 7714
Jiaxin Chen,Zhaoxiang Zhang,Yunhong Wang. Relevance Metric Learning for Person Re-Identification by Exploiting Listwise Similarities[J]. IEEE Transactions on Image Processing,2015,24(12):4741-4755.
APA Jiaxin Chen,Zhaoxiang Zhang,&Yunhong Wang.(2015).Relevance Metric Learning for Person Re-Identification by Exploiting Listwise Similarities.IEEE Transactions on Image Processing,24(12),4741-4755.
MLA Jiaxin Chen,et al."Relevance Metric Learning for Person Re-Identification by Exploiting Listwise Similarities".IEEE Transactions on Image Processing 24.12(2015):4741-4755.
条目包含的文件
条目无相关文件。
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Jiaxin Chen]的文章
[Zhaoxiang Zhang]的文章
[Yunhong Wang]的文章
百度学术
百度学术中相似的文章
[Jiaxin Chen]的文章
[Zhaoxiang Zhang]的文章
[Yunhong Wang]的文章
必应学术
必应学术中相似的文章
[Jiaxin Chen]的文章
[Zhaoxiang Zhang]的文章
[Yunhong Wang]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

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。