Relevance Metric Learning for Person Re-Identification by Exploiting Listwise Similarities

CASIA OpenIR > 智能感知与计算研究中心

	Relevance Metric Learning for Person Re-Identification by Exploiting Listwise Similarities
	Jiaxin Chen; Zhaoxiang Zhang; Yunhong Wang
发表期刊	IEEE Transactions on Image Processing
	2015-08-07
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	智能感知与计算研究中心
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.