CASIA OpenIR  > 类脑智能研究中心
Relevance Metric Learning for Person Re-Identification by Exploiting Global Similarities
Jiaxin Chen; Zhaoxiang Zhang; Yunhong Wang
Conference NameInternational Conference on Pattern Recognition
Source PublicationICPR 2014
Conference Date24-28 August 2014
Conference PlaceStockholm, Sweden
AbstractPerson 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.
KeywordList-wise Similarities Person Re-identification Metric Learning
Document Type会议论文
Corresponding AuthorZhaoxiang Zhang
Recommended Citation
GB/T 7714
Jiaxin Chen,Zhaoxiang Zhang,Yunhong Wang. Relevance Metric Learning for Person Re-Identification by Exploiting Global Similarities[C],2014.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Jiaxin Chen]'s Articles
[Zhaoxiang Zhang]'s Articles
[Yunhong Wang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Jiaxin Chen]'s Articles
[Zhaoxiang Zhang]'s Articles
[Yunhong Wang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Jiaxin Chen]'s Articles
[Zhaoxiang Zhang]'s Articles
[Yunhong Wang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.