Asymmetric cross-view dictionary learning for person re-identification

Minyue Jiang, Yuan Yuan, Qi Wang

科研成果: 书/报告/会议事项章节会议稿件同行评审

4 引用 (Scopus)

摘要

Person re-identification is a critical yet challenging task in video surveillance which intends to match people over non-overlapping cameras. Most metric learning algorithms for person re-identification use symmetric matrix to project feature vectors into the same subspace to compute the similarity while ignoring the discrepancy between views. To solve this problem, we proposed an asymmetric cross-view matching algorithm with dictionary learning to alleviate the variations in human appearance across different views. Not only the views' dictionaries but also the persons' dictionary codes are constrained. Moreover, the 'between-class' and the 'within-class' distance are taken into consideration which makes the forming dictionary codes more robust and discriminative than the original feature vectors. The effectiveness of our approach is validated on the VIPeR and CUHK01 datasets. Experimental results show the proposed algorithm achieves compelling performance and asymmetric model plays an important role in the proposed approach.

源语言英语
主期刊名2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings
出版商Institute of Electrical and Electronics Engineers Inc.
1228-1232
页数5
ISBN(电子版)9781509041176
DOI
出版状态已出版 - 16 6月 2017
活动2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - New Orleans, 美国
期限: 5 3月 20179 3月 2017

出版系列

姓名ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN(印刷版)1520-6149

会议

会议2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017
国家/地区美国
New Orleans
时期5/03/179/03/17

指纹

探究 'Asymmetric cross-view dictionary learning for person re-identification' 的科研主题。它们共同构成独一无二的指纹。

引用此