Affordable Access

deepdyve-link
Publisher Website

End-to-End Comparative Attention Networks for Person Re-identification.

Authors
  • Liu, Hao
  • Feng, Jiashi
  • Qi, Meibin
  • Jiang, Jianguo
  • Yan, Shuicheng
Type
Published Article
Journal
IEEE Transactions on Image Processing
Publisher
Institute of Electrical and Electronics Engineers
Publication Date
May 03, 2017
Identifiers
DOI: 10.1109/TIP.2017.2700762
PMID: 28475058
Source
Medline
License
Unknown

Abstract

Person re-identification across disjoint camera views has been widely applied in video surveillance yet it is still a challenging problem. One of the major challenges lies in the lack of spatial and temporal cues, which makes it difficult to deal with large variations of lighting conditions, viewing angles, body poses and occlusions. Recently, several deep learning based person re-identification approaches have been proposed and achieved remarkable performance. However, most of those approaches extract discriminative features from the whole frame at one glimpse without differentiating various parts of the persons to identify. It is essentially important to examine multiple highly discriminative local regions of the person images in details through multiple glimpses for dealing with the large appearance variance.

Report this publication

Statistics

Seen <100 times