Deep Co-attention based Comparators For Relative Representation Learning in Person Re-identification

arXiv: Computer Vision and Pattern Recognition, Volume abs/1804.11027, 2018.

Cited by: 8|Bibtex|Views17|Links
EI

Abstract:

Person re-identification (re-ID) requires rapid, flexible yet discriminant representations to quickly generalize to unseen observations on-the-fly and recognize the same identity across disjoint camera views. Recent effective methods are developed in a pair-wise similarity learning system to detect a fixed set of features from distinct re...More

Code:

Data:

Your rating :
0

 

Tags
Comments