Title
Adversarial Metric Attack and Defense for Person Re-identification.
Abstract
Person re-identification (re-ID) has attracted much attention recently due to its great importance in video surveillance. In general, distance metrics used to identify two person images are expected to be robust under various appearance changes. However, our work observes the extreme vulnerability of existing distance metrics to adversarial examples, generated by simply adding human-imperceptible ...
Year
DOI
Venue
2021
10.1109/TPAMI.2020.3031625
IEEE Transactions on Pattern Analysis and Machine Intelligence
Keywords
DocType
Volume
Training,Probes,Perturbation methods,Loss measurement,Video surveillance,Testing
Journal
43
Issue
ISSN
Citations 
6
0162-8828
2
PageRank 
References 
Authors
0.54
5
5
Name
Order
Citations
PageRank
Song Bai153333.91
Yingwei Li276.35
Yuyin Zhou39710.94
Qizhu Li491.66
Philip H. S. Torr59140636.18