Adversarial Erasing Attention for Person Re-Identification in Camera Networks Under Complex Environments

Adversarial Erasing Attention for Person Re-Identification in Camera Networks Under Complex Environments

Person re-identification (Re-ID) in camera networks under complex environments has achieved promising performance using deep feature representations. However, most approaches usually ignore to learn features from non-salient parts of pedestrian, which results in an incomplete pedestrian representati...

Full description

Bibliographic Details
Main Authors: Shuang Liu, Xiaolong Hao, Ronghua Zhang, Zhong Zhang, Tariq S. Durrani
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Person re-identification
dynamic strategy
adversarial learning
Online Access:https://ieeexplore.ieee.org/document/9043556/

Internet

https://ieeexplore.ieee.org/document/9043556/

Similar Items