Deeply-Learned Spatial Alignment for Person Re-Identification

Deeply-Learned Spatial Alignment for Person Re-Identification

A large class of Person Re-identification (ReID) approaches identify pedestrians with the TriHard loss. Though the TriHard loss is a robust ReID method, pose variance and viewpoint in pedestrians constrain the performance. To address this problem, we introduce a spatial transformer network (STN) to...

Full description

Bibliographic Details
Main Authors: Dongyue Chen, Peng Chen, Xiaosheng Yu, Mengjiao Cao, Tong Jia
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Access
Subjects:
ReID
STN
alignment
TriHard
pose variance
viewpoint
Online Access:https://ieeexplore.ieee.org/document/8856191/

Internet

https://ieeexplore.ieee.org/document/8856191/

Similar Items