Minimizing Maximum Feature Space Deviation for Visible-Infrared Person Re-Identification

Minimizing Maximum Feature Space Deviation for Visible-Infrared Person Re-Identification

Visible-infrared person re-identification (VIPR) has great potential for intelligent video surveillance systems at night, but it is challenging due to the huge modal gap between visible and infrared modalities. For that, this paper proposes a minimizing maximum feature space deviation (MMFSD) method...

Full description

Bibliographic Details
Main Authors: Zhixiong Wu, Tingxi Wen
Format: Article
Language:English
Published: MDPI AG 2022-09-01
Series:Applied Sciences
Subjects:
deep learning
feature space maximum deviation
visible-infrared person re-identification
Online Access:https://www.mdpi.com/2076-3417/12/17/8792

Internet

https://www.mdpi.com/2076-3417/12/17/8792

Similar Items