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...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Zhixiong Wu, Tingxi Wen
Formato:	Artigo
Idioma:	Inglês
Publicado em:	MDPI AG 2022-09-01
coleção:	Applied Sciences
Assuntos:	deep learning feature space maximum deviation visible-infrared person re-identification
Acesso em linha:	https://www.mdpi.com/2076-3417/12/17/8792
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!