Learning disentangled representation implicitly via transformer for occluded person re-identification

Person re-IDentification (re-ID) under various occlusions has been a long-standing challenge as person images with different types of occlusions often suffer from misalignment in image matching and ranking. Most existing methods tackle this challenge by aligning spatial features of body parts accord...

ver descrição completa

Detalhes bibliográficos
Principais autores: Jia, Mengxi, Cheng, Xinhua, Lu, Shijian, Zhang, Jian
Outros Autores: School of Computer Science and Engineering
Formato: Journal Article
Idioma:English
Publicado em: 2022
Assuntos:
Acesso em linha:https://hdl.handle.net/10356/162960