Cargando…

Vision Transformer with hierarchical structure and windows shifting for person re-identification

Extracting rich feature representations is a key challenge in person re-identification (Re-ID) tasks. However, traditional Convolutional Neural Networks (CNN) based methods could ignore a part of information when processing local regions of person images, which leads to incomplete feature extraction...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhang, Yinghua, Hou, Wei
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10313053/
https://www.ncbi.nlm.nih.gov/pubmed/37390091
http://dx.doi.org/10.1371/journal.pone.0287979