Dual‐granularity feature fusion in visible‐infrared person re‐identification

Abstract Visible‐infrared person re‐identification (VI‐ReID) aims to recognize images of the same person captured in different modalities. Existing methods mainly focus on learning single‐granularity representations, which have limited discriminability and weak robustness. This paper proposes a nove...

Full description

Bibliographic Details

Published in:	IET Image Processing
Main Authors:	Shuang Cai, Shanmin Yang, Jing Hu, Xi Wu
Format:	Article
Language:	English
Published:	Wiley 2024-03-01
Subjects:	computer vision convolutional neural nets image retrieval pedestrians
Online Access:	https://doi.org/10.1049/ipr2.12999