2 papers
cs.CV2024
CLIP-Driven Semantic Discovery Network for Visible-Infrared Person Re-Identification
Xiaoyan Yu, Neng Dong, Liehuang Zhu +2
Visible-infrared person re-identification (VIReID) primarily deals with matching identities across person images from different modalities. Due to the modality gap between visible…
cs.CV2023
Learning Comprehensive Representations with Richer Self for Text-to-Image Person Re-Identification
Shuanglin Yan, Neng Dong, Jun Liu +2
Text-to-image person re-identification (TIReID) retrieves pedestrian images of the same identity based on a query text. However, existing methods for TIReID typically treat it as a…