SAHSR: Semantic Alignment and Hard-Sample Retraining Framework for Cross-Modal Person Re-Identification

March 2025 Jingchen Ni*, Keyu Lyu*, Yu Guo, Chun Yuan ICME 2025, Oral (CCF-B)
SAHSR: Semantic Alignment and Hard-Sample Retraining Framework for Cross-Modal Person Re-Identification

Overview

As the project lead and first author, I proposed the SAHSR framework to address key challenges in Visible-Infrared Person Re-Identification (VI-ReID), including semantic mismatch and hard-sample discrimination. A patent application for the related work is in progress.