AI RESEARCH
BIT: Matching-based Bi-directional Interaction Transformation Network for Visible-Infrared Person Re-Identification
arXiv CS.CV
•
ArXi:2603.14243v1 Announce Type: new Visible-Infrared Person Re-Identification (VI-ReID) is a challenging retrieval task due to the substantial modality gap between visible and infrared images. While existing methods attempt to bridge this gap by learning modality-invariant features within a shared embedding space, they often overlook the complex and implicit correlations between modalities. This limitation becomes severe under distribution shifts, where infrared samples are often far fewer than visible ones.