AI RESEARCH

Homogeneous and Heterogeneous Consistency progressive Re-ranking for Visible-Infrared Person Re-identification

arXiv CS.AI

ArXi:2603.16165v1 Announce Type: cross Visible-infrared person re-identification faces greater challenges than traditional person re-identification due to the significant differences between modalities. In particular, the differences between these modalities make effective matching even challenging, mainly because existing re-ranking algorithms cannot simultaneously address the intra-modal variations and inter-modal discrepancy in cross-modal person re-identification.