<ul><li>The main challenge in the Visible-Infrared Person Re-Identification (VI-ReID) task lies in how to extract discriminative features from different modalities for matching purposes.</li><li>A Multi-scale Semantic Correlation Mining network (MSCMNet) is proposed to comprehensively exploit semantic features at multiple scales and simultaneously reduce modality information loss during feature extraction.</li><li>The proposed MSCMNet includes three novel components: Multi-scale Information Correlation Mining Block (MIMB), quadruple-stream feature extractor (QFE), and Quadruple Center Triplet Loss (QCT).</li><li>Extensive experiments on various datasets show that MSCMNet achieves high accuracy in Visible-Infrared Person Re-Identification.</li></ul>

MSCMNet: Multi-scale Semantic Correlation Mining for Visible-Infrared Person Re-Identification

Discover more