Dual-Edged Homogeneous-Modality Similarity: Towards Visible-Infrared Modality-Incomplete Person Re-Identification with Modality Adaptive Matching
The Modality Adaptive Matching Transformer (MAMT) is proposed, which employs a Divergence Transformer Module (DTM) and a Shared Transformer Module (STM) to extract modality-specific and modality-shared features, respectively, and dynamically fuses features according to the query-gallery modality relationship, enabling...