Search Results for author:
Found 1 papers, 0 papers with code
Multi-Memory Matching for Unsupervised Visible-Infrared Person Re-Identification
To associate cross-modality clustered pseudo-labels, we design a Multi-Memory Learning and Matching (MMLM) module, ensuring that optimization explicitly focuses on the nuances of individual perspectives and establishes reliable cross-modality correspondences.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
