DPM++: Dynamic Masked Metric Learning for Occluded Person Re-identification 事件

DPM++: Dynamic Masked Metric Learning for Occluded Person Re-identification arXiv:2605.06637v2 Announce Type: replace Abstract: Although person re-identification has made impressive progress, occlusion caused by obstacles remains an unsettled issue in real applications. The difficulty lies in the mismatch between incomplete occluded samples and holistic identity representations. Severe occlusion removes discriminative body cues and introduces interference from background clutter and occluders,