Towards Anytime Retrieval: A Benchmark for Anytime Person Re-Identification 事件

Towards Anytime Retrieval: A Benchmark for Anytime Person Re-Identification arXiv:2509.16635v2 Announce Type: replace Abstract: In real applications, person re-identification (ReID) is expected to retrieve the target person at any time, including both daytime and nighttime, ranging from short-term to long-term. However, existing ReID tasks and datasets can not meet this requirement, as they are constrained by available time and only provide training and evaluation for specific scenarios. Theref