Towards Fully Decoupled End-to-End Person Search

arXiv:2309.04967v3 Announce Type: replace
Abstract: End-to-end person search aims to jointly detect and re-identify a target person in raw scene images with a unified model. The detection task unifies all persons while the re-id task discriminates different identities, resulting in conflict optimal objectives. Existing works proposed to decouple end-to-end person search to alleviate such conflict. Yet these methods are still sub-optimal on one or two of the sub-tasks due to their partially decoupled models, which limits the overall person search …

abstract arxiv conflict cs.cv detection identify images person raw search type unified model