2022/04/07 by Jiale Cao, Cao, Jiale, Yanwei Pang +11 · 4 citations
Computer Science · Engineering · #Algorithm #Artificial intelligence #Benchmark (surveying) #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Decoding methods #Discriminative model #Encoder #Encoding (memory) #Engineering #FOS: Computer and information sciences #Gait Recognition and Analysis #IoT and GPS-based Vehicle Safety Systems #Pattern recognition (psychology) #Transformer #Video Surveillance and Tracking Methods #cs.CV
paper · pdf · doi:10.48550/arxiv.2204.03340
published in arXiv (Cornell University) (Cornell University) · CVPR2022, Code: https://github.com/JialeCao001/PSTR
arxiv created 2022/04/07 · openalex publication_date 2022/04/07 · arxiv updated 2022/04/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We propose a novel one-step transformer-based person search framework, PSTR, that jointly performs person detection and re-identification (re-id) in a single architecture. PSTR comprises a person search-specialized (PSS) module that contains a detection encoder-decoder for person detection along with a discriminative re-id decoder for person re-id. The discriminative re-id decoder utilizes a multi-level supervision scheme with a shared decoder for discriminative re-id feature learning and also comprises a part attention block to encode relationship between different parts of a person. We further introduce a simple multi-scale scheme to support re-id across person instances at different scales. PSTR jointly achieves the diverse objectives of object-level recognition (detection) and instance-level matching (re-id). To the best of our knowledge, we are the first to propose an end-to-end one-step transformer-based person search framework. Experiments are performed on two popular benchmarks: CUHK-SYSU and PRW. Our extensive ablations reveal the merits of the proposed contributions. Further, the proposed PSTR sets a new state-of-the-art on both benchmarks. On the challenging PRW benchmark, PSTR achieves a mean average precision (mAP) score of 56.5%. The source code is available at \urlhttps://github.com/JialeCao001/PSTR.