{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/pstr-end-to-end-one-step-person-search-with","title":"PSTR: End-to-End One-Step Person Search With Transformers","arxiv_id":"2204.03340","date":"2022-04-07","proceeding":"CVPR 2022 1","authors":["Jiale Cao","Yanwei Pang","Rao Muhammad Anwer","Hisham Cholakkal","Jin Xie","Mubarak Shah","Fahad Shahbaz Khan"],"abstract":"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 \\url{https://github.com/JialeCao001/PSTR}.","url_abs":"https://arxiv.org/abs/2204.03340v1","url_pdf":"https://arxiv.org/pdf/2204.03340v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"pstr-end-to-end-one-step-person-search-with","repo_url":"https://github.com/jialecao001/pstr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"human-detection","task_name":"Human Detection"},{"task_slug":"person-search","task_name":"Person Search"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2204.03340","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}