{"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/person-search-with-natural-language","title":"Person Search with Natural Language Description","arxiv_id":"1702.05729","date":"2017-02-19","proceeding":"CVPR 2017 7","authors":["Shuang Li","Tong Xiao","Hongsheng Li","Bolei Zhou","Dayu Yue","Xiaogang Wang"],"abstract":"Searching persons in large-scale image databases with the query of natural\nlanguage description has important applications in video surveillance. Existing\nmethods mainly focused on searching persons with image-based or attribute-based\nqueries, which have major limitations for a practical usage. In this paper, we\nstudy the problem of person search with natural language description. Given the\ntextual description of a person, the algorithm of the person search is required\nto rank all the samples in the person database then retrieve the most relevant\nsample corresponding to the queried description. Since there is no person\ndataset or benchmark with textual description available, we collect a\nlarge-scale person description dataset with detailed natural language\nannotations and person samples from various sources, termed as CUHK Person\nDescription Dataset (CUHK-PEDES). A wide range of possible models and baselines\nhave been evaluated and compared on the person search benchmark. An Recurrent\nNeural Network with Gated Neural Attention mechanism (GNA-RNN) is proposed to\nestablish the state-of-the art performance on person search.","url_abs":"http://arxiv.org/abs/1702.05729v2","url_pdf":"http://arxiv.org/pdf/1702.05729v2.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":"person-search-with-natural-language","repo_url":"https://github.com/ShuangLI59/Person-Search-with-Natural-Language-Description","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"person-search","task_name":"Person Search"},{"task_slug":"nlp-based-person-retrival","task_name":"Text based Person Retrieval"}],"methods":[],"datasets_introduced":[{"slug":"cuhk-pedes","name":"CUHK-PEDES","full_name":"CUHK-PEDES"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1702.05729","atlas_url":"https://app.syntology.ai/?focus=1702.05729","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}