{"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-re-identification-by-local-maximal","title":"Person Re-identification by Local Maximal Occurrence Representation and Metric Learning","arxiv_id":"1406.4216","date":"2014-06-17","proceeding":"CVPR 2015 6","authors":["Shengcai Liao","Yang Hu","Xiangyu Zhu","Stan Z. Li"],"abstract":"Person re-identification is an important technique towards automatic search\nof a person's presence in a surveillance video. Two fundamental problems are\ncritical for person re-identification, feature representation and metric\nlearning. An effective feature representation should be robust to illumination\nand viewpoint changes, and a discriminant metric should be learned to match\nvarious person images. In this paper, we propose an effective feature\nrepresentation called Local Maximal Occurrence (LOMO), and a subspace and\nmetric learning method called Cross-view Quadratic Discriminant Analysis\n(XQDA). The LOMO feature analyzes the horizontal occurrence of local features,\nand maximizes the occurrence to make a stable representation against viewpoint\nchanges. Besides, to handle illumination variations, we apply the Retinex\ntransform and a scale invariant texture operator. To learn a discriminant\nmetric, we propose to learn a discriminant low dimensional subspace by\ncross-view quadratic discriminant analysis, and simultaneously, a QDA metric is\nlearned on the derived subspace. We also present a practical computation method\nfor XQDA, as well as its regularization. Experiments on four challenging person\nre-identification databases, VIPeR, QMUL GRID, CUHK Campus, and CUHK03, show\nthat the proposed method improves the state-of-the-art rank-1 identification\nrates by 2.2%, 4.88%, 28.91%, and 31.55% on the four databases, respectively.","url_abs":"http://arxiv.org/abs/1406.4216v2","url_pdf":"http://arxiv.org/pdf/1406.4216v2.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-re-identification-by-local-maximal","repo_url":"https://github.com/zhunzhong07/person-re-ranking","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"metric-learning","task_name":"Metric Learning"},{"task_slug":"person-re-identification","task_name":"Person Re-Identification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/person-re-identification-on-dukemtmc-reid","task":"Person Re-Identification","dataset":"DukeMTMC-reID","model":"LOMO + XQDA","rank_in_archive_order":92,"of":94,"metrics":{"Rank-1":"30.75","mAP":"17.04"},"uses_additional_data":false},{"leaderboard":"/sota/person-re-identification-on-market-1501","task":"Person Re-Identification","dataset":"Market-1501","model":"LOMO + XQDA","rank_in_archive_order":124,"of":135,"metrics":{"Rank-1":"43.79","mAP":"22.22"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}