{"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/region-based-quality-estimation-network-for","title":"Region-based Quality Estimation Network for Large-scale Person Re-identification","arxiv_id":"1711.08766","date":"2017-11-23","proceeding":null,"authors":["Guanglu Song","Biao Leng","Yu Liu","Congrui Hetang","Shaofan Cai"],"abstract":"One of the major restrictions on the performance of video-based person re-id\nis partial noise caused by occlusion, blur and illumination. Since different\nspatial regions of a single frame have various quality, and the quality of the\nsame region also varies across frames in a tracklet, a good way to address the\nproblem is to effectively aggregate complementary information from all frames\nin a sequence, using better regions from other frames to compensate the\ninfluence of an image region with poor quality. To achieve this, we propose a\nnovel Region-based Quality Estimation Network (RQEN), in which an ingenious\ntraining mechanism enables the effective learning to extract the complementary\nregion-based information between different frames. Compared with other feature\nextraction methods, we achieved comparable results of 92.4%, 76.1% and 77.83%\non the PRID 2011, iLIDS-VID and MARS, respectively. In addition, to alleviate\nthe lack of clean large-scale person re-id datasets for the community, this\npaper also contributes a new high-quality dataset, named \"Labeled Pedestrian in\nthe Wild (LPW)\" which contains 7,694 tracklets with over 590,000 images.\nDespite its relatively large scale, the annotations also possess high\ncleanliness. Moreover, it's more challenging in the following aspects: the age\nof characters varies from childhood to elderhood; the postures of people are\ndiverse, including running and cycling in addition to the normal walking state.","url_abs":"http://arxiv.org/abs/1711.08766v2","url_pdf":"http://arxiv.org/pdf/1711.08766v2.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":[],"tasks":[{"task_slug":"large-scale-person-re-identification","task_name":"Large-Scale Person Re-Identification"},{"task_slug":"person-re-identification","task_name":"Person Re-Identification"}],"methods":[],"datasets_introduced":[{"slug":"lpw","name":"LPW","full_name":"Labeled Pedestrian in the Wild"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.08766","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}