{"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/occluded-person-re-identification","title":"Occluded Person Re-identification","arxiv_id":"1804.02792","date":"2018-04-09","proceeding":null,"authors":["Jiaxuan Zhuo","Zeyu Chen","Jian-Huang Lai","Guangcong Wang"],"abstract":"Person re-identification (re-id) suffers from a serious occlusion problem\nwhen applied to crowded public places. In this paper, we propose to retrieve a\nfull-body person image by using a person image with occlusions. This differs\nsignificantly from the conventional person re-id problem where it is assumed\nthat person images are detected without any occlusion. We thus call this new\nproblem the occluded person re-identitification. To address this new problem,\nwe propose a novel Attention Framework of Person Body (AFPB) based on deep\nlearning, consisting of 1) an Occlusion Simulator (OS) which automatically\ngenerates artificial occlusions for full-body person images, and 2) multi-task\nlosses that force the neural network not only to discriminate a person's\nidentity but also to determine whether a sample is from the occluded data\ndistribution or the full-body data distribution. Experiments on a new occluded\nperson re-id dataset and three existing benchmarks modified to include\nfull-body person images and occluded person images show the superiority of the\nproposed method.","url_abs":"http://arxiv.org/abs/1804.02792v3","url_pdf":"http://arxiv.org/pdf/1804.02792v3.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":"occluded-person-re-identification","task_name":"Occluded Person Re-Identification"},{"task_slug":"person-re-identification","task_name":"Person Re-Identification"}],"methods":[],"datasets_introduced":[{"slug":"occluded-reid","name":"Occluded REID","full_name":"Occluded REID"},{"slug":"p-dukemtmc-reid","name":"P-DukeMTMC-reID","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1804.02792","atlas_url":"https://app.syntology.ai/?focus=1804.02792","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}