{"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/occlusion-aware-r-cnn-detecting-pedestrians","title":"Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd","arxiv_id":"1807.08407","date":"2018-07-23","proceeding":"ECCV 2018 9","authors":["Shifeng Zhang","Longyin Wen","Xiao Bian","Zhen Lei","Stan Z. Li"],"abstract":"Pedestrian detection in crowded scenes is a challenging problem since the\npedestrians often gather together and occlude each other. In this paper, we\npropose a new occlusion-aware R-CNN (OR-CNN) to improve the detection accuracy\nin the crowd. Specifically, we design a new aggregation loss to enforce\nproposals to be close and locate compactly to the corresponding objects.\nMeanwhile, we use a new part occlusion-aware region of interest (PORoI) pooling\nunit to replace the RoI pooling layer in order to integrate the prior structure\ninformation of human body with visibility prediction into the network to handle\nocclusion. Our detector is trained in an end-to-end fashion, which achieves\nstate-of-the-art results on three pedestrian detection datasets, i.e.,\nCityPersons, ETH, and INRIA, and performs on-pair with the state-of-the-arts on\nCaltech.","url_abs":"http://arxiv.org/abs/1807.08407v1","url_pdf":"http://arxiv.org/pdf/1807.08407v1.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":"pedestrian-detection","task_name":"Pedestrian Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/pedestrian-detection-on-caltech","task":"Pedestrian Detection","dataset":"Caltech","model":"OR-CNN + CityPersons dataset","rank_in_archive_order":10,"of":33,"metrics":{"Reasonable Miss Rate":"4.1"},"uses_additional_data":true},{"leaderboard":"/sota/pedestrian-detection-on-citypersons","task":"Pedestrian Detection","dataset":"CityPersons","model":"OR-CNN","rank_in_archive_order":16,"of":22,"metrics":{"Bare MR^-2":"6.7","Heavy MR^-2":"55.7","Partial MR^-2":"15.3","Reasonable MR^-2":"12.8"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.08407","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}