{"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/beta-r-cnn-looking-into-pedestrian-detection-1","title":"Beta R-CNN: Looking into Pedestrian Detection from Another Perspective","arxiv_id":"2210.12758","date":"2022-10-23","proceeding":"NeurIPS 2020 12","authors":["Zixuan Xu","Banghuai Li","Ye Yuan","Anhong Dang"],"abstract":"Recently significant progress has been made in pedestrian detection, but it remains challenging to achieve high performance in occluded and crowded scenes. It could be attributed mostly to the widely used representation of pedestrians, i.e., 2D axis-aligned bounding box, which just describes the approximate location and size of the object. Bounding box models the object as a uniform distribution within the boundary, making pedestrians indistinguishable in occluded and crowded scenes due to much noise. To eliminate the problem, we propose a novel representation based on 2D beta distribution, named Beta Representation. It pictures a pedestrian by explicitly constructing the relationship between full-body and visible boxes, and emphasizes the center of visual mass by assigning different probability values to pixels. As a result, Beta Representation is much better for distinguishing highly-overlapped instances in crowded scenes with a new NMS strategy named BetaNMS. What's more, to fully exploit Beta Representation, a novel pipeline Beta R-CNN equipped with BetaHead and BetaMask is proposed, leading to high detection performance in occluded and crowded scenes.","url_abs":"https://arxiv.org/abs/2210.12758v1","url_pdf":"https://arxiv.org/pdf/2210.12758v1.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/object-detection-on-crowdhuman-full-body","task":"Object Detection","dataset":"CrowdHuman (full body)","model":"Beta R-CNN","rank_in_archive_order":12,"of":19,"metrics":{"AP":"89.6","mMR":"40.3"},"uses_additional_data":false},{"leaderboard":"/sota/pedestrian-detection-on-citypersons","task":"Pedestrian Detection","dataset":"CityPersons","model":"Beta R-CNN","rank_in_archive_order":11,"of":22,"metrics":{"Bare MR^-2":"6.4","Heavy MR^-2":"47.1","Partial MR^-2":"10.3","Reasonable MR^-2":"10.6"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2210.12758","atlas_url":"https://app.syntology.ai/?focus=2210.12758","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}