{"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/deep-occlusion-reasoning-for-multi-camera","title":"Deep Occlusion Reasoning for Multi-Camera Multi-Target Detection","arxiv_id":"1704.05775","date":"2017-04-19","proceeding":"ICCV 2017 10","authors":["Pierre Baqué","François Fleuret","Pascal Fua"],"abstract":"People detection in single 2D images has improved greatly in recent years.\nHowever, comparatively little of this progress has percolated into multi-camera\nmulti-people tracking algorithms, whose performance still degrades severely\nwhen scenes become very crowded. In this work, we introduce a new architecture\nthat combines Convolutional Neural Nets and Conditional Random Fields to\nexplicitly model those ambiguities. One of its key ingredients are high-order\nCRF terms that model potential occlusions and give our approach its robustness\neven when many people are present. Our model is trained end-to-end and we show\nthat it outperforms several state-of-art algorithms on challenging scenes.","url_abs":"http://arxiv.org/abs/1704.05775v2","url_pdf":"http://arxiv.org/pdf/1704.05775v2.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":"deep-occlusion-reasoning-for-multi-camera","repo_url":"https://github.com/pierrebaque/DeepOcclusion","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"deep-occlusion-reasoning-for-multi-camera","repo_url":"https://github.com/rickyHong/DeepOcclustion-repl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"multiview-detection","task_name":"Multiview Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/multiview-detection-on-multiviewx","task":"Multiview Detection","dataset":"MultiviewX","model":"Deep-Occulsion","rank_in_archive_order":9,"of":9,"metrics":{"MODA":"75.2","MODP":"54.7"},"uses_additional_data":false},{"leaderboard":"/sota/multiview-detection-on-wildtrack","task":"Multiview Detection","dataset":"Wildtrack","model":"Deep-Occlusion","rank_in_archive_order":10,"of":10,"metrics":{"MODA":"74.1","MODP":"53.8"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1704.05775","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}