{"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/lifted-disjoint-paths-with-application-in-1","title":"Lifted Disjoint Paths with Application in Multiple Object Tracking","arxiv_id":"2006.14550","date":"2020-06-25","proceeding":"ICML 2020 1","authors":["Andrea Hornakova","Roberto Henschel","Bodo Rosenhahn","Paul Swoboda"],"abstract":"We present an extension to the disjoint paths problem in which additional \\emph{lifted} edges are introduced to provide path connectivity priors. We call the resulting optimization problem the lifted disjoint paths problem. We show that this problem is NP-hard by reduction from integer multicommodity flow and 3-SAT. To enable practical global optimization, we propose several classes of linear inequalities that produce a high-quality LP-relaxation. Additionally, we propose efficient cutting plane algorithms for separating the proposed linear inequalities. The lifted disjoint path problem is a natural model for multiple object tracking and allows an elegant mathematical formulation for long range temporal interactions. Lifted edges help to prevent id switches and to re-identify persons. Our lifted disjoint paths tracker achieves nearly optimal assignments with respect to input detections. As a consequence, it leads on all three main benchmarks of the MOT challenge, improving significantly over state-of-the-art.","url_abs":"https://arxiv.org/abs/2006.14550v1","url_pdf":"https://arxiv.org/pdf/2006.14550v1.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":"lifted-disjoint-paths-with-application-in-1","repo_url":"https://github.com/AndreaHor/LifT_Solver","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"multiple-object-tracking","task_name":"Multiple Object Tracking"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-tracking","task_name":"Object Tracking"},{"task_slug":"global-optimization","task_name":"global-optimization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/multi-object-tracking-on-2d-mot-2015","task":"Multi-Object Tracking","dataset":"2D MOT 2015","model":"Lif_T","rank_in_archive_order":2,"of":4,"metrics":{"IDF1":"60.0","MOTA":"52.5"},"uses_additional_data":false},{"leaderboard":"/sota/multi-object-tracking-on-mot16","task":"Multi-Object Tracking","dataset":"MOT16","model":"Lif_T","rank_in_archive_order":16,"of":24,"metrics":{"IDF1":"64.7","MOTA":"61.3"},"uses_additional_data":false},{"leaderboard":"/sota/multi-object-tracking-on-mot17","task":"Multi-Object Tracking","dataset":"MOT17","model":"Lif_T","rank_in_archive_order":41,"of":48,"metrics":{"IDF1":"65.6","MOTA":"60.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2006.14550","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}