{"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/making-higher-order-mot-scalable-an-efficient","title":"Making Higher Order MOT Scalable: An Efficient Approximate Solver for Lifted Disjoint Paths","arxiv_id":"2108.10606","date":"2021-08-24","proceeding":"ICCV 2021 10","authors":["Andrea Hornakova","Timo Kaiser","Paul Swoboda","Michal Rolinek","Bodo Rosenhahn","Roberto Henschel"],"abstract":"We present an efficient approximate message passing solver for the lifted disjoint paths problem (LDP), a natural but NP-hard model for multiple object tracking (MOT). Our tracker scales to very large instances that come from long and crowded MOT sequences. Our approximate solver enables us to process the MOT15/16/17 benchmarks without sacrificing solution quality and allows for solving MOT20, which has been out of reach up to now for LDP solvers due to its size and complexity. On all these four standard MOT benchmarks we achieve performance comparable or better than current state-of-the-art methods including a tracker based on an optimal LDP solver.","url_abs":"https://arxiv.org/abs/2108.10606v1","url_pdf":"https://arxiv.org/pdf/2108.10606v1.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":"making-higher-order-mot-scalable-an-efficient","repo_url":"https://github.com/timok93/aplift","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"making-higher-order-mot-scalable-an-efficient","repo_url":"https://github.com/LPMP/LPMP","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"multiple-object-tracking","task_name":"Multiple Object Tracking"},{"task_slug":"object-tracking","task_name":"Object Tracking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2108.10606","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}