{"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/mots-multi-object-tracking-and-segmentation","title":"MOTS: Multi-Object Tracking and Segmentation","arxiv_id":"1902.03604","date":"2019-02-10","proceeding":"CVPR 2019 6","authors":["Paul Voigtlaender","Michael Krause","Aljosa Osep","Jonathon Luiten","Berin Balachandar Gnana Sekar","Andreas Geiger","Bastian Leibe"],"abstract":"This paper extends the popular task of multi-object tracking to multi-object\ntracking and segmentation (MOTS). Towards this goal, we create dense\npixel-level annotations for two existing tracking datasets using a\nsemi-automatic annotation procedure. Our new annotations comprise 65,213 pixel\nmasks for 977 distinct objects (cars and pedestrians) in 10,870 video frames.\nFor evaluation, we extend existing multi-object tracking metrics to this new\ntask. Moreover, we propose a new baseline method which jointly addresses\ndetection, tracking, and segmentation with a single convolutional network. We\ndemonstrate the value of our datasets by achieving improvements in performance\nwhen training on MOTS annotations. We believe that our datasets, metrics and\nbaseline will become a valuable resource towards developing multi-object\ntracking approaches that go beyond 2D bounding boxes. We make our annotations,\ncode, and models available at https://www.vision.rwth-aachen.de/page/mots.","url_abs":"http://arxiv.org/abs/1902.03604v2","url_pdf":"http://arxiv.org/pdf/1902.03604v2.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":"multi-object-tracking","task_name":"Multi-Object Tracking"},{"task_slug":"multi-object-tracking-and-segmentation","task_name":"Multi-Object Tracking and Segmentation"},{"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":"segmentation","task_name":"Segmentation"}],"methods":[],"datasets_introduced":[{"slug":"kitti-mots","name":"KITTI MOTS","full_name":"KITTI Multi-Object Tracking and Segmentation (MOTS) Evaluation"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/multi-object-tracking-on-mots20","task":"Multi-Object Tracking","dataset":"MOTS20","model":"Track R-CNN","rank_in_archive_order":6,"of":6,"metrics":{"IDF1":"42.4","sMOTSA":"40.6"},"uses_additional_data":false},{"leaderboard":"/sota/multiple-object-tracking-on-kitti-test-online","task":"Multiple Object Tracking","dataset":"KITTI Test (Online Methods)","model":"MOSTFusion","rank_in_archive_order":21,"of":34,"metrics":{"MOTA":"84.83"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.03604","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}