{"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/transtrack-multiple-object-tracking-with","title":"TransTrack: Multiple Object Tracking with Transformer","arxiv_id":"2012.15460","date":"2020-12-31","proceeding":null,"authors":["Peize Sun","Jinkun Cao","Yi Jiang","Rufeng Zhang","Enze Xie","Zehuan Yuan","Changhu Wang","Ping Luo"],"abstract":"In this work, we propose TransTrack, a simple but efficient scheme to solve the multiple object tracking problems. TransTrack leverages the transformer architecture, which is an attention-based query-key mechanism. It applies object features from the previous frame as a query of the current frame and introduces a set of learned object queries to enable detecting new-coming objects. It builds up a novel joint-detection-and-tracking paradigm by accomplishing object detection and object association in a single shot, simplifying complicated multi-step settings in tracking-by-detection methods. On MOT17 and MOT20 benchmark, TransTrack achieves 74.5\\% and 64.5\\% MOTA, respectively, competitive to the state-of-the-art methods. We expect TransTrack to provide a novel perspective for multiple object tracking. The code is available at: \\url{https://github.com/PeizeSun/TransTrack}.","url_abs":"https://arxiv.org/abs/2012.15460v2","url_pdf":"https://arxiv.org/pdf/2012.15460v2.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":"transtrack-multiple-object-tracking-with","repo_url":"https://github.com/PeizeSun/TransTrack","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"transtrack-multiple-object-tracking-with","repo_url":"https://github.com/ligaripash/KWtQ-face-alignment","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"multi-object-tracking","task_name":"Multi-Object Tracking"},{"task_slug":"multiple-object-tracking","task_name":"Multiple Object Tracking"},{"task_slug":"multiple-object-tracking-with-transformer","task_name":"Multiple Object Tracking with Transformer"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-tracking","task_name":"Object Tracking"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/multi-object-tracking-on-dancetrack","task":"Multi-Object Tracking","dataset":"DanceTrack","model":"TransTrack","rank_in_archive_order":34,"of":37,"metrics":{"AssA":"27.5","DetA":"72.1","HOTA":"45.7","IDF1":"44.8","MOTA":"83.0"},"uses_additional_data":false},{"leaderboard":"/sota/multi-object-tracking-on-sportsmot","task":"Multi-Object Tracking","dataset":"SportsMOT","model":"TransTrack","rank_in_archive_order":15,"of":22,"metrics":{"AssA":"57.5","DetA":"82.7","HOTA":"68.9","IDF1":"71.5","MOTA":"92.6"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2012.15460","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}