{"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/global-tracking-transformers","title":"Global Tracking Transformers","arxiv_id":"2203.13250","date":"2022-03-24","proceeding":"CVPR 2022 1","authors":["Xingyi Zhou","Tianwei Yin","Vladlen Koltun","Philipp Krähenbühl"],"abstract":"We present a novel transformer-based architecture for global multi-object tracking. Our network takes a short sequence of frames as input and produces global trajectories for all objects. The core component is a global tracking transformer that operates on objects from all frames in the sequence. The transformer encodes object features from all frames, and uses trajectory queries to group them into trajectories. The trajectory queries are object features from a single frame and naturally produce unique trajectories. Our global tracking transformer does not require intermediate pairwise grouping or combinatorial association, and can be jointly trained with an object detector. It achieves competitive performance on the popular MOT17 benchmark, with 75.3 MOTA and 59.1 HOTA. More importantly, our framework seamlessly integrates into state-of-the-art large-vocabulary detectors to track any objects. Experiments on the challenging TAO dataset show that our framework consistently improves upon baselines that are based on pairwise association, outperforming published works by a significant 7.7 tracking mAP. Code is available at https://github.com/xingyizhou/GTR.","url_abs":"https://arxiv.org/abs/2203.13250v2","url_pdf":"https://arxiv.org/pdf/2203.13250v2.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":"global-tracking-transformers","repo_url":"https://github.com/xingyizhou/GTR","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"multi-object-tracking","task_name":"Multi-Object Tracking"},{"task_slug":"object","task_name":"Object"},{"task_slug":"object-tracking","task_name":"Object Tracking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/multi-object-tracking-on-mot17","task":"Multi-Object Tracking","dataset":"MOT17","model":"GTR","rank_in_archive_order":26,"of":48,"metrics":{"HOTA":"59.1","IDF1":"71.5","MOTA":"75.3"},"uses_additional_data":false},{"leaderboard":"/sota/multi-object-tracking-on-sportsmot","task":"Multi-Object Tracking","dataset":"SportsMOT","model":"GTR","rank_in_archive_order":21,"of":22,"metrics":{"AssA":"45.9","DetA":"64.8","HOTA":"54.5","IDF1":"55.8","MOTA":"67.9"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.13250","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.13250"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/xingyizhou/GTR","reach":null}],"summary":{"ran":4,"unverified":1},"by_repo_kind":{"official":{"samples":5,"ran":4,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":5,"samples":[{"code_sha256_prefix":"42d37be3727e131a","entry":"TransformerDecoder","repo":"xingyizhou/GTR","repo_kind":"official","path":"gtr/modeling/roi_heads/transformer.py","file_url":"https://github.com/xingyizhou/GTR/blob/HEAD/gtr/modeling/roi_heads/transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"42d37be3727e131a"}},{"code_sha256_prefix":"c7d6e9384aadf1a8","entry":"TransformerDecoderLayer","repo":"xingyizhou/GTR","repo_kind":"official","path":"gtr/modeling/roi_heads/transformer.py","file_url":"https://github.com/xingyizhou/GTR/blob/HEAD/gtr/modeling/roi_heads/transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c7d6e9384aadf1a8"}},{"code_sha256_prefix":"4e67c0682b37e2b1","entry":"TransformerEncoder","repo":"xingyizhou/GTR","repo_kind":"official","path":"gtr/modeling/roi_heads/transformer.py","file_url":"https://github.com/xingyizhou/GTR/blob/HEAD/gtr/modeling/roi_heads/transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4e67c0682b37e2b1"}},{"code_sha256_prefix":"6f47261ee5162e04","entry":"TransformerEncoderLayer","repo":"xingyizhou/GTR","repo_kind":"official","path":"gtr/modeling/roi_heads/transformer.py","file_url":"https://github.com/xingyizhou/GTR/blob/HEAD/gtr/modeling/roi_heads/transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6f47261ee5162e04"}},{"code_sha256_prefix":"4b5b8cd244701776","entry":"Transformer","repo":"xingyizhou/GTR","repo_kind":"official","path":"gtr/modeling/roi_heads/transformer.py","file_url":"https://github.com/xingyizhou/GTR/blob/HEAD/gtr/modeling/roi_heads/transformer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4b5b8cd244701776"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}