{"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/odtrack-online-dense-temporal-token-learning","title":"ODTrack: Online Dense Temporal Token Learning for Visual Tracking","arxiv_id":"2401.01686","date":"2024-01-03","proceeding":null,"authors":["Yaozong Zheng","Bineng Zhong","Qihua Liang","Zhiyi Mo","Shengping Zhang","Xianxian Li"],"abstract":"Online contextual reasoning and association across consecutive video frames are critical to perceive instances in visual tracking. However, most current top-performing trackers persistently lean on sparse temporal relationships between reference and search frames via an offline mode. Consequently, they can only interact independently within each image-pair and establish limited temporal correlations. To alleviate the above problem, we propose a simple, flexible and effective video-level tracking pipeline, named \\textbf{ODTrack}, which densely associates the contextual relationships of video frames in an online token propagation manner. ODTrack receives video frames of arbitrary length to capture the spatio-temporal trajectory relationships of an instance, and compresses the discrimination features (localization information) of a target into a token sequence to achieve frame-to-frame association. This new solution brings the following benefits: 1) the purified token sequences can serve as prompts for the inference in the next video frame, whereby past information is leveraged to guide future inference; 2) the complex online update strategies are effectively avoided by the iterative propagation of token sequences, and thus we can achieve more efficient model representation and computation. ODTrack achieves a new \\textit{SOTA} performance on seven benchmarks, while running at real-time speed. Code and models are available at \\url{https://github.com/GXNU-ZhongLab/ODTrack}.","url_abs":"https://arxiv.org/abs/2401.01686v1","url_pdf":"https://arxiv.org/pdf/2401.01686v1.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":"odtrack-online-dense-temporal-token-learning","repo_url":"https://github.com/gxnu-zhonglab/odtrack","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"semi-supervised-video-object-segmentation","task_name":"Semi-Supervised Video Object Segmentation"},{"task_slug":"video-object-tracking","task_name":"Video Object Tracking"},{"task_slug":"visual-object-tracking","task_name":"Visual Object Tracking"},{"task_slug":"visual-tracking","task_name":"Visual Tracking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/semi-supervised-video-object-segmentation-on-15","task":"Semi-Supervised Video Object Segmentation","dataset":"VOT2020","model":"ODTrack-L","rank_in_archive_order":6,"of":20,"metrics":{"EAO":"0.605"},"uses_additional_data":false},{"leaderboard":"/sota/semi-supervised-video-object-segmentation-on-15","task":"Semi-Supervised Video Object Segmentation","dataset":"VOT2020","model":"ODTrack-B","rank_in_archive_order":10,"of":20,"metrics":{"EAO":"0.581"},"uses_additional_data":false},{"leaderboard":"/sota/video-object-tracking-on-nv-vot211","task":"Video Object Tracking","dataset":"NT-VOT211","model":"ODTrack","rank_in_archive_order":2,"of":43,"metrics":{"AUC":"39.60","Precision":"55.80"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-didi","task":"Visual Object Tracking","dataset":"DiDi","model":"ODTrack","rank_in_archive_order":5,"of":11,"metrics":{"Tracking quality":"0.608"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-got-10k","task":"Visual Object Tracking","dataset":"GOT-10k","model":"ODTrack-L","rank_in_archive_order":10,"of":42,"metrics":{"Average Overlap":"78.2"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-got-10k","task":"Visual Object Tracking","dataset":"GOT-10k","model":"ODTrack-B","rank_in_archive_order":15,"of":42,"metrics":{"Average Overlap":"77.0"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-lasot","task":"Visual Object Tracking","dataset":"LaSOT","model":"ODTrack-L","rank_in_archive_order":11,"of":46,"metrics":{"AUC":"74.0"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-lasot","task":"Visual Object Tracking","dataset":"LaSOT","model":"ODTrack-B","rank_in_archive_order":15,"of":46,"metrics":{"AUC":"73.2"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-lasot-ext","task":"Visual Object Tracking","dataset":"LaSOT-ext","model":"ODTrack-L","rank_in_archive_order":9,"of":18,"metrics":{"AUC":"53.9"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-lasot-ext","task":"Visual Object Tracking","dataset":"LaSOT-ext","model":"ODTrack-B","rank_in_archive_order":14,"of":18,"metrics":{"AUC":"52.4"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-otb-2015","task":"Visual Object Tracking","dataset":"OTB-2015","model":"ODTrack-L","rank_in_archive_order":2,"of":18,"metrics":{"AUC":"0.724"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-otb-2015","task":"Visual Object Tracking","dataset":"OTB-2015","model":"ODTrack-B","rank_in_archive_order":3,"of":18,"metrics":{"AUC":"0.723"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-tnl2k","task":"Visual Object Tracking","dataset":"TNL2K","model":"ODTrack-L","rank_in_archive_order":8,"of":16,"metrics":{"AUC":"61.7"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-tnl2k","task":"Visual Object Tracking","dataset":"TNL2K","model":"ODTrack-B","rank_in_archive_order":10,"of":16,"metrics":{"AUC":"60.9"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-trackingnet","task":"Visual Object Tracking","dataset":"TrackingNet","model":"ODTrack-L","rank_in_archive_order":8,"of":40,"metrics":{"Accuracy":"86.1"},"uses_additional_data":false},{"leaderboard":"/sota/visual-object-tracking-on-trackingnet","task":"Visual Object Tracking","dataset":"TrackingNet","model":"ODTrack-B","rank_in_archive_order":15,"of":40,"metrics":{"Accuracy":"85.1"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2401.01686","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.01686"}},"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/GXNU-ZhongLab/ODTrack","reach":null}],"summary":{"ran":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":0,"samples":[{"code_sha256_prefix":"0002ed5067d80cd9","entry":"ODTrack","repo":"GXNU-ZhongLab/ODTrack","repo_kind":"official","path":"lib/models/odtrack/odtrack.py","file_url":"https://github.com/GXNU-ZhongLab/ODTrack/blob/HEAD/lib/models/odtrack/odtrack.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0002ed5067d80cd9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}