Papers › ODTrack: Online Dense Temporal Token Learning for Visual Tracking

ODTrack: Online Dense Temporal Token Learning for Visual Tracking

3 Jan 2024arXiv:2401.01686archive 2025-07-28

Yaozong Zheng, Bineng Zhong, Qihua Liang, Zhiyi Mo, Shengping Zhang, Xianxian Li

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}.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2401.01686")

Code

Syntology Ran 1 of 1 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 1 ran with no contract checked.

By repository: official repository: 1 sample from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

gxnu-zhonglab/odtrack officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

1 sample harvested; 1 ran; 0 honoured the contract we drafted; 0 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran

Licence: 0 of the 1 sample are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from GXNU-ZhongLab/ODTrack. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

ODTrack GXNU-ZhongLab/ODTrack/lib/models/odtrack/odtrack.py official repository ran · metamorphic tier: deterministic MIT (permissive) · 0002ed5067d80cd9 · report

Tasks

Semi-Supervised Video Object SegmentationVideo Object TrackingVisual Object TrackingVisual Tracking

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semi-Supervised Video Object Segmentation VOT2020 ODTrack-L EAO 0.605 #6 of 20 Archive leaderboard report
Semi-Supervised Video Object Segmentation VOT2020 ODTrack-B EAO 0.581 #10 of 20 Archive leaderboard report
Video Object Tracking NT-VOT211 ODTrack AUC 39.60 #2 of 43 Archive leaderboard report
Video Object Tracking NT-VOT211 ODTrack Precision 55.80 #2 of 43 Archive leaderboard report
Visual Object Tracking DiDi ODTrack Tracking quality 0.608 #5 of 11 Archive leaderboard report
Visual Object Tracking GOT-10k ODTrack-L Average Overlap 78.2 #10 of 42 Archive leaderboard report
Visual Object Tracking GOT-10k ODTrack-B Average Overlap 77.0 #15 of 42 Archive leaderboard report
Visual Object Tracking LaSOT ODTrack-L AUC 74.0 #11 of 46 Archive leaderboard report
Visual Object Tracking LaSOT ODTrack-B AUC 73.2 #15 of 46 Archive leaderboard report
Visual Object Tracking LaSOT-ext ODTrack-L AUC 53.9 #9 of 18 Archive leaderboard report
Visual Object Tracking LaSOT-ext ODTrack-B AUC 52.4 #14 of 18 Archive leaderboard report
Visual Object Tracking OTB-2015 ODTrack-L AUC 0.724 #2 of 18 Archive leaderboard report
Visual Object Tracking OTB-2015 ODTrack-B AUC 0.723 #3 of 18 Archive leaderboard report
Visual Object Tracking TNL2K ODTrack-L AUC 61.7 #8 of 16 Archive leaderboard report
Visual Object Tracking TNL2K ODTrack-B AUC 60.9 #10 of 16 Archive leaderboard report
Visual Object Tracking TrackingNet ODTrack-L Accuracy 86.1 #8 of 40 Archive leaderboard report
Visual Object Tracking TrackingNet ODTrack-B Accuracy 85.1 #15 of 40 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections