Papers › Towards Sequence-Level Training for Visual Tracking

Towards Sequence-Level Training for Visual Tracking

11 Aug 2022arXiv:2208.05810archive 2025-07-28

Minji Kim, Seungkwan Lee, Jungseul Ok, Bohyung Han, Minsu Cho

Despite the extensive adoption of machine learning on the task of visual object tracking, recent learning-based approaches have largely overlooked the fact that visual tracking is a sequence-level task in its nature; they rely heavily on frame-level training, which inevitably induces inconsistency between training and testing in terms of both data distributions and task objectives. This work introduces a sequence-level training strategy for visual tracking based on reinforcement learning and discusses how a sequence-level design of data sampling, learning objectives, and data augmentation can improve the accuracy and robustness of tracking algorithms. Our experiments on standard benchmarks including LaSOT, TrackingNet, and GOT-10k demonstrate that four representative tracking models, SiamRPN++, SiamAttn, TransT, and TrDiMP, consistently improve by incorporating the proposed methods in training without modifying architectures.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 5 code samples harvested from 1 repository linked to this paper: 3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 5 samples from 1 repository, 3 ran (3 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

byminji/SLTtrack officialmentioned in papermentioned on GitHubpytorchSyntology: 5 samples, 3 ran (0 instrument-failed) · 2 unverified report
wangxiao5791509/Tracking-with-Deep-Reinforcement-Learning mentioned on GitHubSyntology: not harvested 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

5 samples harvested: 3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran
2unverified

Licence: 5 of the 5 samples 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 byminji/SLTtrack. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

byminji/SLTtrack official repository 5 samples, 3 ran (0 instrument-failed) · 2 unverified
AverageMeter in 26 papers ltr/trainers/slt_transt_trainer.py ran GPL-3.0 (copyleft) · pointer only · 06ad30a435b0a300 · report fixture: signature val:float/0/float, n:int/0/int · returned NoneType · level recorded 2026-09-24
BaseTrainer in 16 papers ltr/trainers/slt_transt_trainer.py ran GPL-3.0 (copyleft) · pointer only · b1a9819a687a220f · report fixture: returned BaseTrainer · level recorded 2026-09-22
StatValue ltr/trainers/slt_transt_trainer.py ran GPL-3.0 (copyleft) · pointer only · 23cc60d1ea522fc3 · report fixture: returned StatValue · level recorded 2026-09-22
SLTTransTTrainer ltr/trainers/slt_transt_trainer.py unverified GPL-3.0 (copyleft) · pointer only · 554a6dcd2219073b · report
TensorboardWriter ltr/trainers/slt_transt_trainer.py unverified GPL-3.0 (copyleft) · pointer only · a634b2ad3f5760ab · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for sequence-level training strategy (graph method: sequence-level training strategy). 5 bricks; individually on a fixture: 3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

  1. SLTTransTTrainer entry · level 0 · unverified · 554a6dcd2219073b
  2. AverageMeter helper · level 1 · ran · 06ad30a435b0a300
  3. BaseTrainer helper · level 1 · ran · b1a9819a687a220f
  4. StatValue helper · level 1 · ran · 23cc60d1ea522fc3
  5. TensorboardWriter helper · level 0 · unverified · a634b2ad3f5760ab

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2208.05810") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Data AugmentationObject TrackingReinforcement Learning (RL)Video Object TrackingVisual Object Tracking

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Object Tracking NT-VOT211 SLT-TransT AUC 37.22 #11 of 43 Archive leaderboard report
Video Object Tracking NT-VOT211 SLT-TransT Precision 51.70 #11 of 43 Archive leaderboard report
Visual Object Tracking GOT-10k SLT-TransT Average Overlap 67.5 #31 of 42 Archive leaderboard report
Visual Object Tracking GOT-10k SLT-TransT Success Rate 0.5 76.8 #31 of 42 Archive leaderboard report
Visual Object Tracking GOT-10k SLT-TransT Success Rate 0.75 60.3 #31 of 42 Archive leaderboard report
Visual Object Tracking LaSOT SLT-TransT AUC 66.8 #36 of 46 Archive leaderboard report
Visual Object Tracking LaSOT SLT-TransT Normalized Precision 75.5 #36 of 46 Archive leaderboard report
Visual Object Tracking TrackingNet SLT-TransT Accuracy 82.8 #25 of 40 Archive leaderboard report
Visual Object Tracking TrackingNet SLT-TransT Normalized Precision 87.5 #25 of 40 Archive leaderboard report
Visual Object Tracking TrackingNet SLT-TransT Precision 81.4 #25 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