Papers › Do Different Tracking Tasks Require Different Appearance Models?

Do Different Tracking Tasks Require Different Appearance Models?

5 Jul 2021NeurIPS 2021 12arXiv:2107.02156archive 2025-07-28

Zhongdao Wang, Hengshuang Zhao, Ya-Li Li, Shengjin Wang, Philip H. S. Torr, Luca Bertinetto

Tracking objects of interest in a video is one of the most popular and widely applicable problems in computer vision. However, with the years, a Cambrian explosion of use cases and benchmarks has fragmented the problem in a multitude of different experimental setups. As a consequence, the literature has fragmented too, and now novel approaches proposed by the community are usually specialised to fit only one specific setup. To understand to what extent this specialisation is necessary, in this work we present UniTrack, a solution to address five different tasks within the same framework. UniTrack consists of a single and task-agnostic appearance model, which can be learned in a supervised or self-supervised fashion, and multiple ``heads'' that address individual tasks and do not require training. We show how most tracking tasks can be solved within this framework, and that the same appearance model can be successfully used to obtain results that are competitive against specialised methods for most of the tasks considered. The framework also allows us to analyse appearance models obtained with the most recent self-supervised methods, thus extending their evaluation and comparison to a larger variety of important problems.

PaperPDFConference PDFCodeCode 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.

Syntology holds a reference implementation of UniTrack, generated from the paper text (not the authors' code), at level 3 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='UniTrack') (how to connect); the free check have('2107.02156') needs no token.

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

Code

Syntology 17 code samples harvested from 1 repository linked to this paper: 6 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 11 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 17 samples from 1 repository, 6 ran (4 with no instrument failure; 2 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 6 samples that ran has no recorded date.

Zhongdao/UniTrack officialmentioned in papermentioned on GitHubpytorchSyntology: 17 samples, 6 ran (2 instrument-failed) · 11 unverified 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

17 samples harvested: 6 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 11 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.

2ran · our draft was wrong
4ran
11unverified

Licence: 0 of the 17 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 Zhongdao/UniTrack. “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”. For 2 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

Zhongdao/UniTrack official repository 17 samples, 6 ran (2 instrument-failed) · 11 unverified
From3D model/model.py ran MIT (permissive) · 6bed795c8790b42f · report fixture: returned From3D · level recorded 2026-09-22
HighResolutionModule in 10 papers model/model.py ran MIT (permissive) · 6cb64253bc2483ab · report fixture: returned HighResolutionModule · level recorded 2026-09-22
RandomFeatGenerator model/model.py ran fingerprinted MIT (permissive) · 24f302b7add67f84 · report fixture: returned RandomFeatGenerator · level recorded 2026-09-22
ResNet in 139 papers model/model.py ran fingerprinted MIT (permissive) · 5fb6217486f7e99c · report fixture: returned ResNet · level recorded 2026-09-22
_resnet in 27 papers model/model.py ran · our draft was wrong MIT (permissive) · 8a5d9f9460c91bb5 · report fixture: signature arch:str/0/str, block:callable/0/?, layers:list/1/int, pretrained:bool/0/bool, progress:bool/0/bool, num_classes:int/0/int · returned ResNet · level recorded 2026-09-22
dets2obs demo/mot_demo.py ran · our draft was wrong MIT (permissive) · 93ff6b09d3e38b8e · report fixture: signature dets:Tensor/2/float, imginfo:dict/0/?, cls:list/1/int · returned ndarray · level recorded, date not recorded
HighResolutionNet in 6 papers model/model.py unverified MIT (permissive) · fe69a6b9983c5ce3 · report
get_cls_net model/model.py unverified MIT (permissive) · ec2a972e12e2c2f6 · report
load_tc_model model/model.py unverified MIT (permissive) · bb753455f7400311 · report
load_uvc_model model/model.py unverified MIT (permissive) · 407da3ab43d8ba3f · report
make_encoder in 15 papers model/model.py unverified MIT (permissive) · d3b2fda956486d2c · report
partial_load model/model.py unverified MIT (permissive) · c0367497ab1f7faa · report
resnet101 in 24 papers model/model.py unverified MIT (permissive) · 33b995998b62c580 · report
resnet18 in 432 papers model/model.py unverified MIT (permissive) · 08e568179967e865 · report
resnet50 in 121 papers model/model.py unverified MIT (permissive) · 92b061ec78263602 · report
resnext101_32x8d model/model.py unverified MIT (permissive) · bf216e79a1ef8b76 · report
resnext50_32x4d in 5 papers model/model.py unverified MIT (permissive) · 8cc2e400c38e8730 · 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. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. 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. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

2 assemblies on this paper: 1 harvested, 1 generated.

generated Assembly for UniTrack (graph method: UniTrack), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 3; 5 property tests passed on both).

label matches by construction: the code was generated for this method (not judged by a model)

  1. compute_combined_cost_matrix entry · level 3 · ran · honoured contract · 15c321975fc9dd130e069ae44cbf3641bd8e3ce60bcd93689dd970008a390a82

harvested Assembly for UniTrack (graph method: UniTrack). 19 bricks; individually on a fixture: 8 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 11 unverified. The assembly has not been run end-to-end.

  1. make_encoder entry · level 0 · unverified · d3b2fda956486d2c
  2. From3D helper · level 1 · ran · 6bed795c8790b42f
  3. RandomFeatGenerator helper · level 1 · ran · 24f302b7add67f84
  4. get_cls_net helper · level 0 · unverified · ec2a972e12e2c2f6
  5. load_tc_model helper · level 0 · unverified · bb753455f7400311
  6. load_uvc_model helper · level 0 · unverified · 407da3ab43d8ba3f
  7. partial_load helper · level 0 · unverified · c0367497ab1f7faa
  8. resnet101 helper · level 0 · unverified · 33b995998b62c580
  9. resnet18 helper · level 0 · unverified · 08e568179967e865
  10. resnet50 helper · level 0 · unverified · 92b061ec78263602
  11. resnext101_32x8d helper · level 0 · unverified · bf216e79a1ef8b76
  12. resnext50_32x4d helper · level 0 · unverified · 8cc2e400c38e8730
  13. HighResolutionNet helper · level 0 · unverified · fe69a6b9983c5ce3
  14. Bottleneck helper · level 1 · ran · 70a3b60f25883442
  15. _resnet helper · level 1 · ran · our draft was wrong · 8a5d9f9460c91bb5
  16. BasicBlock helper · level 1 · ran · aa08b1e9b931f4dd
  17. ResNet helper · level 1 · ran · 5fb6217486f7e99c
  18. HighResolutionModule helper · level 1 · ran · 6cb64253bc2483ab
  19. conv3x3 helper · level 1 · ran · our draft was wrong · fac5364e2f53c6db

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="2107.02156") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Multi-Object TrackingMulti-Object Tracking and SegmentationMultiple People TrackingObject TrackingOnline Multi-Object TrackingPose EstimationPose PredictionPose TrackingSemi-Supervised Video Object SegmentationVideo Instance SegmentationVideo Object SegmentationVideo Object TrackingVisual Object TrackingVisual Tracking

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multi-Object Tracking MOT16 UniTrack IDF1 71.8 #6 of 24 Archive leaderboard report
Multi-Object Tracking MOT16 UniTrack IDs 683 #6 of 24 Archive leaderboard report
Multi-Object Tracking MOT16 UniTrack MOTA 74.7 #6 of 24 Archive leaderboard report
Multi-Object Tracking MOTS20 UniTrack IDF1 67.2 #2 of 6 Archive leaderboard report
Multi-Object Tracking MOTS20 UniTrack IDs 622 #2 of 6 Archive leaderboard report
Multi-Object Tracking MOTS20 UniTrack sMOTSA 68.9 #2 of 6 Archive leaderboard report
Pose Estimation J-HMDB UniTrack_i18 Mean PCK@0.1 58.3 #5 of 5 Archive leaderboard report
Pose Estimation J-HMDB UniTrack_i18 Mean PCK@0.2 80.5 #5 of 5 Archive leaderboard report
Pose Tracking PoseTrack2018 UniTrack IDF1 73.2 #2 of 5 Archive leaderboard report
Pose Tracking PoseTrack2018 UniTrack IDs 6760 #2 of 5 Archive leaderboard report
Pose Tracking PoseTrack2018 UniTrack MOTA 63.5 #2 of 5 Archive leaderboard report
Video Instance Segmentation YouTube-VIS validation UniTrack mask AP 30.1 #42 of 44 Archive leaderboard report
Video Object Segmentation DAVIS 2017 UniTrack mIoU 58.4 #4 of 5 Archive leaderboard report
Visual Object Tracking OTB-2015 UniTrack_DCF AUC 0.618 #16 of 18 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