Papers › ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation

ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation

26 Apr 2022arXiv:2204.12484archive 2025-07-28

Yufei Xu, Jing Zhang, Qiming Zhang, DaCheng Tao

Although no specific domain knowledge is considered in the design, plain vision transformers have shown excellent performance in visual recognition tasks. However, little effort has been made to reveal the potential of such simple structures for pose estimation tasks. In this paper, we show the surprisingly good capabilities of plain vision transformers for pose estimation from various aspects, namely simplicity in model structure, scalability in model size, flexibility in training paradigm, and transferability of knowledge between models, through a simple baseline model called ViTPose. Specifically, ViTPose employs plain and non-hierarchical vision transformers as backbones to extract features for a given person instance and a lightweight decoder for pose estimation. It can be scaled up from 100M to 1B parameters by taking the advantages of the scalable model capacity and high parallelism of transformers, setting a new Pareto front between throughput and performance. Besides, ViTPose is very flexible regarding the attention type, input resolution, pre-training and finetuning strategy, as well as dealing with multiple pose tasks. We also empirically demonstrate that the knowledge of large ViTPose models can be easily transferred to small ones via a simple knowledge token. Experimental results show that our basic ViTPose model outperforms representative methods on the challenging MS COCO Keypoint Detection benchmark, while the largest model sets a new state-of-the-art. The code and models are available at https://github.com/ViTAE-Transformer/ViTPose.

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

No sample from the archive's official repository (vitae-transformer/vitpose) is linked to this paper; the 31 samples below come from 3 community repositories. Syntology harvested code from vitae-transformer/vitpose for another paper.

vitae-transformer/vitpose: Syntology's graph links these samples to ViTPose++: Vision Transformer for Generic Body Pose Estimation (arXiv:2212.04246; that paper's own run record: 3 ran (of which 0 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) · 0 unverified); nothing checks that they implement this paper's method.

Syntology 31 code samples harvested from 3 repositories linked to this paper: 18 ran (of which 8 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 8 where Syntology's instrument failed) · 13 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 7 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 31 samples from 3 repositories, 18 ran (10 with no instrument failure; 8 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.

No sample is linked to this paper from 3 of its repositories that Syntology harvested for other papers:

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.

vitae-transformer/vitpose officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ViTPose++: Vision Transformer for Generic Body Pose Estimation (arXiv:2212.04246; that paper's own run record: 3 ran (of which 0 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) · 0 unverified); nothing checks that they implement this paper's method. report
vitae-transformer/qformer mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to VSA: Learning Varied-Size Window Attention in Vision Transformers (arXiv:2204.08446; that paper's own run record: 3 ran (of which 3 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) · 1 unverified; every one of the 3 samples that ran constructed an object rather than computing a result) and Vision Transformer with Quadrangle Attention (arXiv:2303.15105; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
JunkyByte/easy_ViTPose pytorchSyntology: 20 samples, 12 ran (8 instrument-failed) · 8 unverified report
gpastal24/ViTPose-Pytorch pytorchSyntology: 6 samples, 5 ran (0 instrument-failed) · 1 unverified report
huggingface/transformers pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Attention Is All You Need (arXiv:1706.03762; that paper's own run record: 610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified), HuggingFace's Transformers: State-of-the-art Natural Language Processing (arXiv:1910.03771; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified), DeBERTa: Decoding-enhanced BERT with Disentangled Attention (arXiv:2006.03654; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
jaehyunnn/ViTPose_pytorch pytorchSyntology: 5 samples, 1 ran (0 instrument-failed) · 4 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

31 samples harvested: 18 ran (of which 8 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 8 where Syntology's instrument failed) · 13 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong
7ran; the contract check could not run
10ran
13unverified

Licence: 6 of the 31 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 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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 6 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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

JunkyByte/easy_ViTPose community (archive-listed) 20 samples, 12 ran (8 instrument-failed) · 8 unverified
Block in 252 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
easy_ViTPose/vit_models/model.py ran Apache-2.0 (permissive) · b45be27e9755bcea · report fixture: returned Block · level recorded 2026-09-22
DropPath in 75 papers
census: 17 implementations from 17 papers, 8 distinct outputs across 3 buckets, one shared input per bucket
easy_ViTPose/vit_models/model.py ran fingerprinted Apache-2.0 (permissive) · bcec6a4434dcfdb8 · report fixture: returned DropPath · level recorded 2026-09-22
HybridEmbed in 7 papers easy_ViTPose/vit_models/model.py ran fingerprinted Apache-2.0 (permissive) · 3729451b09b4c285 · report fixture: returned HybridEmbed · level recorded 2026-09-22
PatchEmbed in 123 papers
census: 9 implementations from 9 papers, 6 distinct outputs on one shared input
easy_ViTPose/vit_models/model.py ran Apache-2.0 (permissive) · 38811a374b1cff76 · report fixture: returned PatchEmbed · level recorded 2026-09-22
_calc_distances easy_ViTPose/vit_models/model.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · c4c1705ff75a3ef5 · report fixture: signature preds:ndarray/3/float, targets:ndarray/3/float, mask:ndarray/2/bool, normalize:ndarray/2/float · returned ndarray · level recorded 2026-09-22
_distance_acc easy_ViTPose/vit_models/model.py ran; the contract check could not run (RAISES) fingerprinted Apache-2.0 (permissive) · c053b8c18815c5f8 · report fixture: signature distances:ndarray/1/float, thr:float/0/float · returned float64 · level recorded 2026-09-22
_gaussian_blur easy_ViTPose/vit_models/model.py ran; the contract check could not run (RAISES) fingerprinted Apache-2.0 (permissive) · 92e7b0a551d548fb · report fixture: signature heatmaps:ndarray/4/float, kernel:int/0/int · returned ndarray · level recorded 2026-09-22
_get_max_preds easy_ViTPose/vit_models/model.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · e53d577562ffb351 · report fixture: signature heatmaps:ndarray/4/float · returned tuple · level recorded 2026-09-22
_taylor easy_ViTPose/vit_models/model.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 6c308dbbb4a9949b · report fixture: signature heatmap:ndarray/2/float, coord:ndarray/1/float · returned ndarray · level recorded 2026-09-22
keypoint_pck_accuracy easy_ViTPose/vit_models/model.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · 8d099da3b789e317 · report fixture: signature pred:ndarray/3/float, gt:ndarray/3/float, mask:ndarray/2/bool, thr:float/0/float, normalize:ndarray/2/float · returned tuple · level recorded 2026-09-22
post_dark_udp easy_ViTPose/vit_models/model.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · 8294c29e3ad40443 · report fixture: signature coords:ndarray/3/float, batch_heatmaps:ndarray/4/float, kernel:int/0/int · returned ndarray · level recorded 2026-09-22
trunc_normal_ in 154 papers
census: 37 implementations from 54 papers, 4 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
easy_ViTPose/vit_models/model.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · c3487124f762d881 · report fixture: signature tensor:Tensor/2/float, mean:float/0/float, std:float/0/float, a:float/0/float, b:float/0/float · returned Tensor · level recorded 2026-09-22
TopdownHeatmapBaseHead easy_ViTPose/vit_models/model.py unverified Apache-2.0 (permissive) · c828e7e8249b42be · report
TopdownHeatmapSimpleHead easy_ViTPose/vit_models/model.py unverified Apache-2.0 (permissive) · bbca4a34f6f76844 · report
ViT in 10 papers easy_ViTPose/vit_models/model.py unverified Apache-2.0 (permissive) · ec2566dcbcbac9aa · report
ViTPose easy_ViTPose/vit_models/model.py unverified Apache-2.0 (permissive) · e38694c775a09153 · report
keypoints_from_heatmaps easy_ViTPose/vit_models/model.py unverified Apache-2.0 (permissive) · c706a215373869f8 · report
normal_init in 11 papers easy_ViTPose/vit_models/model.py unverified Apache-2.0 (permissive) · fb206aa7be7aa229 · report
pose_pck_accuracy in 5 papers easy_ViTPose/vit_models/model.py unverified Apache-2.0 (permissive) · 6d08729cda37113c · report
gpastal24/ViTPose-Pytorch community (archive-listed) 6 samples, 5 ran (0 instrument-failed) · 1 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
src/vitpose_infer/builder/backbones/vit.py ran GPL-3.0 (copyleft) · pointer only · a17528cd8209371a · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-24
Block in 252 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
src/vitpose_infer/builder/backbones/vit.py ran · metamorphic tier: deterministic GPL-3.0 (copyleft) · pointer only · daeb52387dc365ad · report fixture: returned Block · level recorded 2026-09-22
DropPath in 75 papers
census: 17 implementations from 17 papers, 8 distinct outputs across 3 buckets, one shared input per bucket
src/vitpose_infer/builder/backbones/vit.py ran · metamorphic tier: deterministic fingerprinted GPL-3.0 (copyleft) · pointer only · cd0e7be073ad785f · report fixture: returned DropPath · level recorded 2026-09-22
HybridEmbed in 7 papers src/vitpose_infer/builder/backbones/vit.py ran · metamorphic tier: deterministic fingerprinted GPL-3.0 (copyleft) · pointer only · 6f5efea0780d30f0 · report fixture: returned HybridEmbed · level recorded 2026-09-22
PatchEmbed in 123 papers
census: 9 implementations from 9 papers, 6 distinct outputs on one shared input
src/vitpose_infer/builder/backbones/vit.py ran · metamorphic tier: deterministic GPL-3.0 (copyleft) · pointer only · fa78df3f00a52ac8 · report fixture: returned PatchEmbed · level recorded 2026-09-22
ViT in 10 papers src/vitpose_infer/builder/backbones/vit.py unverified GPL-3.0 (copyleft) · pointer only · d17daecae39897ce · report
jaehyunnn/ViTPose_pytorch community (archive-listed) 5 samples, 1 ran (0 instrument-failed) · 4 unverified
PatchEmbed in 123 papers
census: 9 implementations from 9 papers, 6 distinct outputs on one shared input
models/model.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · c26b0690c76a9818 · report fixture: signature x:Tensor/4/float · returned tuple · level recorded 2026-09-22
TopdownHeatmapSimpleHead models/model.py unverified Apache-2.0 (permissive) · dbcb1917083518a7 · report
ViT in 10 papers models/model.py unverified Apache-2.0 (permissive) · a3947ec0fada50f7 · report
ViTPose models/model.py unverified Apache-2.0 (permissive) · ee523b19fa42ef3e · 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. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

3 assemblies on this paper: 3 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

3 sibling assemblies for ViTPose (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for ViTPose (graph method: ViTPose). 7 bricks; individually on a fixture: 6 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. ViT entry · level 0 · unverified · d17daecae39897ce
  2. Block helper · level 1 · ran · daeb52387dc365ad
  3. HybridEmbed helper · level 1 · ran · 6f5efea0780d30f0
  4. PatchEmbed helper · level 1 · ran · fa78df3f00a52ac8
  5. Attention helper · level 1 · ran · a17528cd8209371a
  6. DropPath helper · level 1 · ran · cd0e7be073ad785f
  7. Mlp helper · level 1 · ran · e71525ebf968c4c3

harvested Assembly for ViTPose (graph method: ViTPose). 26 bricks; individually on a fixture: 17 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 11 where Syntology's instrument failed) · 9 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. ViTPose entry · level 0 · unverified · e38694c775a09153
  2. TopdownHeatmapSimpleHead model · level 0 · unverified · bbca4a34f6f76844
  3. ViT model · level 0 · unverified · ec2566dcbcbac9aa
  4. TopdownHeatmapBaseHead helper · level 0 · unverified · c828e7e8249b42be
  5. constant_init helper · level 0 · unverified · a10a9642969fb96e
  6. normal_init helper · level 0 · unverified · fb206aa7be7aa229
  7. pose_pck_accuracy helper · level 0 · unverified · 6d08729cda37113c
  8. resize helper · level 0 · unverified · 471e5bd20e25b2a2
  9. Block helper · level 1 · ran · b45be27e9755bcea
  10. HybridEmbed helper · level 1 · ran · 3729451b09b4c285
  11. PatchEmbed helper · level 1 · ran · 38811a374b1cff76
  12. trunc_normal_ helper · level 1 · ran; the contract check could not run (RAISES) · c3487124f762d881
  13. keypoints_from_heatmaps helper · level 0 · unverified · c706a215373869f8
  14. _get_max_preds helper · level 1 · ran; the contract check could not run (RAISES) · e53d577562ffb351
  15. keypoint_pck_accuracy helper · level 1 · ran; the contract check could not run (RAISES) · 8d099da3b789e317
  16. Attention helper · level 1 · ran · a17528cd8209371a
  17. DropPath helper · level 1 · ran · bcec6a4434dcfdb8
  18. Mlp helper · level 1 · ran · e71525ebf968c4c3
  19. drop_path helper · level 1 · ran; the contract check could not run · 87577b3ff9d32712
  20. _trunc_normal_ helper · level 1 · ran; the contract check could not run · 119ce2c5455542b0
  21. _gaussian_blur helper · level 1 · ran; the contract check could not run (RAISES) · 92e7b0a551d548fb
  22. _taylor helper · level 1 · ran · our draft was wrong · 6c308dbbb4a9949b
  23. post_dark_udp helper · level 1 · ran; the contract check could not run (RAISES) · 8294c29e3ad40443
  24. _calc_distances helper · level 1 · ran; the contract check could not run (RAISES) · c4c1705ff75a3ef5
  25. _distance_acc helper · level 1 · ran; the contract check could not run (RAISES) · c053b8c18815c5f8
  26. _ntuple helper · level 1 · ran · our draft was wrong · cd4d36b9126e53f2

harvested Assembly for ViTPose (graph method: ViTPose). 26 bricks; individually on a fixture: 17 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 11 where Syntology's instrument failed) · 9 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. ViTPose entry · level 0 · unverified · ee523b19fa42ef3e
  2. TopdownHeatmapSimpleHead model · level 0 · unverified · dbcb1917083518a7
  3. ViT model · level 0 · unverified · a3947ec0fada50f7
  4. TopdownHeatmapBaseHead model · level 0 · unverified · c828e7e8249b42be
  5. constant_init helper · level 0 · unverified · a10a9642969fb96e
  6. normal_init helper · level 0 · unverified · fb206aa7be7aa229
  7. pose_pck_accuracy helper · level 0 · unverified · 6d08729cda37113c
  8. resize helper · level 0 · unverified · 126e704199014f2d
  9. Block helper · level 1 · ran · b45be27e9755bcea
  10. HybridEmbed helper · level 1 · ran · 3729451b09b4c285
  11. PatchEmbed helper · level 1 · ran · c26b0690c76a9818
  12. trunc_normal_ helper · level 1 · ran; the contract check could not run (RAISES) · c3487124f762d881
  13. keypoints_from_heatmaps helper · level 0 · unverified · c706a215373869f8
  14. _get_max_preds helper · level 1 · ran; the contract check could not run (RAISES) · e53d577562ffb351
  15. keypoint_pck_accuracy helper · level 1 · ran; the contract check could not run (RAISES) · 8d099da3b789e317
  16. Attention helper · level 1 · ran · a17528cd8209371a
  17. DropPath helper · level 1 · ran · bcec6a4434dcfdb8
  18. Mlp helper · level 1 · ran · e71525ebf968c4c3
  19. drop_path helper · level 1 · ran; the contract check could not run · 87577b3ff9d32712
  20. _trunc_normal_ helper · level 1 · ran; the contract check could not run · 119ce2c5455542b0
  21. _gaussian_blur helper · level 1 · ran; the contract check could not run (RAISES) · 92e7b0a551d548fb
  22. _taylor helper · level 1 · ran · our draft was wrong · 6c308dbbb4a9949b
  23. post_dark_udp helper · level 1 · ran; the contract check could not run (RAISES) · 8294c29e3ad40443
  24. _calc_distances helper · level 1 · ran; the contract check could not run (RAISES) · c4c1705ff75a3ef5
  25. _distance_acc helper · level 1 · ran; the contract check could not run (RAISES) · c053b8c18815c5f8
  26. _ntuple helper · level 1 · ran · our draft was wrong · cd4d36b9126e53f2

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="2204.12484") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

2D Human Pose EstimationKeypoint DetectionPose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
2D Human Pose Estimation Human-Art ViTPose-h AP 0.468 #3 of 10 Archive leaderboard report
2D Human Pose Estimation Human-Art ViTPose-h AP (gt bbox) 0.800 #3 of 10 Archive leaderboard report
2D Human Pose Estimation Human-Art ViTPose-l AP 0.459 #4 of 10 Archive leaderboard report
2D Human Pose Estimation Human-Art ViTPose-l AP (gt bbox) 0.789 #4 of 10 Archive leaderboard report
2D Human Pose Estimation Human-Art ViTpose-b AP 0.410 #6 of 10 Archive leaderboard report
2D Human Pose Estimation Human-Art ViTpose-b AP (gt bbox) 0.759 #6 of 10 Archive leaderboard report
2D Human Pose Estimation Human-Art ViTPose-s AP 0.381 #8 of 10 Archive leaderboard report
2D Human Pose Estimation Human-Art ViTPose-s AP (gt bbox) 0.738 #8 of 10 Archive leaderboard report
Pose Estimation COCO test-dev ViTPose (ViTAE-G, ensemble) AP 81.1 #1 of 47 Archive leaderboard report
Pose Estimation COCO test-dev ViTPose (ViTAE-G, ensemble) AP50 95.0 #1 of 47 Archive leaderboard report
Pose Estimation COCO test-dev ViTPose (ViTAE-G, ensemble) AP75 88.2 #1 of 47 Archive leaderboard report
Pose Estimation COCO test-dev ViTPose (ViTAE-G, ensemble) APL 86.0 #1 of 47 Archive leaderboard report
Pose Estimation COCO test-dev ViTPose (ViTAE-G, ensemble) APM 77.8 #1 of 47 Archive leaderboard report
Pose Estimation COCO test-dev ViTPose (ViTAE-G, ensemble) AR 85.6 #1 of 47 Archive leaderboard report
Pose Estimation COCO test-dev ViTPose (ViTAE-G) AP 80.9 #2 of 47 Archive leaderboard report
Pose Estimation COCO test-dev ViTPose (ViTAE-G) AP50 94.8 #2 of 47 Archive leaderboard report
Pose Estimation COCO test-dev ViTPose (ViTAE-G) AP75 88.1 #2 of 47 Archive leaderboard report
Pose Estimation COCO test-dev ViTPose (ViTAE-G) APL 85.9 #2 of 47 Archive leaderboard report
Pose Estimation COCO test-dev ViTPose (ViTAE-G) APM 77.5 #2 of 47 Archive leaderboard report
Pose Estimation COCO test-dev ViTPose (ViTAE-G) AR 85.4 #2 of 47 Archive leaderboard report
Pose Estimation COCO val2017 ViTPose-B (Single-task_GT-bbox_256x192) AP 77.3 #3 of 11 Archive leaderboard report
Pose Estimation COCO val2017 ViTPose-B (Single-task_GT-bbox_256x192) AP50 93.5 #3 of 11 Archive leaderboard report
Pose Estimation COCO val2017 ViTPose-B (Single-task_GT-bbox_256x192) AP75 84.5 #3 of 11 Archive leaderboard report
Pose Estimation COCO val2017 ViTPose-B (Single-task_GT-bbox_256x192) AR 80.4 #3 of 11 Archive leaderboard report
Pose Estimation COCO val2017 ViTPose-B (Single-task_Det-bbox_256x192) AP 75.8 #5 of 11 Archive leaderboard report
Pose Estimation COCO val2017 ViTPose-B (Single-task_Det-bbox_256x192) AP50 90.7 #5 of 11 Archive leaderboard report
Pose Estimation COCO val2017 ViTPose-B (Single-task_Det-bbox_256x192) AP75 83.2 #5 of 11 Archive leaderboard report
Pose Estimation COCO val2017 ViTPose-B (Single-task_Det-bbox_256x192) AR 81.1 #5 of 11 Archive leaderboard report
Pose Estimation CrowdPose ViTPose-G AP 78.3 #2 of 12 Archive leaderboard report
Pose Estimation CrowdPose ViTPose-G AP Hard 67.9 #2 of 12 Archive leaderboard report
Pose Estimation CrowdPose ViTPose-G AP50 85.3 #2 of 12 Archive leaderboard report
Pose Estimation CrowdPose ViTPose-G AP75 81.4 #2 of 12 Archive leaderboard report
Pose Estimation CrowdPose ViTPose-G APM 86.6 #2 of 12 Archive leaderboard report
Pose Estimation OCHuman ViTPose (ViTAE-G, GT bounding boxes) Test AP 93.3 #1 of 19 Archive leaderboard report
Pose Estimation OCHuman ViTPose (ViTAE-G, GT bounding boxes) Validation AP 92.8 #1 of 19 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.

Methods

AttentionDense ConnectionsLayer NormalizationLinear LayerMulti-Head AttentionResidual ConnectionSoftmaxVision Transformer

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