Papers › Deep High-Resolution Representation Learning for Human Pose Estimation

Deep High-Resolution Representation Learning for Human Pose Estimation

25 Feb 2019CVPR 2019 6arXiv:1902.09212archive 2025-07-28

Ke Sun, Bin Xiao, Dong Liu, Jingdong Wang

This is an official pytorch implementation of Deep High-Resolution Representation Learning for Human Pose Estimation. In this work, we are interested in the human pose estimation problem with a focus on learning reliable high-resolution representations. Most existing methods recover high-resolution representations from low-resolution representations produced by a high-to-low resolution network. Instead, our proposed network maintains high-resolution representations through the whole process. We start from a high-resolution subnetwork as the first stage, gradually add high-to-low resolution subnetworks one by one to form more stages, and connect the mutli-resolution subnetworks in parallel. We conduct repeated multi-scale fusions such that each of the high-to-low resolution representations receives information from other parallel representations over and over, leading to rich high-resolution representations. As a result, the predicted keypoint heatmap is potentially more accurate and spatially more precise. We empirically demonstrate the effectiveness of our network through the superior pose estimation results over two benchmark datasets: the COCO keypoint detection dataset and the MPII Human Pose dataset. The code and models have been publicly available at https://github.com/leoxiaobin/deep-high-resolution-net.pytorch.

PaperPDFConference PDFCodeCode Syntology ran

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 25 code samples harvested from 6 repositories linked to this paper: 16 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 8 where Syntology's instrument failed) · 9 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 4 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 9 samples from 1 repository, 8 ran (4 with no instrument failure; 4 where Syntology's instrument failed); community (archive-listed): 16 samples from 5 repositories, 8 ran (4 with no instrument failure; 4 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 13 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 16 samples that ran have no recorded date.

39 repositories listed; official and paper-mentioned ones first.

leoxiaobin/deep-high-resolution-net.pytorch officialmentioned in papermentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarks (arXiv:2105.06152; that paper's own run record: 14 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 7 where Syntology's instrument failed) · 11 unverified); nothing checks that they implement this paper's method. report
Microsoft/human-pose-estimation.pytorch officialmentioned in paperpytorchMITSyntology: 9 samples, 8 ran (4 instrument-failed) · 1 unverified report
CASIA-IVA-Lab/ISP-reID mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Identity-Guided Human Semantic Parsing for Person Re-Identification (arXiv:2007.13467; that paper's own run record: 6 ran (of which 0 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) · 1 unverified); nothing checks that they implement this paper's method. report
HRNet/HRNet-Facial-Landmark-Detection mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep High-Resolution Representation Learning for Visual Recognition (arXiv:1908.07919; that paper's own run record: 21 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 1 violated, 15 with no contract checked; 5 where Syntology's instrument failed) · 13 unverified); nothing checks that they implement this paper's method. report
HRNet/HRNet-Human-Pose-Estimation mentioned on GitHubpytorchSyntology: not harvested report
HRNet/HRNet-Image-Classification mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep High-Resolution Representation Learning for Visual Recognition (arXiv:1908.07919; that paper's own run record: 21 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 1 violated, 15 with no contract checked; 5 where Syntology's instrument failed) · 13 unverified); nothing checks that they implement this paper's method. report
HRNet/HRNet-MaskRCNN-Benchmark mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
HRNet/HRNet-Object-Detection mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
HRNet/HRNet-Semantic-Segmentation mentioned on GitHubpytorchNOASSERTIONSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation (arXiv:1909.11065; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
Mary-xl/HRnet_Kaggle_iNat2019_FGVC mentioned on GitHubpytorchSyntology: not harvested report
NU-LL/lighttrack- mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to LightTrack: A Generic Framework for Online Top-Down Human Pose Tracking (arXiv:1905.02822; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
NVlabs/PAMTRI mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
Vill-Lab/2022-TIP-HCGA mentioned on GitHubpytorchMITSyntology: 8 samples, 6 ran (2 instrument-failed) · 2 unverified report
abhi1kumar/hrnet_pose_single_gpu mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation (arXiv:1908.10357; that paper's own run record: 17 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 4 where Syntology's instrument failed) · 10 unverified); nothing checks that they implement this paper's method. report
anshky/HR-NET mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation (arXiv:1908.10357; that paper's own run record: 17 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 4 where Syntology's instrument failed) · 10 unverified); nothing checks that they implement this paper's method. report
baoshengyu/deep-high-resolution-net.pytorch mentioned on GitHubpytorchMITSyntology: not harvested report
chuanqichen/deepcoaching mentioned on GitHubpytorchSyntology: not harvested report
ducongju/HRNet mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation (arXiv:1908.10357; that paper's own run record: 17 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 4 where Syntology's instrument failed) · 10 unverified); nothing checks that they implement this paper's method. report
goutern/PoseEstimation mentioned on GitHubpytorchSyntology: not harvested report
gox-ai/hrnet-pose-api mentioned on GitHubpytorchMITSyntology: not harvested report
k-miran/hear mentioned on GitHubMITSyntology: not harvested report
ken724049/action-recognition mentioned on GitHubSyntology: not harvested report
laowang666888/HRNET mentioned on GitHubpytorchMITSyntology: not harvested report
leeyegy/SimDR mentioned on GitHubpytorchSyntology: not harvested report
leeyegy/simcc mentioned on GitHubpytorchSyntology: not harvested report
mks0601/PoseFix_RELEASE mentioned on GitHubtfMITSyntology: 4 samples, 0 ran · 4 unverified report
sdll/hrnet-pose-estimation mentioned on GitHubpytorchMITSyntology: not harvested report
strivebo/image_segmentation_dl mentioned on GitHubtfSyntology: not harvested report
thomasslloyd/FitSpatial mentioned on GitHubSyntology: not harvested report
v1viswan/Domain_adaptation_in_HRNet mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
visionNoob/hrnet_pytorch mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
wsjzha/deep-high-resolution-net.pytorch mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
PaddlePaddle/PaddleDetection paddleSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to PP-YOLOE: An evolved version of YOLO (arXiv:2203.16250; that paper's own run record: 22 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 2 honoured, 0 violated, 17 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
mindspore-lab/mindone mindsporenot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-readySyntology: not harvested report
open-mmlab/mmdetection pytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to An Open and Comprehensive Pipeline for Unified Object Grounding and Detection (arXiv:2401.02361; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
open-mmlab/mmpose pytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RTMO: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimation (arXiv:2312.07526; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
osmr/imgclsmob mxnetMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ResNeSt: Split-Attention Networks (arXiv:2004.08955; that paper's own run record: 28 ran (of which 0 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 0 violated, 21 with no contract checked; 7 where Syntology's instrument failed) · 20 unverified); nothing checks that they implement this paper's method. report
thoughtmachines/Human-Pose-Estimation-using-HRNets pytorchnot reachable when probed 2026-09-18 — repositories for recent papers often appear after camera-readySyntology: 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.

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

25 samples harvested: 16 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 8 where Syntology's instrument failed) · 9 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.

4ran · our draft was wrong
4ran; the contract check could not run
8ran
9unverified

Licence: 2 of the 25 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 6 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”. “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.

Microsoft/human-pose-estimation.pytorch official repository 9 samples, 8 ran (4 instrument-failed) · 1 unverified
calc_dists in 7 papers lib/core/evaluate.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · b91b38261b03587d · report fixture: signature preds:ndarray/3/float, target:ndarray/3/float, normalize:ndarray/1/float · returned ndarray · level recorded 2026-09-22
conv3x3 in 1,376 papers lib/models/pose_resnet.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · fac5364e2f53c6db · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded
cpu_nms_wrapper lib/nms/nms.py ran MIT (permissive) · 0bdca114d99f4177 · report fixture: signature thresh:float/0/float · returned function · level recorded 2026-09-25
dist_acc in 7 papers lib/core/evaluate.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 1c2da88027e6e151 · report fixture: signature dists:ndarray/1/float, thr:float/0/float · returned float64 · level recorded 2026-09-22
get_max_preds in 8 papers lib/core/inference.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic fingerprinted MIT (permissive) · 55c58ef5f795e3d1 · report fixture: signature batch_heatmaps:ndarray/4/float · returned tuple · level recorded 2026-09-22
get_model_name in 34 papers lib/core/config.py ran MIT (permissive) · 18f7aa997852bcc0 · report fixture: signature cfg:Config/0/? · returned tuple · level recorded 2026-09-25
gpu_nms_wrapper lib/nms/nms.py ran MIT (permissive) · 167b862a31de0adf · report fixture: signature thresh:float/0/float, device_id:int/0/int · returned function · level recorded 2026-09-25
py_nms_wrapper lib/nms/nms.py ran MIT (permissive) · 8551f210abffd79e · report fixture: signature thresh:float/0/float · returned function · level recorded 2026-09-25
get_pose_net in 15 papers lib/models/pose_resnet.py unverified MIT (permissive) · 9dfb17266423d20d · report
HRNet/HRNet-MaskRCNN-Benchmark community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
calc_iou in 17 papers tools/test_net.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed fingerprinted MIT (permissive) · 451bcfd505206dce · report fixture: signature a:list/1/int, b:list/1/int · returned float · level recorded 2026-09-22
voting tools/test_net.py ran · our draft was wrong MIT (permissive) · bb37605b18846a6b · report fixture: returned list · level recorded 2026-09-22
Vill-Lab/2022-TIP-HCGA community (archive-listed) 8 samples, 6 ran (2 instrument-failed) · 2 unverified
euclidean_dist in 69 papers
census: 12 implementations from 14 papers, 3 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
layers/triplet_loss.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · c83d9f7fca950b77 · report fixture: signature x:Tensor/2/float, y:Tensor/2/float · returned Tensor · level recorded, date not recorded
hard_example_mining in 9 papers layers/triplet_loss.py ran MIT (permissive) · 93f2c0b80ea7f36e · report fixture: signature dist_mat:Tensor/2/float, labels:Tensor/1/int, return_inds:bool/0/bool · returned tuple · level recorded 2026-09-25
normalize in 638 papers
census: 70 implementations from 82 papers, 51 distinct outputs across 11 buckets, one shared input per bucket this sample: bucket 1 of 11, arg 1: rank 2, kind float, dtype float32
layers/triplet_loss.py ran · our draft was wrong fingerprinted MIT (permissive) · e3b2a83f52101f2d · report fixture: signature x:Tensor/2/float, axis:int/0/int · returned Tensor · level recorded 2026-09-22
pil_loader in 144 papers engine/clustering.py ran MIT (permissive) · 1508ae9fb90b8de1 · report fixture: signature path:str/0/str · returned Image · level recorded 2026-09-25
preprocess_features in 20 papers engine/clustering.py ran MIT (permissive) · 53f8b1e59f08664a · report fixture: signature npdata:ndarray/2/float, norm:bool/0/bool, pca:int/0/int · returned ndarray · level recorded 2026-09-25
split_n deep_feature_clustersing.py ran fingerprinted MIT (permissive) · 1be7fb0ef331f2a5 · report fixture: signature seq:list/1/int, num:int/0/int · returned list · level recorded 2026-09-24
clustering in 10 papers deep_feature_clustersing.py unverified MIT (permissive) · 5d13a519b4ca488b · report
make_graph in 9 papers engine/clustering.py unverified MIT (permissive) · c1ac4ee52106027c · report
mks0601/PoseFix_RELEASE community (archive-listed) 4 samples, 0 ran · 4 unverified
aggregate_batch lib/tfflat/net_utils.py unverified MIT (permissive) · d9b08c7049915445 · report
average_gradients in 20 papers lib/tfflat/net_utils.py unverified MIT (permissive) · 94ffb5d47eee6270 · report
get_variables_in_checkpoint_file lib/tfflat/saver.py unverified MIT (permissive) · 27cc68d97f7be674 · report
sum_gradients lib/tfflat/net_utils.py unverified MIT (permissive) · 3eb931c10df5890d · report
visionNoob/hrnet_pytorch community (archive-listed) 1 sample, 0 ran · 1 unverified
get_pose_net in 15 papers lib/models/pose_hrnet.py unverified MIT (permissive) · 78015ae361e585ca · report
wsjzha/deep-high-resolution-net.pytorch community (archive-listed) 1 sample, 0 ran · 1 unverified
get_pose_net in 15 papers lib/models/pose_hrnet.py unverified MIT (permissive) · 2534c81208f21998 · report

Tasks

2D Human Pose Estimation2D Pose Estimation3D Human Pose Estimation3D Pose EstimationInstance SegmentationKeypoint DetectionMulti-Person Pose EstimationObject DetectionPose EstimationPose TrackingRepresentation LearningVocal Bursts Intensity Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
2D Human Pose Estimation COCO-WholeBody HRNet WB 43.2 #12 of 15 Archive leaderboard report
2D Human Pose Estimation COCO-WholeBody HRNet body 65.9 #12 of 15 Archive leaderboard report
2D Human Pose Estimation COCO-WholeBody HRNet face 52.3 #12 of 15 Archive leaderboard report
2D Human Pose Estimation COCO-WholeBody HRNet foot 31.4 #12 of 15 Archive leaderboard report
2D Human Pose Estimation COCO-WholeBody HRNet hand 30.0 #12 of 15 Archive leaderboard report
2D Human Pose Estimation Human-Art HRNet-w48 AP 0.417 #5 of 10 Archive leaderboard report
2D Human Pose Estimation Human-Art HRNet-w48 AP (gt bbox) 0.769 #5 of 10 Archive leaderboard report
2D Human Pose Estimation Human-Art HRNet-w32 AP 0.399 #7 of 10 Archive leaderboard report
2D Human Pose Estimation Human-Art HRNet-w32 AP (gt bbox) 0.754 #7 of 10 Archive leaderboard report
2D Pose Estimation HARPER HRNet PCK 86,8 #1 of 1 Archive leaderboard report
3D Pose Estimation HARPER HRNet + Depth Average MPJPE (mm) 151 #1 of 1 Archive leaderboard report
Instance Segmentation COCO minival HTC (HRNetV2p-W48) mask AP 41.0 #68 of 93 Archive leaderboard report
Keypoint Detection COCO (Common Objects in Context) HRNet-48(384x288) Test AP 75.5 #9 of 24 Archive leaderboard report
Keypoint Detection COCO (Common Objects in Context) HRNet-48(384x288) Validation AP 76.3 #9 of 24 Archive leaderboard report
Keypoint Detection COCO (Common Objects in Context) HRNet-32 Validation AP 75.8 #21 of 24 Archive leaderboard report
Keypoint Detection COCO test-dev HRNet* AP50 92.7 #1 of 16 Archive leaderboard report
Keypoint Detection COCO test-dev HRNet* AP75 84.5 #1 of 16 Archive leaderboard report
Keypoint Detection COCO test-dev HRNet* APL 83.1 #1 of 16 Archive leaderboard report
Keypoint Detection COCO test-dev HRNet* APM 73.4 #1 of 16 Archive leaderboard report
Keypoint Detection COCO test-dev HRNet* AR 82.0 #1 of 16 Archive leaderboard report
Keypoint Detection COCO test-dev HRNet AP50 92.5 #4 of 16 Archive leaderboard report
Keypoint Detection COCO test-dev HRNet AP75 83.3 #4 of 16 Archive leaderboard report
Keypoint Detection COCO test-dev HRNet APL 81.5 #4 of 16 Archive leaderboard report
Keypoint Detection COCO test-dev HRNet APM 71.9 #4 of 16 Archive leaderboard report
Keypoint Detection COCO test-dev HRNet AR 80.5 #4 of 16 Archive leaderboard report
Pose Estimation AIC HRNet (HRNet-w48 ) AP 33.5 #5 of 10 Archive leaderboard report
Pose Estimation AIC HRNet (HRNet-w48 ) AP50 78.0 #5 of 10 Archive leaderboard report
Pose Estimation AIC HRNet (HRNet-w48 ) AP75 23.6 #5 of 10 Archive leaderboard report
Pose Estimation AIC HRNet (HRNet-w48 ) AR 37.9 #5 of 10 Archive leaderboard report
Pose Estimation AIC HRNet (HRNet-w48 ) AR50 80.0 #5 of 10 Archive leaderboard report
Pose Estimation AIC HRNet (HRNet-w32) AP 32.3 #6 of 10 Archive leaderboard report
Pose Estimation AIC HRNet (HRNet-w32) AP50 76.2 #6 of 10 Archive leaderboard report
Pose Estimation AIC HRNet (HRNet-w32) AP75 21.9 #6 of 10 Archive leaderboard report
Pose Estimation AIC HRNet (HRNet-w32) AR 36.6 #6 of 10 Archive leaderboard report
Pose Estimation AIC HRNet (HRNet-w32) AR50 78.9 #6 of 10 Archive leaderboard report
Pose Estimation BRACE HRNet fine-tuned on BRACE Average Precision 0.357 #1 of 2 Archive leaderboard report
Pose Estimation BRACE HRNet fine-tuned on BRACE Average Recall 0.445 #1 of 2 Archive leaderboard report
Pose Estimation BRACE HRNet pre-trained on COCO Average Precision 0.158 #2 of 2 Archive leaderboard report
Pose Estimation BRACE HRNet pre-trained on COCO Average Recall 0.202 #2 of 2 Archive leaderboard report
Pose Estimation COCO test-dev HRNet-W48 + extra data AP 77 #12 of 47 Archive leaderboard report
Pose Estimation COCO test-dev HRNet-W48 + extra data AP50 92.7 #12 of 47 Archive leaderboard report
Pose Estimation COCO test-dev HRNet-W48 + extra data AP75 84.5 #12 of 47 Archive leaderboard report
Pose Estimation COCO test-dev HRNet-W48 + extra data APL 83.1 #12 of 47 Archive leaderboard report
Pose Estimation COCO test-dev HRNet-W48 + extra data APM 73.4 #12 of 47 Archive leaderboard report
Pose Estimation COCO test-dev HRNet-W48 + extra data AR 82 #12 of 47 Archive leaderboard report
Pose Estimation COCO val2017 HRNet (256x192) AP 75.3 #7 of 11 Archive leaderboard report
Pose Estimation COCO val2017 HRNet (256x192) AP50 - #7 of 11 Archive leaderboard report
Pose Estimation COCO val2017 HRNet (256x192) AP75 - #7 of 11 Archive leaderboard report
Pose Estimation COCO val2017 HRNet (256x192) AR - #7 of 11 Archive leaderboard report
Pose Estimation MPII Human Pose HRNet-W32 PCKh-0.5 92.3 #11 of 46 Archive leaderboard report
Pose Tracking PoseTrack2017 HRNet-W48 COCO MOTA 57.93 #4 of 10 Archive leaderboard report
Pose Tracking PoseTrack2017 HRNet-W48 COCO mAP 74.95 #4 of 10 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

Heatmap

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