Papers › Simple Baselines for Human Pose Estimation and Tracking

Simple Baselines for Human Pose Estimation and Tracking

17 Apr 2018ECCV 2018 9arXiv:1804.06208archive 2025-07-28

Bin Xiao, Haiping Wu, Yichen Wei

There has been significant progress on pose estimation and increasing interests on pose tracking in recent years. At the same time, the overall algorithm and system complexity increases as well, making the algorithm analysis and comparison more difficult. This work provides simple and effective baseline methods. They are helpful for inspiring and evaluating new ideas for the field. State-of-the-art results are achieved on challenging benchmarks. The code will be available at https://github.com/leoxiaobin/pose.pytorch.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page 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

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

leoxiaobin/pose.pytorch officialmentioned in paperpytorchMITSyntology: not harvested report
CuberrChen/HumanPoseBL-Paddle mentioned on GitHubpaddleSyntology: not harvested report
Microsoft/human-pose-estimation.pytorch 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 Human Pose Estimation (arXiv:1902.09212; that paper's own run record: 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); nothing checks that they implement this paper's method. report
Mind23-2/MindCode-77 mentioned on GitHubmindsporeSyntology: not harvested report
bearpaw/pytorch-pose mentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
dog-qiuqiu/MobileNetV2-SimplePose mentioned on GitHubmxnetSyntology: not harvested report
dog-qiuqiu/Ultralight-SimplePose mentioned on GitHubmxnetSyntology: not harvested report
leeyegy/SimDR mentioned on GitHubpytorchSyntology: not harvested report
leeyegy/simcc mentioned on GitHubpytorchSyntology: not harvested report
lyqcom/alphapose mentioned on GitHubmindsporeApache-2.0Syntology: not harvested report
mindspore-lab/mindone mentioned on GitHubmindsporenot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-readySyntology: not harvested report
mks0601/TF-SimpleHumanPose mentioned on GitHubtfSyntology: not harvested report
osmr/imgclsmob mentioned on GitHubmxnetMITSyntology: 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
samson6460/tf2_pose_estimation mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to U-Net: Convolutional Networks for Biomedical Image Segmentation (arXiv:1505.04597; that paper's own run record: 530 ran (of which 247 constructed an object rather than computing a result; 378 with no instrument failure: 18 honoured, 10 violated, 350 with no contract checked; 152 where Syntology's instrument failed) · 227 unverified) and Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation (arXiv:1802.02611; that paper's own run record: 44 ran (of which 17 constructed an object rather than computing a result; 28 with no instrument failure: 2 honoured, 0 violated, 26 with no contract checked; 16 where Syntology's instrument failed) · 28 unverified); nothing checks that they implement this paper's method. report
simochen/flowtrack.pytorch mentioned on GitHubpytorchSyntology: not harvested report
victimsnino/Simple-Baselines-for-Human-Pose-Estimation-and-Tracking-sample- mentioned on GitHubpytorchSyntology: not harvested report
victimsnino/pose-simple-baselines-demo.pytorch. mentioned on GitHubpytorchSyntology: not harvested report
2023-MindSpore-1/ms-code-216 mindsporeSyntology: not harvested report
2023-MindSpore-4/Code11 mindsporeSyntology: not harvested report
MegEngine/Models Syntology: not harvested 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
SunJuil-Ty/simplebaselines-mindspore mindsporeSyntology: not harvested report
code-implementation1/Code8 mindsporeSyntology: not harvested report
mindspore-ai/models mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets (arXiv:2208.08084; that paper's own run record: 4 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; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
mindspore-ai/models mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets (arXiv:2208.08084; that paper's own run record: 4 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; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
mindspore-ai/models mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets (arXiv:2208.08084; that paper's own run record: 4 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; 0 where Syntology's instrument failed) · 1 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

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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

2D Human Pose EstimationKeypoint DetectionMulti-Person Pose EstimationPose EstimationPose Tracking

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
2D Human Pose Estimation JHMDB (2D poses only) SimplePose PCK 94.4 #3 of 5 Archive leaderboard report
2D Human Pose Estimation OCHuman ResNet-152 Test AP 33.3 #6 of 11 Archive leaderboard report
2D Human Pose Estimation OCHuman ResNet-152 Validation AP 41.0 #6 of 11 Archive leaderboard report
2D Human Pose Estimation OCHuman ResNet-50 Test AP 30.4 #9 of 11 Archive leaderboard report
2D Human Pose Estimation OCHuman ResNet-50 Validation AP 37.8 #9 of 11 Archive leaderboard report
Keypoint Detection COCO (Common Objects in Context) ResNet-50 Validation AP 72.2 #22 of 24 Archive leaderboard report
Keypoint Detection COCO test-challenge Simple Base+* AP 74.5 #3 of 8 Archive leaderboard report
Keypoint Detection COCO test-challenge Simple Base+* AP50 90.9 #3 of 8 Archive leaderboard report
Keypoint Detection COCO test-challenge Simple Base+* AP75 80.8 #3 of 8 Archive leaderboard report
Keypoint Detection COCO test-challenge Simple Base+* APL 87.5 #3 of 8 Archive leaderboard report
Keypoint Detection COCO test-challenge Simple Base+* AR 80.5 #3 of 8 Archive leaderboard report
Keypoint Detection COCO test-challenge Simple Base+* AR50 95.1 #3 of 8 Archive leaderboard report
Keypoint Detection COCO test-challenge Simple Base+* AR75 86.3 #3 of 8 Archive leaderboard report
Keypoint Detection COCO test-challenge Simple Base+* ARL 82.9 #3 of 8 Archive leaderboard report
Keypoint Detection COCO test-challenge Simple Base+* ARM 75.3 #3 of 8 Archive leaderboard report
Keypoint Detection COCO test-dev Simple Base+* AP50 92.4 #2 of 16 Archive leaderboard report
Keypoint Detection COCO test-dev Simple Base+* AP75 84.0 #2 of 16 Archive leaderboard report
Keypoint Detection COCO test-dev Simple Base+* APL 82.7 #2 of 16 Archive leaderboard report
Keypoint Detection COCO test-dev Simple Base+* APM 73.0 #2 of 16 Archive leaderboard report
Keypoint Detection COCO test-dev Simple Base+* AR 81.5 #2 of 16 Archive leaderboard report
Keypoint Detection COCO test-dev Simple Base+* AR50 95.8 #2 of 16 Archive leaderboard report
Keypoint Detection COCO test-dev Simple Base+* AR75 88.2 #2 of 16 Archive leaderboard report
Keypoint Detection COCO test-dev Simple Base+* ARL 87.2 #2 of 16 Archive leaderboard report
Keypoint Detection COCO test-dev Simple Base+* ARM 77.4 #2 of 16 Archive leaderboard report
Keypoint Detection COCO test-dev Simple Base AP50 91.9 #5 of 16 Archive leaderboard report
Keypoint Detection COCO test-dev Simple Base AP75 81.1 #5 of 16 Archive leaderboard report
Keypoint Detection COCO test-dev Simple Base APL 80.0 #5 of 16 Archive leaderboard report
Keypoint Detection COCO test-dev Simple Base APM 70.3 #5 of 16 Archive leaderboard report
Keypoint Detection COCO test-dev Simple Base AR 79.0 #5 of 16 Archive leaderboard report
Keypoint Detection OCHuman ResNet-152 Test AP 33.3 #5 of 10 Archive leaderboard report
Keypoint Detection OCHuman ResNet-152 Validation AP 41.0 #5 of 10 Archive leaderboard report
Keypoint Detection OCHuman ResNet-50 Test AP 29.5 #8 of 10 Archive leaderboard report
Keypoint Detection OCHuman ResNet-50 Validation AP 32.1 #8 of 10 Archive leaderboard report
Multi-Person Pose Estimation CrowdPose Simple baseline AP Easy 71.4 #22 of 28 Archive leaderboard report
Multi-Person Pose Estimation CrowdPose Simple baseline AP Hard 51.2 #22 of 28 Archive leaderboard report
Multi-Person Pose Estimation CrowdPose Simple baseline AP Medium 61.2 #22 of 28 Archive leaderboard report
Multi-Person Pose Estimation CrowdPose Simple baseline mAP @0.5:0.95 60.8 #22 of 28 Archive leaderboard report
Multi-Person Pose Estimation OCHuman SimplePose AP50 37.4 #7 of 8 Archive leaderboard report
Multi-Person Pose Estimation OCHuman SimplePose AP75 26.8 #7 of 8 Archive leaderboard report
Multi-Person Pose Estimation OCHuman SimplePose Validation AP 24.1 #7 of 8 Archive leaderboard report
Pose Estimation AIC SimpleBaseline (ResNet-152) AP 29.9 #8 of 10 Archive leaderboard report
Pose Estimation AIC SimpleBaseline (ResNet-152) AP50 73.8 #8 of 10 Archive leaderboard report
Pose Estimation AIC SimpleBaseline (ResNet-152) AP75 18.3 #8 of 10 Archive leaderboard report
Pose Estimation AIC SimpleBaseline (ResNet-152) AR 34.3 #8 of 10 Archive leaderboard report
Pose Estimation AIC SimpleBaseline (ResNet-152) AR50 76.9 #8 of 10 Archive leaderboard report
Pose Estimation AIC SimpleBaseline (ResNet-101) AP 29.4 #9 of 10 Archive leaderboard report
Pose Estimation AIC SimpleBaseline (ResNet-101) AP50 73.6 #9 of 10 Archive leaderboard report
Pose Estimation AIC SimpleBaseline (ResNet-101) AP75 17.4 #9 of 10 Archive leaderboard report
Pose Estimation AIC SimpleBaseline (ResNet-101) AR 33.7 #9 of 10 Archive leaderboard report
Pose Estimation AIC SimpleBaseline (ResNet-101) AR50 76.3 #9 of 10 Archive leaderboard report
Pose Estimation AIC SimpleBaseline (ResNet-50) AP 28.0 #10 of 10 Archive leaderboard report
Pose Estimation AIC SimpleBaseline (ResNet-50) AP50 71.6 #10 of 10 Archive leaderboard report
Pose Estimation AIC SimpleBaseline (ResNet-50) AP75 15.8 #10 of 10 Archive leaderboard report
Pose Estimation AIC SimpleBaseline (ResNet-50) AR 32.1 #10 of 10 Archive leaderboard report
Pose Estimation AIC SimpleBaseline (ResNet-50) AR50 74.1 #10 of 10 Archive leaderboard report
Pose Estimation COCO test-dev Flow-based (ResNet-152) AP 73.7 #25 of 47 Archive leaderboard report
Pose Estimation COCO test-dev Flow-based (ResNet-152) AP50 91.9 #25 of 47 Archive leaderboard report
Pose Estimation COCO test-dev Flow-based (ResNet-152) AP75 81.1 #25 of 47 Archive leaderboard report
Pose Estimation COCO test-dev Flow-based (ResNet-152) APL 80 #25 of 47 Archive leaderboard report
Pose Estimation COCO test-dev Flow-based (ResNet-152) APM 70.3 #25 of 47 Archive leaderboard report
Pose Estimation COCO test-dev Flow-based (ResNet-152) AR 79 #25 of 47 Archive leaderboard report
Pose Estimation COCO val2017 SimpleBaseLine (256x192) AP 70.4 #11 of 11 Archive leaderboard report
Pose Estimation COCO val2017 SimpleBaseLine (256x192) AP50 - #11 of 11 Archive leaderboard report
Pose Estimation COCO val2017 SimpleBaseLine (256x192) AP75 - #11 of 11 Archive leaderboard report
Pose Estimation COCO val2017 SimpleBaseLine (256x192) AR - #11 of 11 Archive leaderboard report
Pose Estimation OCHuman ResNet-152 Test AP 33.3 #14 of 19 Archive leaderboard report
Pose Estimation OCHuman ResNet-152 Validation AP 41.0 #14 of 19 Archive leaderboard report
Pose Estimation OCHuman ResNet-50 Test AP 29.5 #17 of 19 Archive leaderboard report
Pose Estimation OCHuman ResNet-50 Validation AP 32.1 #17 of 19 Archive leaderboard report
Pose Tracking PoseTrack2017 MSRA (FlowTrack) MOTA 57.81 #5 of 10 Archive leaderboard report
Pose Tracking PoseTrack2017 MSRA (FlowTrack) mAP 74.57 #5 of 10 Archive leaderboard report
Pose Tracking PoseTrack2018 MSRA MOTA 61.37 #4 of 5 Archive leaderboard report
Pose Tracking PoseTrack2018 MSRA mAP 74.03 #4 of 5 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

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionGlobal Average PoolingKaiming InitializationMax PoolingReLUResidual BlockResidual Connection

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