Papers › Convolutional Pose Machines

Convolutional Pose Machines

30 Jan 2016CVPR 2016 6arXiv:1602.00134archive 2025-07-28

Shih-En Wei, Varun Ramakrishna, Takeo Kanade, Yaser Sheikh

Pose Machines provide a sequential prediction framework for learning rich implicit spatial models. In this work we show a systematic design for how convolutional networks can be incorporated into the pose machine framework for learning image features and image-dependent spatial models for the task of pose estimation. The contribution of this paper is to implicitly model long-range dependencies between variables in structured prediction tasks such as articulated pose estimation. We achieve this by designing a sequential architecture composed of convolutional networks that directly operate on belief maps from previous stages, producing increasingly refined estimates for part locations, without the need for explicit graphical model-style inference. Our approach addresses the characteristic difficulty of vanishing gradients during training by providing a natural learning objective function that enforces intermediate supervision, thereby replenishing back-propagated gradients and conditioning the learning procedure. We demonstrate state-of-the-art performance and outperform competing methods on standard benchmarks including the MPII, LSP, and FLIC datasets.

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1602.00134")

Code

Syntology Ran 1 of 4 code samples harvested from 2 repositories linked to this paper; 3 have no recorded run. Of those that ran: 1 ran · fixture could not drive it.

By repository: community (archive-listed): 3 samples from 2 repositories, 1 ran; 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

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

CMU-Perceptual-Computing-Lab/convolutional-pose-machines-release officialmentioned in papermentioned on GitHubNOASSERTION report
CMU-Perceptual-Computing-Lab/openpose mentioned on GitHubpytorchNOASSERTION report
ClePol/CPM_Presentation mentioned on GitHub report
D1vyansh/BodyJointDetection mentioned on GitHubpytorch report
Kaif10/Pose-Detection mentioned on GitHub report
KarinaKorsgaard/Bartender-AI-OpenPose-Osc-Sender mentioned on GitHubpytorchNOASSERTION report
blake58/openpose mentioned on GitHubpytorchNOASSERTION report
chanyn/3Dpose_ssl mentioned on GitHubtf report
chengguixiong1010/rnn_STAF_2dpose mentioned on GitHubpytorchNOASSERTION report
delirecs/facial-keypoints-heatmaps mentioned on GitHubpytorch report
fcr3/OpenVINO_Tutorials mentioned on GitHubtf report
fcr3/wine_detector mentioned on GitHubtf report
fengyidong123/openpose-master mentioned on GitHubpytorch report
harshalsonioo1/hpe mentioned on GitHubpytorchNOASSERTION report
jarrodanderson/openpose-demo mentioned on GitHubpytorch report
jreisam/Unity-OpenPose-Edutable mentioned on GitHubNOASSERTION report
laobaiswag/openpose1 mentioned on GitHubpytorch report
liang-faan/openpose mentioned on GitHubpytorchNOASSERTION report
lncarter/Openpose mentioned on GitHubpytorch report
lwxGitHub123/openpose mentioned on GitHubpytorchNOASSERTION report
lwxGitHub123/openpose20200610 mentioned on GitHubpytorchNOASSERTION report
mayorquinmachines/YogAI mentioned on GitHubtfGPL-3.0 report
mgolnezhad/openpose mentioned on GitHubpytorchNOASSERTION report
mohammadreyaz/openposered mentioned on GitHubpytorchNOASSERTION report
mohammadreyaz/pose mentioned on GitHubpytorchNOASSERTION report
ostadabbas/in-bed-pose-estimation mentioned on GitHubBSD-3-Clause report
oublalkhalid/AI-OpenPose mentioned on GitHubpytorchApache-2.0 report
qdhill/openpose mentioned on GitHubpytorchNOASSERTION report
radioactiverockets/OpenPoseBreackoutGame mentioned on GitHubNOASSERTION report
shihenw/convolutional-pose-machines-release mentioned on GitHubtfNOASSERTION report
smellslikeml/YogAI mentioned on GitHubtfGPL-3.0 report
soulslicer/staf mentioned on GitHubpytorchNOASSERTION report
starman360/openpose_xavier mentioned on GitHubpytorchNOASSERTION report
techforgood-kiran/ai mentioned on GitHubpytorchNOASSERTION report
theyellowdiary/openpose mentioned on GitHubpytorchNOASSERTION report
xaoch/rapJetson2 mentioned on GitHubpytorch report
xar47x/pose mentioned on GitHubpytorchNOASSERTION report
xiaozeguo123/-Quick-Capture-system-HSR mentioned on GitHubpytorchNOASSERTION report
yikegami/openpose mentioned on GitHubpytorch report
yinzhiyan43/openpose-dev mentioned on GitHubpytorch report
yongsheng268/OpenPose mentioned on GitHubpytorchNOASSERTION report
zyxcambridge/openpose_all mentioned on GitHubpytorch report
open-mmlab/mmpose pytorchApache-2.0 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

4 samples harvested; 1 ran; 0 honoured the contract we drafted; 3 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · fixture could not drive it
3unverified

Licence: 3 of the 4 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 2 repositories linked to this paper, official or community; each sample names its own and says which. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

extract_keypoints Daniil-Osokin/gccpm-look-into-person-cvpr19.pytorch/val.py community (archive-listed) ran · fixture could not drive it fingerprinted Apache-2.0 (permissive) · f90c727f39d7a010 · report
gaussian_image digital-thinking/deep-posemachine/net.py community (archive-listed) unverified no licence file found · pointer only · 451f4f29e16e8085 · report
pdf_debug_img digital-thinking/deep-posemachine/net.py community (archive-listed) unverified no licence file found · pointer only · a0b7025f8f07f08f · report
normalize identical code first harvested elsewhere unverified licence of this copy not recorded · c79acdb155994f2a · report

Tasks

3D Human Pose EstimationCar Pose EstimationClassificationPose EstimationStructured Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Human Pose Estimation Total Capture Tri-CPM Average MPJPE (mm) 99 #12 of 14 Archive leaderboard report
Car Pose Estimation ApolloCar3D CPM Detection Rate 75.4 #3 of 3 Archive leaderboard report
Classification RSSCN7 CPM 1:1 Accuracy 50 #2 of 2 Archive leaderboard report
Pose Estimation FLIC Elbows Convolutional Pose Machines PCK@0.2 97.59% #2 of 2 Archive leaderboard report
Pose Estimation FLIC Wrists Convolutional Pose Machines PCK@0.2 95.03% #2 of 2 Archive leaderboard report
Pose Estimation J-HMDB CPM Mean PCK@0.2 91.9 #4 of 5 Archive leaderboard report
Pose Estimation Leeds Sports Poses Convolutional Pose Machines PCK 90.5% #11 of 18 Archive leaderboard report
Pose Estimation MPII Human Pose Convolutional Pose Machines PCKh-0.5 88.52 #32 of 46 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