Papers › Semantic Graph Convolutional Networks for 3D Human Pose Regression

Semantic Graph Convolutional Networks for 3D Human Pose Regression

6 Apr 2019CVPR 2019 6arXiv:1904.03345archive 2025-07-28

Long Zhao, Xi Peng, Yu Tian, Mubbasir Kapadia, Dimitris N. Metaxas

In this paper, we study the problem of learning Graph Convolutional Networks (GCNs) for regression. Current architectures of GCNs are limited to the small receptive field of convolution filters and shared transformation matrix for each node. To address these limitations, we propose Semantic Graph Convolutional Networks (SemGCN), a novel neural network architecture that operates on regression tasks with graph-structured data. SemGCN learns to capture semantic information such as local and global node relationships, which is not explicitly represented in the graph. These semantic relationships can be learned through end-to-end training from the ground truth without additional supervision or hand-crafted rules. We further investigate applying SemGCN to 3D human pose regression. Our formulation is intuitive and sufficient since both 2D and 3D human poses can be represented as a structured graph encoding the relationships between joints in the skeleton of a human body. We carry out comprehensive studies to validate our method. The results prove that SemGCN outperforms state of the art while using 90% fewer parameters.

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="1904.03345")

Code

Syntology Ran 2 of 8 code samples harvested from 1 repository linked to this paper; 6 have no recorded run. Of those that ran: 2 ran with no contract checked.

By repository: official repository: 8 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

garyzhao/SemGCN officialmentioned in papermentioned on GitHubpytorchApache-2.0 report
happyvictor008/High-order-GNN-LF-iter mentioned on GitHubpytorch report
sjtuxcx/ITES mentioned on GitHubpytorch report
tamasino52/Any-GCN mentioned on GitHubpytorch report
zhimingzo/modulated-gcn mentioned on GitHubpytorch 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

8 samples harvested; 2 ran; 0 honoured the contract we drafted; 6 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.

2ran
6unverified

Licence: 0 of the 8 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 garyzhao/SemGCN. “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.

mpjpe garyzhao/SemGCN/common/loss.py official repository ran fingerprinted Apache-2.0 (permissive) · 3afb541a8147d123 · report
p_mpjpe garyzhao/SemGCN/common/loss.py official repository ran Apache-2.0 (permissive) · 29d56deadc8fcd3c · report
create_2d_data garyzhao/SemGCN/common/data_utils.py official repository unverified Apache-2.0 (permissive) · c1285546d25a021d · report
fetch garyzhao/SemGCN/common/data_utils.py official repository unverified Apache-2.0 (permissive) · a01e37bb132ecaf4 · report
image_coordinates garyzhao/SemGCN/common/camera.py official repository unverified Apache-2.0 (permissive) · 7669d6b1ce1e7096 · report
normalize_screen_coordinates garyzhao/SemGCN/common/camera.py official repository unverified Apache-2.0 (permissive) · 82baf6aa4fb040a1 · report
read_3d_data garyzhao/SemGCN/common/data_utils.py official repository unverified Apache-2.0 (permissive) · 2bc24c0c1c934d2d · report
weighted_mpjpe garyzhao/SemGCN/common/loss.py official repository unverified Apache-2.0 (permissive) · 6dd3ba892d9349d8 · report

Tasks

3D Human Pose EstimationMonocular 3D Human Pose Estimationregression

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Human Pose Estimation Human3.6M SemGCN Average MPJPE (mm) 57.6 #79 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M SemGCN Multi-View or Monocular Monocular #79 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M SemGCN Using 2D ground-truth joints No #79 of 88 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M SemGCN Average MPJPE (mm) 57.6 #28 of 52 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M SemGCN Frames Needed 1 #28 of 52 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M SemGCN Need Ground Truth 2D Pose No #28 of 52 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M SemGCN Use Video Sequence No #28 of 52 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

ConvolutionGraph Convolutional Networks

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