Papers › Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition

Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition

23 Jan 2018arXiv:1801.07455archive 2025-07-28

Sijie Yan, Yuanjun Xiong, Dahua Lin

Dynamics of human body skeletons convey significant information for human action recognition. Conventional approaches for modeling skeletons usually rely on hand-crafted parts or traversal rules, thus resulting in limited expressive power and difficulties of generalization. In this work, we propose a novel model of dynamic skeletons called Spatial-Temporal Graph Convolutional Networks (ST-GCN), which moves beyond the limitations of previous methods by automatically learning both the spatial and temporal patterns from data. This formulation not only leads to greater expressive power but also stronger generalization capability. On two large datasets, Kinetics and NTU-RGBD, it achieves substantial improvements over mainstream methods.

PaperPDFCodeCode 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="1801.07455")

Code

Syntology Ran 2 of 2 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 2 ran · honoured contract.

By repository: community (archive-listed): 2 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.

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

yysijie/st-gcn officialmentioned in papermentioned on GitHubpytorch report
1zgh/st-gcn mentioned on GitHubpytorch report
AbiterVX/ST-GCN mentioned on GitHubpytorch report
DixinFan/st-gcn mentioned on GitHubpytorch report
GeyuanZhang/st-gcn-master mentioned on GitHubpytorch report
KrisLee512/ST-GCN mentioned on GitHubpytorch report
Powercoder64/TAA-GCN mentioned on GitHubpytorch report
TaatiTeam/stgcn_parkinsonism_prediction mentioned on GitHubpytorchNOASSERTION report
Tudouu/stgcn_light_op mentioned on GitHubpytorch report
XinzeWu/st-GCN mentioned on GitHubpytorch report
ZhangNYG/ST-GCN mentioned on GitHubpytorch report
antoniolq/st-gcn mentioned on GitHubpytorch report
ericksiavichay/cs230-final-project mentioned on GitHubpytorch report
github-zbx/ST-GCN mentioned on GitHubpytorch report
ken724049/action-recognition mentioned on GitHub report
kennymckormick/pyskl mentioned on GitHubpytorch report
l13025816/PGCN mentioned on GitHubpytorch report
metrics-lab/st-fmri mentioned on GitHubpytorch report
open-mmlab/mmskeleton mentioned on GitHubpytorch report
stillarrow/S2VT_ACT 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

2 samples harvested; 2 ran; 2 honoured the contract we drafted; 0 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 · honoured contract

Licence: 0 of the 2 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 open-mmlab/mmskeleton. “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.

iden open-mmlab/mmskeleton/mmskeleton/models/backbones/st_gcn_aaai18.py community (archive-listed) ran · honoured contract fingerprinted Apache-2.0 (permissive) · b8ec5cdbd4736df9 · report
zero open-mmlab/mmskeleton/mmskeleton/models/backbones/st_gcn_aaai18.py community (archive-listed) ran · honoured contract fingerprinted Apache-2.0 (permissive) · 0a17b477ccbcee05 · report

Tasks

3D Human Pose EstimationAction RecognitionMultimodal Activity RecognitionSkeleton Based Action RecognitionTemporal Action Localization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Recognition H2O (2 Hands and Objects) ST-GCN Actions Top-1 73.86 #10 of 11 Archive leaderboard report
Action Recognition H2O (2 Hands and Objects) ST-GCN Hand Pose 3D #10 of 11 Archive leaderboard report
Action Recognition H2O (2 Hands and Objects) ST-GCN Object Label No #10 of 11 Archive leaderboard report
Action Recognition H2O (2 Hands and Objects) ST-GCN Object Pose Yes #10 of 11 Archive leaderboard report
Action Recognition H2O (2 Hands and Objects) ST-GCN RGB No #10 of 11 Archive leaderboard report
Action Recognition ICVL-4 ST-GCN Accuracy 80.23% #2 of 2 Archive leaderboard report
Action Recognition IRD ST-GCN Accuracy 74.03% #2 of 2 Archive leaderboard report
Multimodal Activity Recognition EV-Action ST-GCN (Skeleton Kinect) Accuracy 79.6 #2 of 9 Archive leaderboard report
Multimodal Activity Recognition EV-Action ST-GCN (Skeleton Vicon) Accuracy 50.7 #7 of 9 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D ST-GCN [PYSKL, 3D Skeleton] Accuracy (CS) 90.7 #47 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D ST-GCN [PYSKL, 3D Skeleton] Accuracy (CV) 96.5 #47 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D ST-GCN [Vanilla, 2D Skeleton] Accuracy (CS) 90.1 #52 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D ST-GCN [Vanilla, 2D Skeleton] Accuracy (CV) 95.1 #52 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D ST-GCN [Vanilla, 3D Skeleton] Accuracy (CS) 86.6 #82 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D ST-GCN [Vanilla, 3D Skeleton] Accuracy (CV) 93.2 #82 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D ST-GCN Accuracy (CS) 81.5 #109 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D ST-GCN Accuracy (CV) 88.3 #109 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 ST-GCN [PYSKL, 3D Skeleton] Accuracy (Cross-Setup) 88.4 #41 of 83 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 ST-GCN [PYSKL, 3D Skeleton] Accuracy (Cross-Subject) 86.2 #41 of 83 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 ST-GCN [PYSKL, 2D Skeleton] Accuracy (Cross-Setup) 89.0 #48 of 83 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 ST-GCN [PYSKL, 2D Skeleton] Accuracy (Cross-Subject) 84.7 #48 of 83 Archive leaderboard report
Skeleton Based Action Recognition UAV-Human ST-GCN CSv1(%) 30.25 #8 of 9 Archive leaderboard report
Skeleton Based Action Recognition UAV-Human ST-GCN CSv2(%) 56.14 #8 of 9 Archive leaderboard report
Skeleton Based Action Recognition Varying-view RGB-D Action-Skeleton ST-GCN Accuracy (AV I) 53% #2 of 7 Archive leaderboard report
Skeleton Based Action Recognition Varying-view RGB-D Action-Skeleton ST-GCN Accuracy (AV II) 43% #2 of 7 Archive leaderboard report
Skeleton Based Action Recognition Varying-view RGB-D Action-Skeleton ST-GCN Accuracy (CS) 71% #2 of 7 Archive leaderboard report
Skeleton Based Action Recognition Varying-view RGB-D Action-Skeleton ST-GCN Accuracy (CV I) 25% #2 of 7 Archive leaderboard report
Skeleton Based Action Recognition Varying-view RGB-D Action-Skeleton ST-GCN Accuracy (CV II) 56% #2 of 7 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