Papers › Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition

Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition

31 Mar 2020CVPR 2020 6arXiv:2003.14111archive 2025-07-28

Ziyu Liu, Hongwen Zhang, Zhenghao Chen, Zhiyong Wang, Wanli Ouyang

Spatial-temporal graphs have been widely used by skeleton-based action recognition algorithms to model human action dynamics. To capture robust movement patterns from these graphs, long-range and multi-scale context aggregation and spatial-temporal dependency modeling are critical aspects of a powerful feature extractor. However, existing methods have limitations in achieving (1) unbiased long-range joint relationship modeling under multi-scale operators and (2) unobstructed cross-spacetime information flow for capturing complex spatial-temporal dependencies. In this work, we present (1) a simple method to disentangle multi-scale graph convolutions and (2) a unified spatial-temporal graph convolutional operator named G3D. The proposed multi-scale aggregation scheme disentangles the importance of nodes in different neighborhoods for effective long-range modeling. The proposed G3D module leverages dense cross-spacetime edges as skip connections for direct information propagation across the spatial-temporal graph. By coupling these proposals, we develop a powerful feature extractor named MS-G3D based on which our model outperforms previous state-of-the-art methods on three large-scale datasets: NTU RGB+D 60, NTU RGB+D 120, and Kinetics Skeleton 400.

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="2003.14111")

Code

Syntology Ran 3 of 3 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 2 ran · honoured contract; 1 ran · our draft was wrong.

By repository: official repository: 3 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

kenziyuliu/ms-g3d officialmentioned in papermentioned on GitHubpytorch report
kennymckormick/pyskl mentioned on GitHubpytorch report
metrics-lab/st-fmri 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

3 samples harvested; 3 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
1ran · our draft was wrong

Licence: 0 of the 3 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 kenziyuliu/ms-g3d. “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.

get_nonzero_std kenziyuliu/ms-g3d/data_gen/ntu_gendata.py official repository ran · honoured contract fingerprinted MIT (permissive) · 47a234b123ed6809 · report
read_skeleton_filter kenziyuliu/ms-g3d/data_gen/ntu_gendata.py official repository ran · our draft was wrong MIT (permissive) · c6381bb48f81a144 · report
read_xyz kenziyuliu/ms-g3d/data_gen/ntu_gendata.py official repository ran · honoured contract MIT (permissive) · 7e6ab20b3ba9e367 · report

Tasks

3D Action RecognitionAction RecognitionLong-range modelingSkeleton Based Action Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Action Recognition Assembly101 MS-G3D Actions Top-1 28.7 #4 of 7 Archive leaderboard report
3D Action Recognition Assembly101 MS-G3D Object Top-1 36.3 #4 of 7 Archive leaderboard report
3D Action Recognition Assembly101 MS-G3D Verbs Top-1 65.7 #4 of 7 Archive leaderboard report
Action Recognition H2O (2 Hands and Objects) MS-G3D Actions Top-1 50.83 #11 of 11 Archive leaderboard report
Action Recognition H2O (2 Hands and Objects) MS-G3D Hand Pose 3D #11 of 11 Archive leaderboard report
Action Recognition H2O (2 Hands and Objects) MS-G3D Object Label No #11 of 11 Archive leaderboard report
Action Recognition H2O (2 Hands and Objects) MS-G3D Object Pose No #11 of 11 Archive leaderboard report
Action Recognition H2O (2 Hands and Objects) MS-G3D RGB No #11 of 11 Archive leaderboard report
Skeleton Based Action Recognition Kinetics-Skeleton dataset MS-G3D Accuracy 38.0 #10 of 42 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D MS-G3D Net Accuracy (CS) 91.5 #40 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D MS-G3D Net Accuracy (CV) 96.2 #40 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 MS-G3D Net Accuracy (Cross-Setup) 88.4% #38 of 83 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 MS-G3D Net Accuracy (Cross-Subject) 86.9% #38 of 83 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

Introduced by this paper: G3D

G3D

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