Papers › Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition

Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition

23 Aug 2022ICCV 2023 1arXiv:2208.10741archive 2025-07-28

Jungho Lee, Minhyeok Lee, Dogyoon Lee, Sangyoun Lee

Graph convolutional networks (GCNs) are the most commonly used methods for skeleton-based action recognition and have achieved remarkable performance. Generating adjacency matrices with semantically meaningful edges is particularly important for this task, but extracting such edges is challenging problem. To solve this, we propose a hierarchically decomposed graph convolutional network (HD-GCN) architecture with a novel hierarchically decomposed graph (HD-Graph). The proposed HD-GCN effectively decomposes every joint node into several sets to extract major structurally adjacent and distant edges, and uses them to construct an HD-Graph containing those edges in the same semantic spaces of a human skeleton. In addition, we introduce an attention-guided hierarchy aggregation (A-HA) module to highlight the dominant hierarchical edge sets of the HD-Graph. Furthermore, we apply a new six-way ensemble method, which uses only joint and bone stream without any motion stream. The proposed model is evaluated and achieves state-of-the-art performance on four large, popular datasets. Finally, we demonstrate the effectiveness of our model with various comparative experiments.

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="2208.10741")

Code

Syntology Ran 8 of 11 code samples harvested from 1 repository linked to this paper; 3 have no recorded run. Of those that ran: 1 ran · violated contract; 2 ran · our draft was wrong; 5 ran with no contract checked.

By repository: official repository: 11 samples from 1 repository, 8 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Jho-Yonsei/HD-GCN officialmentioned in papermentioned on GitHubpytorchMIT 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

11 samples harvested; 8 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 · violated contract
2ran · our draft was wrong
5ran
3unverified

Licence: 0 of the 11 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 Jho-Yonsei/HD-GCN. “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.

downsample Jho-Yonsei/HD-GCN/feeders/tools.py official repository ran MIT (permissive) · 8b14974e8aa7320f · report
edge2mat Jho-Yonsei/HD-GCN/graph/tools.py official repository ran · our draft was wrong MIT (permissive) · 5f5ae82020ac7ec2 · report
import_class Jho-Yonsei/HD-GCN/model/HDGCN.py official repository ran · our draft was wrong MIT (permissive) · ffed4f85d50832c9 · report
ngpu Jho-Yonsei/HD-GCN/torchlight/torchlight/gpu.py official repository ran fingerprinted MIT (permissive) · 83ed4b272b1e38d0 · report
normalize_digraph Jho-Yonsei/HD-GCN/graph/tools.py official repository ran fingerprinted MIT (permissive) · abe9afd483b702d8 · report
str2bool Jho-Yonsei/HD-GCN/ensemble.py official repository ran · violated contract MIT (permissive) · a957019ca36a6747 · report
valid_crop_resize Jho-Yonsei/HD-GCN/feeders/tools.py official repository ran MIT (permissive) · 37939bae213ecfd4 · report
visible_gpu Jho-Yonsei/HD-GCN/torchlight/torchlight/gpu.py official repository ran fingerprinted MIT (permissive) · 621e08e84928c5c3 · report
get_spatial_graph Jho-Yonsei/HD-GCN/graph/tools.py official repository unverified MIT (permissive) · 795e24b648013e1d · report
str2dict Jho-Yonsei/HD-GCN/torchlight/torchlight/util.py official repository unverified MIT (permissive) · 1e89b2b546737164 · report
temporal_slice Jho-Yonsei/HD-GCN/feeders/tools.py official repository unverified MIT (permissive) · 2f7f389f0584c97e · report

Tasks

Action RecognitionSkeleton Based Action Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Skeleton Based Action Recognition Kinetics-Skeleton dataset HD-GCN Accuracy 40.9 #7 of 42 Archive leaderboard report
Skeleton Based Action Recognition N-UCLA HD-GCN Accuracy 97.2 #8 of 25 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D HD-GCN Accuracy (CS) 93.4 #14 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D HD-GCN Accuracy (CV) 97.2 #14 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D HD-GCN Ensembled Modalities 6 #14 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 HD-GCN Accuracy (Cross-Setup) 91.6 #9 of 83 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 HD-GCN Accuracy (Cross-Subject) 90.1 #9 of 83 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 HD-GCN Ensembled Modalities 6 #9 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.

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