Papers › Hypergraph Transformer for Skeleton-based Action Recognition

Hypergraph Transformer for Skeleton-based Action Recognition

17 Nov 2022arXiv:2211.09590archive 2025-07-28

Yuxuan Zhou, Zhi-Qi Cheng, Chao Li, Yanwen Fang, Yifeng Geng, Xuansong Xie, Margret Keuper

Skeleton-based action recognition aims to recognize human actions given human joint coordinates with skeletal interconnections. By defining a graph with joints as vertices and their natural connections as edges, previous works successfully adopted Graph Convolutional networks (GCNs) to model joint co-occurrences and achieved superior performance. More recently, a limitation of GCNs is identified, i.e., the topology is fixed after training. To relax such a restriction, Self-Attention (SA) mechanism has been adopted to make the topology of GCNs adaptive to the input, resulting in the state-of-the-art hybrid models. Concurrently, attempts with plain Transformers have also been made, but they still lag behind state-of-the-art GCN-based methods due to the lack of structural prior. Unlike hybrid models, we propose a more elegant solution to incorporate the bone connectivity into Transformer via a graph distance embedding. Our embedding retains the information of skeletal structure during training, whereas GCNs merely use it for initialization. More importantly, we reveal an underlying issue of graph models in general, i.e., pairwise aggregation essentially ignores the high-order kinematic dependencies between body joints. To fill this gap, we propose a new self-attention (SA) mechanism on hypergraph, termed Hypergraph Self-Attention (HyperSA), to incorporate intrinsic higher-order relations into the model. We name the resulting model Hyperformer, and it beats state-of-the-art graph models w.r.t. accuracy and efficiency on NTU RGB+D, NTU RGB+D 120, and Northwestern-UCLA datasets.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 12 code samples harvested from 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 1 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 12 samples from 1 repository, 11 ran (6 with no instrument failure; 5 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 11 samples that ran has no recorded date.

ZhouYuxuanYX/Hypergraph-Transformer-for-Skeleton-based-Action-Recognition officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 12 samples, 11 ran (5 instrument-failed) · 1 unverified 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

12 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 1 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
1ran · violated contract
4ran · our draft was wrong
1ran; the contract check could not run
3ran
1unverified

Licence: 9 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. For 9 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from ZhouYuxuanYX/Hypergraph-Transformer-for-Skeleton-based-Action-Recognition. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

ZhouYuxuanYX/Hypergraph-Transformer-for-Skeleton-based-Action-Recognition official repository 12 samples, 11 ran (5 instrument-failed) · 1 unverified
downsample in 59 papers feeders/tools.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · 8b14974e8aa7320f · report fixture: signature data_numpy:ndarray/4/float, step:int/0/int, random_sample:bool/0/bool · returned ndarray · level recorded 2026-09-24
edge2mat in 8 papers graph/tools.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 5f5ae82020ac7ec2 · report fixture: signature link:list/1/tuple, num_node:int/0/int · returned ndarray · level recorded 2026-09-22
get_k_scale_graph graph/tools.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) here; the stored copy is pointer only · d3e8dd52d4a2755a · report fixture: signature scale:int/0/int, A:ndarray/2/float · returned ndarray · level recorded 2026-09-24
get_sgp_mat graph/tools.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 5940d00ced3d0637 · report fixture: signature num_in:int/0/int, num_out:int/0/int, link:list/1/tuple · returned ndarray · level recorded 2026-09-24
import_class in 29 papers feeders/feeder_ntu.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · ffed4f85d50832c9 · report fixture: signature name:str/0/str · returned type · level recorded 2026-09-22
import_class in 29 papers torchlight/torchlight/util.py ran · our draft was wrong Apache-2.0 (permissive) · 4e946d7c92be9d41 · report fixture: signature import_str:str/0/str · returned type · level recorded 2026-09-22
ngpu in 5 papers torchlight/torchlight/gpu.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 83ed4b272b1e38d0 · report fixture: signature gpus:list/1/int · returned int · level recorded 2026-09-24
str2bool in 533 papers torchlight/torchlight/util.py ran · violated contract Apache-2.0 (permissive) · f017532fc389cbfe · report fixture: signature v:str/0/str · returned bool · level recorded, date not recorded
str2dict in 7 papers torchlight/torchlight/util.py ran fingerprinted Apache-2.0 (permissive) · 1e89b2b546737164 · report fixture: signature v:str/0/str · returned dict · level recorded 2026-09-25
valid_crop_resize in 8 papers feeders/tools.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · 37939bae213ecfd4 · report fixture: signature data_numpy:ndarray/4/float, valid_frame_num:int/0/int, p_interval:list/1/float, window:int/0/int · returned ndarray · level recorded 2026-09-24
visible_gpu in 5 papers torchlight/torchlight/gpu.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 621e08e84928c5c3 · report fixture: signature gpus:int/0/int · returned list · level recorded 2026-09-24
temporal_slice in 11 papers feeders/tools.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · 2f7f389f0584c97e · report

Tasks

Action RecognitionSkeleton Based Action Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Skeleton Based Action Recognition NTU RGB+D Hyperformer Accuracy (CS) 92.9 #26 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D Hyperformer Accuracy (CV) 96.5 #26 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D Hyperformer Ensembled Modalities 4 #26 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 Hyperformer Accuracy (Cross-Setup) 91.3 #12 of 83 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 Hyperformer Accuracy (Cross-Subject) 89.9 #12 of 83 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 Hyperformer Ensembled Modalities 4 #12 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: HyperSA

AttentionHyperSAMulti-Head AttentionResidual ConnectionTransformer

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