Papers › Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition

Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition

27 Jun 2022arXiv:2206.13028archive 2025-07-28

Zhan Chen, Sicheng Li, Bing Yang, Qinghan Li, Hong Liu

Graph convolutional networks have been widely used for skeleton-based action recognition due to their excellent modeling ability of non-Euclidean data. As the graph convolution is a local operation, it can only utilize the short-range joint dependencies and short-term trajectory but fails to directly model the distant joints relations and long-range temporal information that are vital to distinguishing various actions. To solve this problem, we present a multi-scale spatial graph convolution (MS-GC) module and a multi-scale temporal graph convolution (MT-GC) module to enrich the receptive field of the model in spatial and temporal dimensions. Concretely, the MS-GC and MT-GC modules decompose the corresponding local graph convolution into a set of sub-graph convolution, forming a hierarchical residual architecture. Without introducing additional parameters, the features will be processed with a series of sub-graph convolutions, and each node could complete multiple spatial and temporal aggregations with its neighborhoods. The final equivalent receptive field is accordingly enlarged, which is capable of capturing both short- and long-range dependencies in spatial and temporal domains. By coupling these two modules as a basic block, we further propose a multi-scale spatial temporal graph convolutional network (MST-GCN), which stacks multiple blocks to learn effective motion representations for action recognition. The proposed MST-GCN achieves remarkable performance on three challenging benchmark datasets, NTU RGB+D, NTU-120 RGB+D and Kinetics-Skeleton, for skeleton-based action recognition.

PaperPDFCodeCode Syntology ranMethod as code

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 26 code samples harvested from 1 repository linked to this paper: 19 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 26 samples from 1 repository, 19 ran (19 with no instrument failure; 0 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

czhaneva/mst-gcn officialmentioned in paperpytorchSyntology: 26 samples, 19 ran (0 instrument-failed) · 7 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

26 samples harvested: 19 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

19ran
7unverified

Licence: 0 of the 26 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 czhaneva/mst-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. 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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

czhaneva/mst-gcn official repository 26 samples, 19 ran (0 instrument-failed) · 7 unverified
Activations model/AEMST_GCN.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · adf2726a0b3d58c7 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
Basic_GCN_layer model/AEMST_GCN.py ran fingerprinted MIT (permissive) · b98c6db6e1002327 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
Basic_TCN_layer model/AEMST_GCN.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · c796ca9dd59fa236 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
Channel_Att model/AEMST_GCN.py ran · metamorphic tier: invariant MIT (permissive) · 48fe3fb98da81973 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
Frame_Att model/AEMST_GCN.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · dbee7b6fa4f1ce15 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
HardSwish model/AEMST_GCN.py ran fingerprinted MIT (permissive) · 30a4e5eac52b5024 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-24
Joint_Att model/AEMST_GCN.py ran MIT (permissive) · c1df0458dc14ccc0 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
MS_GCN_layer model/AEMST_GCN.py ran fingerprinted MIT (permissive) · 75741374fad8b7e5 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
MS_TCN_layer model/AEMST_GCN.py ran fingerprinted MIT (permissive) · bfbe1f03029f7ad2 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
MS_Temporal_Bottleneck_Layer model/AEMST_GCN.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · d2414716f801d45c · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
Part_Att model/AEMST_GCN.py ran MIT (permissive) · c5666841a031b400 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
ST_Joint_Att model/AEMST_GCN.py ran · metamorphic tier: invariant MIT (permissive) · c00428bb1087d8c7 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
SpatialGraphCov model/AEMST_GCN.py ran · metamorphic tier: invariant MIT (permissive) · 5af17e125ae250fa · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
Spatial_Bottleneck_Layer model/AEMST_GCN.py ran MIT (permissive) · 5080808855c5f5ab · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
Spatial_Sep_Layer model/AEMST_GCN.py ran MIT (permissive) · 1287702d2c4a9cd2 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
Swish in 30 papers
census: 22 implementations from 19 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
model/AEMST_GCN.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · f96addd2fbf1a9ff · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
Temporal_Bottleneck_Layer model/AEMST_GCN.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 50d877700bf66c6e · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
Temporal_Sep_Layer model/AEMST_GCN.py ran fingerprinted MIT (permissive) · ec58271211aef2f7 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
Zero_Layer model/AEMST_GCN.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · 3ab2a8a648baad65 · report fixture: signature x:Tensor/2/float · returned int · level recorded 2026-09-22
Attention_Layer model/AEMST_GCN.py unverified MIT (permissive) · 702b399cba4cde41 · report
Basic_Layer model/AEMST_GCN.py unverified MIT (permissive) · 2793d688802c51f8 · report
MST_GCN_block model/AEMST_GCN.py unverified MIT (permissive) · 2a8639e74ce27e44 · report
MS_Spatial_Bottleneck_Layer model/AEMST_GCN.py unverified MIT (permissive) · 45f3e4bb934a1064 · report
Model in 227 papers model/AEMST_GCN.py unverified MIT (permissive) · 6734a97abcc87eb8 · report
STC_Joint_Att model/AEMST_GCN.py unverified MIT (permissive) · 20ef600dd57166cb · report
conv_branch_init model/AEMST_GCN.py unverified MIT (permissive) · a80e2c1116a03a17 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for MST-GCN (graph method: MST-GCN). 29 bricks; individually on a fixture: 20 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified. The assembly has not been run end-to-end.

  1. Model entry · level 0 · unverified · 6734a97abcc87eb8
  2. Activations helper · level 1 · ran · adf2726a0b3d58c7
  3. MST_GCN_block model · level 0 · unverified · 2a8639e74ce27e44
  4. SpatialGraphCov model · level 1 · ran · 5af17e125ae250fa
  5. Spatial_Sep_Layer helper · level 1 · ran · 1287702d2c4a9cd2
  6. bn_init helper · level 0 · unverified · da94160ed9fd5926
  7. conv_branch_init helper · level 0 · unverified · a80e2c1116a03a17
  8. conv_init helper · level 0 · unverified · a3ca5080ddd9c2fc
  9. import_class helper · level 1 · ran · our draft was wrong · ffed4f85d50832c9
  10. HardSwish helper · level 1 · ran · 30a4e5eac52b5024
  11. Swish helper · level 1 · ran · f96addd2fbf1a9ff
  12. Attention_Layer model · level 0 · unverified · 702b399cba4cde41
  13. Zero_Layer helper · level 1 · ran · 3ab2a8a648baad65
  14. Channel_Att helper · level 1 · ran · 48fe3fb98da81973
  15. Frame_Att helper · level 1 · ran · dbee7b6fa4f1ce15
  16. Joint_Att helper · level 1 · ran · c1df0458dc14ccc0
  17. Part_Att helper · level 1 · ran · c5666841a031b400
  18. STC_Joint_Att helper · level 0 · unverified · 20ef600dd57166cb
  19. ST_Joint_Att model · level 1 · ran · c00428bb1087d8c7
  20. Basic_Layer helper · level 0 · unverified · 2793d688802c51f8
  21. Basic_TCN_layer helper · level 1 · ran · c796ca9dd59fa236
  22. MS_GCN_layer model · level 1 · ran · 75741374fad8b7e5
  23. MS_Spatial_Bottleneck_Layer model · level 0 · unverified · 45f3e4bb934a1064
  24. MS_TCN_layer model · level 1 · ran · bfbe1f03029f7ad2
  25. MS_Temporal_Bottleneck_Layer model · level 1 · ran · d2414716f801d45c
  26. Spatial_Bottleneck_Layer helper · level 1 · ran · 5080808855c5f5ab
  27. Temporal_Bottleneck_Layer helper · level 1 · ran · 50d877700bf66c6e
  28. Temporal_Sep_Layer helper · level 1 · ran · ec58271211aef2f7
  29. Basic_GCN_layer helper · level 1 · ran · b98c6db6e1002327

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2206.13028") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

3D Action RecognitionAction RecognitionSkeleton Based Action Recognition

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Convolution

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