Papers › On the Utility of 3D Hand Poses for Action Recognition

On the Utility of 3D Hand Poses for Action Recognition

14 Mar 2024arXiv:2403.09805archive 2025-07-28

Md Salman Shamil, Dibyadip Chatterjee, Fadime Sener, Shugao Ma, Angela Yao

3D hand pose is an underexplored modality for action recognition. Poses are compact yet informative and can greatly benefit applications with limited compute budgets. However, poses alone offer an incomplete understanding of actions, as they cannot fully capture objects and environments with which humans interact. We propose HandFormer, a novel multimodal transformer, to efficiently model hand-object interactions. HandFormer combines 3D hand poses at a high temporal resolution for fine-grained motion modeling with sparsely sampled RGB frames for encoding scene semantics. Observing the unique characteristics of hand poses, we temporally factorize hand modeling and represent each joint by its short-term trajectories. This factorized pose representation combined with sparse RGB samples is remarkably efficient and highly accurate. Unimodal HandFormer with only hand poses outperforms existing skeleton-based methods at 5x fewer FLOPs. With RGB, we achieve new state-of-the-art performance on Assembly101 and H2O with significant improvements in egocentric 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 13 code samples harvested from 1 repository linked to this paper: 8 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 13 samples from 1 repository, 8 ran (6 with no instrument failure; 2 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

s-shamil/HandFormer officialmentioned on GitHubpytorchSyntology: 13 samples, 8 ran (2 instrument-failed) · 5 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

13 samples harvested: 8 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 5 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.

1ran · violated contract
2ran · our draft was wrong
5ran
5unverified

Licence: 0 of the 13 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 s-shamil/HandFormer. “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”. For 4 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

s-shamil/HandFormer official repository 13 samples, 8 ran (2 instrument-failed) · 5 unverified
PositionalEncoding in 126 papers
census: 13 implementations from 9 papers, 9 distinct outputs across 5 buckets, one shared input per bucket
HandFormer/models/hf_pose.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · ea63108588c955b8 · report fixture: returned PositionalEncoding · level recorded 2026-09-22
TemporalConv in 8 papers HandFormer/models/hf_pose.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · bb9b0666242adf98 · report fixture: returned TemporalConv · level recorded 2026-09-22
TransformerEncoder in 96 papers HandFormer/models/hf_pose.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 5bbd4da441a48e72 · report fixture: returned TransformerEncoder · level recorded 2026-09-22
TransformerEncoderLayer in 90 papers HandFormer/models/hf_pose.py ran · metamorphic tier: deterministic MIT (permissive) · f8f7be5c3f791c68 · report fixture: returned TransformerEncoderLayer · level recorded 2026-09-22
Transformer_Encoder HandFormer/models/hf_pose.py ran MIT (permissive) · 12e7bd98c7ee2907 · report fixture: returned Transformer_Encoder · level recorded 2026-09-22
_get_clones in 28 papers HandFormer/models/hf_pose.py ran · our draft was wrong MIT (permissive) · df625bd27a59d895 · report fixture: signature module:callable/0/?, N:int/0/int · returned ModuleList · level recorded 2026-09-22
activation_factory in 8 papers HandFormer/models/hf_pose.py ran · our draft was wrong MIT (permissive) · 5426f077b824bbb4 · report fixture: signature name:str/0/str, inplace:bool/0/bool · returned ReLU · level recorded 2026-09-22
normalize_tensor in 47 papers
census: 3 implementations from 5 papers, 2 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 2 of 2, arg 1: rank 4, kind float, dtype float32
HandFormer/models/hf_pose.py ran · violated contract fingerprinted MIT (permissive) · 61e29634518807c2 · report fixture: signature tensor:Tensor/4/float · returned Tensor · level recorded 2026-09-22
HF_Pose HandFormer/models/hf_pose.py unverified MIT (permissive) · 619c6b2598ece3bf · report
MicroactionEncoder HandFormer/models/hf_pose.py unverified MIT (permissive) · 0ed7906dcdd465df · report
Trajectory_SelfAttention HandFormer/models/hf_pose.py unverified MIT (permissive) · e5491621abfadb10 · report
Unimodal_TF HandFormer/models/hf_pose.py unverified MIT (permissive) · b9201db3a21104d5 · report
fc_init HandFormer/models/hf_pose.py unverified MIT (permissive) · 5870cc705fd8d62e · 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 Hand-Former (graph method: Hand-Former). 14 bricks; individually on a fixture: 9 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

  1. HF_Pose entry · level 0 · unverified · 619c6b2598ece3bf
  2. MicroactionEncoder helper · level 0 · unverified · 0ed7906dcdd465df
  3. Unimodal_TF model · level 0 · unverified · b9201db3a21104d5
  4. normalize_tensor helper · level 1 · ran · violated contract · 61e29634518807c2
  5. Trajectory_SelfAttention model · level 0 · unverified · e5491621abfadb10
  6. fc_init helper · level 0 · unverified · 5870cc705fd8d62e
  7. PositionalEncoding helper · level 1 · ran · ea63108588c955b8
  8. Transformer_Encoder helper · level 1 · ran · 12e7bd98c7ee2907
  9. TransformerEncoder helper · level 1 · ran · 5bbd4da441a48e72
  10. TransformerEncoderLayer helper · level 1 · ran · f8f7be5c3f791c68
  11. _get_clones helper · level 1 · ran · our draft was wrong · df625bd27a59d895
  12. _get_activation_fn helper · level 1 · ran · our draft was wrong · 0bb264f52e707e08
  13. TemporalConv helper · level 1 · ran · bb9b0666242adf98
  14. activation_factory helper · level 1 · ran · our draft was wrong · 5426f077b824bbb4

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="2403.09805") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

3D Action RecognitionAction Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Action Recognition Assembly101 HandFormer-B/21 Actions Top-1 41.06 #1 of 7 Archive leaderboard report
3D Action Recognition Assembly101 HandFormer-B/21 Object Top-1 51.17 #1 of 7 Archive leaderboard report
3D Action Recognition Assembly101 HandFormer-B/21 Verbs Top-1 69.23 #1 of 7 Archive leaderboard report
Action Recognition H2O (2 Hands and Objects) HandFormer-B/21x8 Actions Top-1 93.39 #1 of 11 Archive leaderboard report
Action Recognition H2O (2 Hands and Objects) HandFormer-B/21x8 Hand Pose 3D #1 of 11 Archive leaderboard report
Action Recognition H2O (2 Hands and Objects) HandFormer-B/21x8 Object Label No #1 of 11 Archive leaderboard report
Action Recognition H2O (2 Hands and Objects) HandFormer-B/21x8 Object Pose No #1 of 11 Archive leaderboard report
Action Recognition H2O (2 Hands and Objects) HandFormer-B/21x8 RGB Yes #1 of 11 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