Papers › Augmented Skeleton Based Contrastive Action Learning with Momentum LSTM for...

Augmented Skeleton Based Contrastive Action Learning with Momentum LSTM for Unsupervised Action Recognition

1 Aug 2020arXiv:2008.00188archive 2025-07-28

Haocong Rao, Shihao Xu, Xiping Hu, Jun Cheng, Bin Hu

Action recognition via 3D skeleton data is an emerging important topic in these years. Most existing methods either extract hand-crafted descriptors or learn action representations by supervised learning paradigms that require massive labeled data. In this paper, we for the first time propose a contrastive action learning paradigm named AS-CAL that can leverage different augmentations of unlabeled skeleton data to learn action representations in an unsupervised manner. Specifically, we first propose to contrast similarity between augmented instances (query and key) of the input skeleton sequence, which are transformed by multiple novel augmentation strategies, to learn inherent action patterns ("pattern-invariance") of different skeleton transformations. Second, to encourage learning the pattern-invariance with more consistent action representations, we propose a momentum LSTM, which is implemented as the momentum-based moving average of LSTM based query encoder, to encode long-term action dynamics of the key sequence. Third, we introduce a queue to store the encoded keys, which allows our model to flexibly reuse proceeding keys and build a more consistent dictionary to improve contrastive learning. Last, by temporally averaging the hidden states of action learned by the query encoder, a novel representation named Contrastive Action Encoding (CAE) is proposed to represent human's action effectively. Extensive experiments show that our approach typically improves existing hand-crafted methods by 10-50% top-1 accuracy, and it can achieve comparable or even superior performance to numerous supervised learning methods.

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 11 code samples harvested from 1 repository linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 1 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: 11 samples from 1 repository, 9 ran (7 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 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.

Mikexu007/AS-CAL officialmentioned in paperpytorchnot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-readySyntology: not harvested report
Mikexu007/AS_CAL officialmentioned in paperpytorchMITSyntology: 11 samples, 9 ran (2 instrument-failed) · 2 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

11 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 2 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 · our draft was wrong
1ran; the contract check could not run
7ran
2unverified

Licence: 2 of the 11 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 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 Mikexu007/AS_CAL. “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.

Mikexu007/AS_CAL official repository 11 samples, 9 ran (2 instrument-failed) · 2 unverified
denormalize in 64 papers
census: 9 implementations from 11 papers, 8 distinct outputs across 4 buckets, one shared input per bucket
feeders/sbu_feeder.py ran fingerprinted MIT (permissive) · dc89adec7492521a · report fixture: signature norm_coords:ndarray/2/float · returned ndarray · level recorded 2026-09-25
get_ground_truth feeders/sbu_feeder.py ran fingerprinted MIT (permissive) · 63dca04df5440f53 · report fixture: signature data_dir:str/0/str · returned tuple · level recorded 2026-09-25
get_shuffle_ids in 9 papers pretrain_and_linEval.py ran; the contract check could not run (RAISES) MIT (permissive) · e2e91e39d8368ced · report fixture: returned tuple · level recorded 2026-09-22
import_class in 29 papers linEval.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · ffed4f85d50832c9 · report fixture: signature name:str/0/str · returned type · level recorded 2026-09-22
parse_sbu_txt feeders/sbu_feeder.py ran MIT (permissive) · 5deb486c8215ef31 · report fixture: signature pose_filepath:str/0/str, normalized:bool/0/bool · returned ndarray · level recorded 2026-09-25
pose_embed_ linEval.py ran MIT (permissive) · 16950c872dc57466 · report fixture: signature x:Tensor/3/float, t:int/0/int, n:int/0/int, pose_model:callable/0/? · returned Tensor · level recorded 2026-09-25
reshap_input_for_lstm models/Models.py ran MIT (permissive) · d82afa8773b11f30 · report fixture: signature x1:Tensor/5/float · returned Tensor · level recorded 2026-09-25
subsample in 25 papers feeders/tools.py ran fingerprinted MIT (permissive) · d4cef4738b78026c · report fixture: signature data_numpy:ndarray/4/float, time_range:int/0/int · returned ndarray · level recorded 2026-09-25
subtract in 5 papers feeders/tools.py ran fingerprinted MIT (permissive) · 5772bc1d78b90f56 · report fixture: signature data_numpy:ndarray/4/float, joint:int/0/int · returned ndarray · level recorded 2026-09-25
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
util.py unverified MIT (permissive) here; the stored copy is pointer only · 913d82af53065418 · report
aug_look feeders/tools.py unverified MIT (permissive) · fec3ca8e9cb588e8 · report

Tasks

Action RecognitionContrastive LearningSelf-Supervised Human Action RecognitionSelf-supervised Skeleton-based Action Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Self-Supervised Human Action Recognition NTU RGB+D 120 AS-CAL Classifier FC #6 of 8 Archive leaderboard report
Self-Supervised Human Action Recognition NTU RGB+D 120 AS-CAL Encoder LSTM #6 of 8 Archive leaderboard report
Self-Supervised Human Action Recognition NTU RGB+D 120 AS-CAL xset (%) 49.2 #6 of 8 Archive leaderboard report
Self-Supervised Human Action Recognition NTU RGB+D 120 AS-CAL xsub (%) 48.6 #6 of 8 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

LSTMSigmoid ActivationTanh Activation

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