Papers › HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations

HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representations

10 Mar 2023arXiv:2303.06242archive 2025-07-28

Luca Franco, Paolo Mandica, Bharti Munjal, Fabio Galasso

Self-paced learning has been beneficial for tasks where some initial knowledge is available, such as weakly supervised learning and domain adaptation, to select and order the training sample sequence, from easy to complex. However its applicability remains unexplored in unsupervised learning, whereby the knowledge of the task matures during training. We propose a novel HYperbolic Self-Paced model (HYSP) for learning skeleton-based action representations. HYSP adopts self-supervision: it uses data augmentations to generate two views of the same sample, and it learns by matching one (named online) to the other (the target). We propose to use hyperbolic uncertainty to determine the algorithmic learning pace, under the assumption that less uncertain samples should be more strongly driving the training, with a larger weight and pace. Hyperbolic uncertainty is a by-product of the adopted hyperbolic neural networks, it matures during training and it comes with no extra cost, compared to the established Euclidean SSL framework counterparts. When tested on three established skeleton-based action recognition datasets, HYSP outperforms the state-of-the-art on PKU-MMD I, as well as on 2 out of 3 downstream tasks on NTU-60 and NTU-120. Additionally, HYSP only uses positive pairs and bypasses therefore the complex and computationally-demanding mining procedures required for the negatives in contrastive techniques. Code is available at https://github.com/paolomandica/HYSP.

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: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 13 samples from 1 repository, 4 ran (4 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.

paolomandica/hysp officialmentioned in papermentioned on GitHubpytorchMITSyntology: 13 samples, 4 ran (0 instrument-failed) · 9 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: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 9 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.

4ran
9unverified

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 paolomandica/hysp. “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.

paolomandica/hysp official repository 13 samples, 4 ran (0 instrument-failed) · 9 unverified
DropBlockT_1d src/net/hysp.py ran MIT (permissive) · 180f114b9cbc15ea · report fixture: signature input:Tensor/4/float, mask:Tensor/3/float · returned Tensor · level recorded 2026-09-24
EMA in 18 papers src/net/hysp.py ran · metamorphic tier: deterministic MIT (permissive) · 8ba7eaf2c8a7739a · report fixture: signature ma_model:callable/0/?, current_model:callable/0/? · returned NoneType · level recorded 2026-09-22
Graph in 18 papers src/net/hysp.py ran MIT (permissive) · 2bbb5e685ad2f3b3 · report fixture: returned ndarray · level recorded 2026-09-24
Simam_Drop src/net/hysp.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · dd034bb1c67ea073 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
DropBlock_Ske src/net/hysp.py unverified MIT (permissive) · bc2bd6c395543b89 · report
HYSP src/net/hysp.py unverified MIT (permissive) · 90735a76fd308958 · report
HyperMapper src/net/hysp.py unverified MIT (permissive) · 80f6560d69b89e68 · report
MLP in 375 papers src/net/hysp.py unverified MIT (permissive) · 3a7a63e8f839cd58 · report
MobiusLinear src/net/hysp.py unverified MIT (permissive) · 3b892a99281475cb · report
PositiveOnlyLoss src/net/hysp.py unverified MIT (permissive) · 45cf805fdfb46a6c · report
_mobius_matvec src/net/hysp.py unverified MIT (permissive) · bc7290a25a803047 · report
mobius_linear src/net/hysp.py unverified MIT (permissive) · 59823bc0371d269d · report
mobius_matvec src/net/hysp.py unverified MIT (permissive) · 46dd9b384ab6543c · 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 HYSP (graph method: HYSP). 17 bricks; individually on a fixture: 8 ran (of which 2 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified. The assembly has not been run end-to-end.

  1. HYSP entry · level 0 · unverified · 90735a76fd308958
  2. EMA helper · level 1 · ran · 8ba7eaf2c8a7739a
  3. HyperMapper helper · level 0 · unverified · 80f6560d69b89e68
  4. MLP helper · level 0 · unverified · 3a7a63e8f839cd58
  5. PositiveOnlyLoss loss · level 0 · unverified · 45cf805fdfb46a6c
  6. MobiusLinear model · level 0 · unverified · 3b892a99281475cb
  7. mobius_linear helper · level 0 · unverified · 59823bc0371d269d
  8. mobius_matvec helper · level 0 · unverified · 46dd9b384ab6543c
  9. _mobius_matvec helper · level 0 · unverified · bc7290a25a803047
  10. ConvTemporalGraphical helper · level 1 · ran · a7af8c079621d2b7
  11. DropBlockT_1d helper · level 1 · ran · 180f114b9cbc15ea
  12. DropBlock_Ske helper · level 0 · unverified · bc2bd6c395543b89
  13. Graph helper · level 1 · ran · 2bbb5e685ad2f3b3
  14. Simam_Drop helper · level 1 · ran · dd034bb1c67ea073
  15. get_hop_distance helper · level 1 · ran · our draft was wrong · c257ac36cba643a2
  16. normalize_digraph helper · level 1 · ran · violated contract · 8158f4435afa26b7
  17. st_gcn helper · level 1 · ran · 1b4ec459a91bb8fd

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="2303.06242") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Action RecognitionDomain AdaptationSkeleton Based Action RecognitionUnsupervised Skeleton Based Action RecognitionWeakly-supervised Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Skeleton Based Action Recognition NTU RGB+D 3s-HYSP Accuracy (CS) 89.1 #65 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 3s-HYSP Accuracy (CV) 95.2 #65 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D HYSP Accuracy (CS) 86.5 #83 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D HYSP Accuracy (CV) 93.5 #83 of 135 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 3s-HYSP Accuracy (Cross-Setup) 86.3 #49 of 83 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 3s-HYSP Accuracy (Cross-Subject) 84.5 #49 of 83 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 HYSP Accuracy (Cross-Setup) 82 #54 of 83 Archive leaderboard report
Skeleton Based Action Recognition NTU RGB+D 120 HYSP Accuracy (Cross-Subject) 81.4 #54 of 83 Archive leaderboard report
Skeleton Based Action Recognition PKU-MMD 3s-HYSP Accuracy (Cross-Subject) 96.2 #4 of 4 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