Papers › Unsupervised Motion Representation Learning with Capsule Autoencoders

Unsupervised Motion Representation Learning with Capsule Autoencoders

1 Oct 2021NeurIPS 2021 12arXiv:2110.00529archive 2025-07-28

Ziwei Xu, Xudong Shen, Yongkang Wong, Mohan S Kankanhalli

We propose the Motion Capsule Autoencoder (MCAE), which addresses a key challenge in the unsupervised learning of motion representations: transformation invariance. MCAE models motion in a two-level hierarchy. In the lower level, a spatio-temporal motion signal is divided into short, local, and semantic-agnostic snippets. In the higher level, the snippets are aggregated to form full-length semantic-aware segments. For both levels, we represent motion with a set of learned transformation invariant templates and the corresponding geometric transformations by using capsule autoencoders of a novel design. This leads to a robust and efficient encoding of viewpoint changes. MCAE is evaluated on a novel Trajectory20 motion dataset and various real-world skeleton-based human action datasets. Notably, it achieves better results than baselines on Trajectory20 with considerably fewer parameters and state-of-the-art performance on the unsupervised skeleton-based action recognition task.

PaperPDFConference PDFCodeCode 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 20 code samples harvested from 1 repository linked to this paper: 15 ran (of which 4 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 2 violated, 5 with no contract checked; 7 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 20 samples from 1 repository, 15 ran (8 with no instrument failure; 7 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. 1 of the 15 samples that ran has no recorded date.

ZiweiXU/CapsuleMotion officialmentioned in papermentioned on GitHubpytorchSyntology: 20 samples, 15 ran (7 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

20 samples harvested: 15 ran (of which 4 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 2 violated, 5 with no contract checked; 7 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 · honoured contract
2ran · violated contract
4ran · our draft was wrong
3ran; the contract check could not run
5ran
5unverified

Licence: 0 of the 20 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 ZiweiXU/CapsuleMotion. “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 1 sample 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.

ZiweiXU/CapsuleMotion official repository 20 samples, 15 ran (7 instrument-failed) · 5 unverified
BatchLinear lib/mcae/model.py ran MIT (permissive) · 791124774ac72001 · report fixture: returned BatchLinear · level recorded 2026-09-22
SegmentDecoder lib/mcae/model.py ran MIT (permissive) · 67a918cc07243e1d · report fixture: returned SegmentDecoder · level recorded 2026-09-22
SegmentEncoder lib/mcae/model.py ran MIT (permissive) · 4e176ccdd110ccc3 · report fixture: returned SegmentEncoder · level recorded 2026-09-22
SnippetEncoder lib/mcae/model.py ran MIT (permissive) · 9d5043f4be759579 · report fixture: returned SnippetEncoder · level recorded 2026-09-22
compact_pose lib/mcae/model.py ran · violated contract fingerprinted MIT (permissive) · 6d4d34062e1c5530 · report fixture: signature full_pose:Tensor/3/float · returned Tensor · level recorded 2026-09-22
compact_pose_3d lib/mcae/model.py ran · violated contract MIT (permissive) · 2e5f0a62fa71eea9 · report fixture: signature full_pose:Tensor/3/float · returned Tensor · level recorded 2026-09-22
constrain_pose lib/mcae/model.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 626bb1811a1b7445 · report fixture: signature pose:Tensor/2/float, scale:float/0/float, trans_range:float/0/float · returned Tensor · level recorded 2026-09-22
constrain_pose_3d lib/mcae/model.py ran; the contract check could not run (RAISES) MIT (permissive) · e1661d691e4a901a · report fixture: signature pose:Tensor/2/float, scale:float/0/float, trans_range:float/0/float · returned Tensor · level recorded 2026-09-22
expand_pose lib/mcae/model.py ran · our draft was wrong fingerprinted MIT (permissive) · 9efa4b606d03159d · report fixture: signature pose:Tensor/2/float · returned Tensor · level recorded 2026-09-22
fixed_template_initializer lib/mcae/model.py ran · honoured contract fingerprinted MIT (permissive) · bf75b48517195b2b · report fixture: signature num_sni_temp:int/0/int, len_sni_temp:int/0/int, scale_factor:float/0/float, mode:str/0/str · returned Tensor · level recorded 2026-09-22
full_pose lib/mcae/model.py ran · our draft was wrong fingerprinted MIT (permissive) · 6b422476f7a75d45 · report fixture: signature pose:Tensor/2/float · returned Tensor · level recorded 2026-09-22
full_pose_3d lib/mcae/model.py ran · our draft was wrong MIT (permissive) · dbac1fbe39d62402 · report fixture: signature pose:Tensor/2/float · returned Tensor · level recorded 2026-09-22
init_truncated_normal lib/mcae/model.py ran · our draft was wrong fingerprinted MIT (permissive) · 164fc00eb042e928 · report fixture: signature param:Tensor/2/float, stdv:NoneType/0/?, fan_in:NoneType/0/? · returned Parameter · level recorded 2026-09-22
loss_fn in 55 papers
census: 8 implementations from 9 papers, 6 distinct outputs across 3 buckets, one shared input per bucket
lib/mcae/model.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic MIT (permissive) · 3aa0d94122193b9e · report fixture: signature x:Tensor/3/float, results:dict/0/?, is_valtest:bool/0/bool, y:Tensor/1/int, loss_weights:dict/0/? · returned tuple · level recorded, date not recorded
myself lib/mcae/model.py ran MIT (permissive) · a5e44072bb9d9d5d · report fixture: returned str · level recorded 2026-09-22
MCAE lib/mcae/model.py unverified MIT (permissive) · efbad1cbdacbe091 · report
Module in 7 papers lib/mcae/model.py unverified MIT (permissive) · 335cc3b992ddaf73 · report
SnippetDecoder lib/mcae/model.py unverified MIT (permissive) · 07fdb5a4536b7a31 · report
_truncated_normal lib/mcae/model.py unverified MIT (permissive) · f7fcffe777530157 · report
fixed_template_initializer_3d lib/mcae/model.py unverified MIT (permissive) · a393a223aba0b7cb · 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 Motion Capsule Autoencoder (MCAE) (graph method: Motion Capsule Autoencoder (MCAE)). 19 bricks; individually on a fixture: 14 ran (of which 4 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 2 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

  1. MCAE entry · level 0 · unverified · efbad1cbdacbe091
  2. Module helper · level 0 · unverified · 335cc3b992ddaf73
  3. SegmentDecoder model · level 1 · ran · 67a918cc07243e1d
  4. SegmentEncoder model · level 1 · ran · 4e176ccdd110ccc3
  5. SnippetDecoder model · level 0 · unverified · 07fdb5a4536b7a31
  6. SnippetEncoder model · level 1 · ran · 9d5043f4be759579
  7. compact_pose helper · level 1 · ran · violated contract · 6d4d34062e1c5530
  8. myself helper · level 1 · ran · a5e44072bb9d9d5d
  9. constrain_pose helper · level 1 · ran; the contract check could not run (RAISES) · 626bb1811a1b7445
  10. full_pose helper · level 1 · ran · our draft was wrong · 6b422476f7a75d45
  11. BatchLinear helper · level 1 · ran · 791124774ac72001
  12. fixed_template_initializer helper · level 1 · ran · honoured contract · bf75b48517195b2b
  13. fixed_template_initializer_3d helper · level 0 · unverified · a393a223aba0b7cb
  14. compact_pose_3d helper · level 1 · ran · violated contract · 2e5f0a62fa71eea9
  15. constrain_pose_3d helper · level 1 · ran; the contract check could not run (RAISES) · e1661d691e4a901a
  16. expand_pose helper · level 1 · ran · our draft was wrong · 9efa4b606d03159d
  17. full_pose_3d helper · level 1 · ran · our draft was wrong · dbac1fbe39d62402
  18. init_truncated_normal helper · level 1 · ran · our draft was wrong · 164fc00eb042e928
  19. _truncated_normal helper · level 0 · unverified · f7fcffe777530157

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="2110.00529") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Action RecognitionRepresentation LearningSelf-Supervised Human Action RecognitionSkeleton Based Action RecognitionUnsupervised Skeleton Based Action Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Self-Supervised Human Action Recognition NTU RGB+D 120 MCAE Classifier FC #4 of 8 Archive leaderboard report
Self-Supervised Human Action Recognition NTU RGB+D 120 MCAE Encoder MCAE #4 of 8 Archive leaderboard report
Self-Supervised Human Action Recognition NTU RGB+D 120 MCAE xset (%) 54.7 #4 of 8 Archive leaderboard report
Self-Supervised Human Action Recognition NTU RGB+D 120 MCAE xsub (%) 52.8 #4 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.

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