Papers › MacDiff: Unified Skeleton Modeling with Masked Conditional Diffusion

MacDiff: Unified Skeleton Modeling with Masked Conditional Diffusion

16 Sep 2024arXiv:2409.10473archive 2025-07-28

Lehong Wu, Lilang Lin, Jiahang Zhang, Yiyang Ma, Jiaying Liu

Self-supervised learning has proved effective for skeleton-based human action understanding. However, previous works either rely on contrastive learning that suffers false negative problems or are based on reconstruction that learns too much unessential low-level clues, leading to limited representations for downstream tasks. Recently, great advances have been made in generative learning, which is naturally a challenging yet meaningful pretext task to model the general underlying data distributions. However, the representation learning capacity of generative models is under-explored, especially for the skeletons with spacial sparsity and temporal redundancy. To this end, we propose Masked Conditional Diffusion (MacDiff) as a unified framework for human skeleton modeling. For the first time, we leverage diffusion models as effective skeleton representation learners. Specifically, we train a diffusion decoder conditioned on the representations extracted by a semantic encoder. Random masking is applied to encoder inputs to introduce a information bottleneck and remove redundancy of skeletons. Furthermore, we theoretically demonstrate that our generative objective involves the contrastive learning objective which aligns the masked and noisy views. Meanwhile, it also enforces the representation to complement for the noisy view, leading to better generalization performance. MacDiff achieves state-of-the-art performance on representation learning benchmarks while maintaining the competence for generative tasks. Moreover, we leverage the diffusion model for data augmentation, significantly enhancing the fine-tuning performance in scenarios with scarce labeled data. Our project is available at https://lehongwu.github.io/ECCV24MacDiff/.

PaperPDFCode 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 12 code samples harvested from 1 repository linked to this paper: 8 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: found in paper text by Syntology: 12 samples from 1 repository, 8 ran (7 with no instrument failure; 1 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.

LehongWu/MacDiff found in paper text by SyntologySyntology: 12 samples, 8 ran (1 instrument-failed) · 4 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

12 samples harvested: 8 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 4 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; the contract check could not run
7ran
4unverified

Licence: 12 of the 12 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 LehongWu/MacDiff. “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.

LehongWu/MacDiff found in paper text by Syntology 12 samples, 8 ran (1 instrument-failed) · 4 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
model/transformer_macdiff.py ran no licence file found · pointer only · c41cf977fcc5f5cb · report fixture: signature x:Tensor/3/float, seqlen:int/0/int · returned Tensor · level recorded 2026-09-24
Block in 252 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
model/transformer_macdiff.py ran no licence file found · pointer only · d87bd702280998e1 · report fixture: returned Block · level recorded 2026-09-22
DecoderBlock in 30 papers model/transformer_macdiff.py ran no licence file found · pointer only · f035f943e5114e94 · report fixture: returned DecoderBlock · level recorded 2026-09-22
FeatureModulation model/transformer_macdiff.py ran no licence file found · pointer only · 0096ff0f534391b0 · report fixture: returned FeatureModulation · level recorded 2026-09-22
GaussianDiffusion in 61 papers model/transformer_macdiff.py ran no licence file found · pointer only · 44ea42448b5bf98c · report fixture: returned GaussianDiffusion · level recorded 2026-09-22
SkeleEmbed model/transformer_macdiff.py ran no licence file found · pointer only · 71aeba8837a31bba · report fixture: returned SkeleEmbed · level recorded 2026-09-22
UniformSampler model/transformer_macdiff.py ran no licence file found · pointer only · 391ceeaed087e497 · report fixture: returned UniformSampler · level recorded 2026-09-22
space_timesteps in 72 papers model/transformer_macdiff.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 9b6e4e070473e76f · report fixture: signature num_timesteps:int/0/int, section_counts:list/1/int · returned set · level recorded 2026-09-22
ScheduleSampler model/transformer_macdiff.py unverified no licence file found · pointer only · 9cc3dab0e22fbf67 · report
SpacedDiffusion in 12 papers model/transformer_macdiff.py unverified no licence file found · pointer only · 9a13449b9c6b302b · report
Transformer in 173 papers model/transformer_macdiff.py unverified no licence file found · pointer only · 2d91a1ea1d185ce8 · report
create_gaussian_diffusion model/transformer_macdiff.py unverified no licence file found · pointer only · 9bb0960c615d2f3e · 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 MacDiff (graph method: MacDiff). 20 bricks; individually on a fixture: 13 ran (of which 9 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified. The assembly has not been run end-to-end.

  1. Transformer entry · level 0 · unverified · 2d91a1ea1d185ce8
  2. Block helper · level 1 · ran · d87bd702280998e1
  3. DecoderBlock model · level 1 · ran · f035f943e5114e94
  4. SkeleEmbed data_transform · level 1 · ran · 71aeba8837a31bba
  5. UniformSampler helper · level 1 · ran · 391ceeaed087e497
  6. create_gaussian_diffusion helper · level 0 · unverified · 9bb0960c615d2f3e
  7. Attention helper · level 1 · ran · c41cf977fcc5f5cb
  8. DropPath helper · level 1 · ran · 75f5c156267fccbd
  9. MLP helper · level 1 · ran · 00ab6e2a5e0dd98d
  10. drop_path helper · level 1 · ran; the contract check could not run · 3ac6b7d76e8e3584
  11. FeatureModulation model · level 1 · ran · 0096ff0f534391b0
  12. ScheduleSampler helper · level 0 · unverified · 9cc3dab0e22fbf67
  13. SpacedDiffusion helper · level 0 · unverified · 9a13449b9c6b302b
  14. space_timesteps helper · level 1 · ran; the contract check could not run (RAISES) · 9b6e4e070473e76f
  15. GaussianDiffusion scheduler · level 1 · ran · 44ea42448b5bf98c
  16. _WrappedModel helper · level 1 · ran · eeb6b2016ef36e61
  17. LossType helper · level 0 · unverified · 3dfb2574af178220
  18. ModelMeanType helper · level 0 · unverified · f1e863a92ff43943
  19. ModelVarType helper · level 0 · unverified · 9df953f617d68af1
  20. _extract_into_tensor helper · level 1 · ran; the contract check could not run · 47d10dfc019ed932

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="2409.10473") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Action UnderstandingContrastive LearningData AugmentationRepresentation LearningSelf-Supervised Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Contrastive LearningDiffusion

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