Papers › P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimation

P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimation

15 Mar 2022arXiv:2203.07628archive 2025-07-28

Wenkang Shan, Zhenhua Liu, Xinfeng Zhang, Shanshe Wang, Siwei Ma, Wen Gao

This paper introduces a novel Pre-trained Spatial Temporal Many-to-One (P-STMO) model for 2D-to-3D human pose estimation task. To reduce the difficulty of capturing spatial and temporal information, we divide this task into two stages: pre-training (Stage I) and fine-tuning (Stage II). In Stage I, a self-supervised pre-training sub-task, termed masked pose modeling, is proposed. The human joints in the input sequence are randomly masked in both spatial and temporal domains. A general form of denoising auto-encoder is exploited to recover the original 2D poses and the encoder is capable of capturing spatial and temporal dependencies in this way. In Stage II, the pre-trained encoder is loaded to STMO model and fine-tuned. The encoder is followed by a many-to-one frame aggregator to predict the 3D pose in the current frame. Especially, an MLP block is utilized as the spatial feature extractor in STMO, which yields better performance than other methods. In addition, a temporal downsampling strategy is proposed to diminish data redundancy. Extensive experiments on two benchmarks show that our method outperforms state-of-the-art methods with fewer parameters and less computational overhead. For example, our P-STMO model achieves 42.1mm MPJPE on Human3.6M dataset when using 2D poses from CPN as inputs. Meanwhile, it brings a 1.5-7.1 times speedup to state-of-the-art methods. Code is available at https://github.com/paTRICK-swk/P-STMO.

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 11 code samples: 10 from 1 repository linked to this paper, 1 identical to code harvested from another paper's repository. Across all 11: 9 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; 2 where Syntology's instrument failed) · 2 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: 10 samples from 1 repository, 8 ran (7 with no instrument failure; 1 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. 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.

patrick-swk/p-stmo officialmentioned in papermentioned on GitHubpytorchMITSyntology: 10 samples, 8 ran (1 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 6 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.

2ran · our draft was wrong
7ran
2unverified

Licence: 1 of the 11 samples is 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 patrick-swk/p-stmo. 1 sample is listed last, in a group without a repository. “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 5 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.

patrick-swk/p-stmo official repository 10 samples, 8 ran (1 instrument-failed) · 2 unverified
Encoder in 278 papers model/stmo_pretrain.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 1aaaa9db258f9346 · report fixture: returned Encoder · level recorded 2026-09-22
EncoderLayer in 73 papers model/stmo_pretrain.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 1e31c11931ce7561 · report fixture: returned EncoderLayer · level recorded 2026-09-22
FCBlock in 8 papers model/stmo_pretrain.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 3dd75f638909b681 · report fixture: returned FCBlock · level recorded 2026-09-22
Linear in 127 papers model/stmo_pretrain.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 106e2299d93b5ed7 · report fixture: returned Linear · level recorded 2026-09-22
MultiHeadedAttention in 38 papers model/stmo_pretrain.py ran · metamorphic tier: deterministic MIT (permissive) · 9bc6abc38072722f · report fixture: returned MultiHeadedAttention · level recorded 2026-09-22
PositionwiseFeedForward in 36 papers model/stmo_pretrain.py ran · metamorphic tier: invariant MIT (permissive) · cb80183aeec842d5 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
Transformer in 173 papers model/stmo_pretrain.py ran · metamorphic tier: deterministic MIT (permissive) · 56c8855e69bdbfe5 · report fixture: returned Transformer · level recorded 2026-09-22
attention in 144 papers
census: 11 implementations from 10 papers, 7 distinct outputs across 5 buckets, one shared input per bucket
model/stmo_pretrain.py ran · our draft was wrong MIT (permissive) · cbe07626e47b77c3 · report fixture: signature query:Tensor/3/float, key:Tensor/3/float, value:Tensor/3/float, mask:Tensor/3/float, dropout:callable/0/? · returned tuple · level recorded 2026-09-22
Model_MAE model/stmo_pretrain.py unverified MIT (permissive) · 75538e6a2c58ef23 · report
Transformer_dec model/stmo_pretrain.py unverified MIT (permissive) · a135de1a158f5ac6 · report
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
clones in 92 papers repository not located ran · our draft was wrong licence of this copy not recorded · d2d810cddae9f875 · report fixture: signature module:callable/0/?, N:int/0/int · returned ModuleList · level recorded 2026-09-22

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 P-STMO (graph method: P-STMO). 13 bricks; individually on a fixture: 11 ran (of which 7 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

  1. Model_MAE entry · level 0 · unverified · 75538e6a2c58ef23
  2. FCBlock helper · level 1 · ran · 3dd75f638909b681
  3. LayerNorm helper · level 1 · ran · 2691a73a5c57364c
  4. Transformer model · level 1 · ran · 56c8855e69bdbfe5
  5. Transformer_dec helper · level 0 · unverified · a135de1a158f5ac6
  6. Linear helper · level 1 · ran · 106e2299d93b5ed7
  7. Encoder model · level 1 · ran · 1aaaa9db258f9346
  8. EncoderLayer helper · level 1 · ran · 1e31c11931ce7561
  9. MultiHeadedAttention model · level 1 · ran · 9bc6abc38072722f
  10. PositionwiseFeedForward model · level 1 · ran · cb80183aeec842d5
  11. clones helper · level 1 · ran · our draft was wrong · d2d810cddae9f875
  12. SublayerConnection model · level 1 · ran · 36faad4da521bc32
  13. attention helper · level 1 · ran · our draft was wrong · cbe07626e47b77c3

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="2203.07628") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

3D Human Pose EstimationDenoisingMonocular 3D Human Pose EstimationPose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Human Pose Estimation Human3.6M P-STMO (N=243) Average MPJPE (mm) 42.1 #23 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M P-STMO (N=243) Multi-View or Monocular Monocular #23 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M P-STMO (N=243) PA-MPJPE 34.4 #23 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M P-STMO (N=243) Using 2D ground-truth joints No #23 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M P-STMO-S (N=81) Average MPJPE (mm) 44.1 #34 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M P-STMO-S (N=81) Multi-View or Monocular Monocular #34 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M P-STMO-S (N=81) Using 2D ground-truth joints No #34 of 88 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP P-STMO (N=81) AUC 75.8 #15 of 108 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP P-STMO (N=81) MPJPE 32.2 #15 of 108 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP P-STMO (N=81) PCK 97.9 #15 of 108 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M P-STMO (N=243) 2D detector CPN #12 of 52 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M P-STMO (N=243) Average MPJPE (mm) 42.1 #12 of 52 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M P-STMO (N=243) Frames Needed 243 #12 of 52 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M P-STMO (N=243) Need Ground Truth 2D Pose No #12 of 52 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M P-STMO (N=243) Use Video Sequence Yes #12 of 52 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

CPNConvolutionNon Maximum Suppression

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