Papers › Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimation

Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimation

26 Mar 2021arXiv:2103.14304archive 2025-07-28

Wenhao Li, Hong Liu, Runwei Ding, Mengyuan Liu, Pichao Wang, Wenming Yang

Despite the great progress in 3D human pose estimation from videos, it is still an open problem to take full advantage of a redundant 2D pose sequence to learn representative representations for generating one 3D pose. To this end, we propose an improved Transformer-based architecture, called Strided Transformer, which simply and effectively lifts a long sequence of 2D joint locations to a single 3D pose. Specifically, a Vanilla Transformer Encoder (VTE) is adopted to model long-range dependencies of 2D pose sequences. To reduce the redundancy of the sequence, fully-connected layers in the feed-forward network of VTE are replaced with strided convolutions to progressively shrink the sequence length and aggregate information from local contexts. The modified VTE is termed as Strided Transformer Encoder (STE), which is built upon the outputs of VTE. STE not only effectively aggregates long-range information to a single-vector representation in a hierarchical global and local fashion, but also significantly reduces the computation cost. Furthermore, a full-to-single supervision scheme is designed at both full sequence and single target frame scales applied to the outputs of VTE and STE, respectively. This scheme imposes extra temporal smoothness constraints in conjunction with the single target frame supervision and hence helps produce smoother and more accurate 3D poses. The proposed Strided Transformer is evaluated on two challenging benchmark datasets, Human3.6M and HumanEva-I, and achieves state-of-the-art results with fewer parameters. Code and models are available at https://github.com/Vegetebird/StridedTransformer-Pose3D.

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 10 code samples harvested from 1 repository linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 10 samples from 1 repository, 8 ran (8 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 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

Vegetebird/StridedTransformer-Pose3D officialmentioned in papermentioned on GitHubpytorchMITSyntology: 10 samples, 8 ran (0 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

10 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 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.

8ran
2unverified

Licence: 1 of the 10 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, 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 Vegetebird/StridedTransformer-Pose3D. “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.

Vegetebird/StridedTransformer-Pose3D official repository 10 samples, 8 ran (0 instrument-failed) · 2 unverified
camera_to_world in 5 papers common/camera.py ran MIT (permissive) · 0892bc8406224611 · report fixture: signature X:ndarray/3/float, R:ndarray/1/float, t:ndarray/3/float · returned ndarray · level recorded 2026-09-25
coco_h36m demo/lib/preprocess.py ran MIT (permissive) · f3a0f7cf8690505f · report fixture: signature keypoints:ndarray/3/float · returned tuple · level recorded 2026-09-24
deterministic_random in 5 papers common/utils.py ran fingerprinted MIT (permissive) · ec58bab810b80366 · report fixture: signature min_value:int/0/int, max_value:int/0/int, data:str/0/str · returned int · level recorded 2026-09-25
h36m_coco_format demo/lib/preprocess.py ran MIT (permissive) · 85be84dc21eb6ce3 · report fixture: signature keypoints:ndarray/4/float, scores:ndarray/3/float · returned tuple · level recorded 2026-09-24
mpjpe_cal common/utils.py ran fingerprinted MIT (permissive) · c5148aea3c7b76b6 · report fixture: signature predicted:Tensor/3/float, target:Tensor/3/float · returned Tensor · level recorded 2026-09-25
revise_kpts demo/lib/preprocess.py ran MIT (permissive) · b9f70678ddc9add2 · report fixture: signature h36m_kpts:ndarray/4/float, h36m_scores:ndarray/3/float, valid_frames:list/1/ndarray · returned ndarray · level recorded 2026-09-24
show2Dpose demo/vis.py ran MIT (permissive) · 912a1369d1563d3b · report fixture: signature kps:ndarray/2/float, img:ndarray/3/int · returned ndarray · level recorded 2026-09-25
test_calculation common/utils.py ran MIT (permissive) · d8222b9b5b8b97c9 · report fixture: signature predicted:Tensor/3/float, target:Tensor/3/float, action:list/1/str, error_sum:dict/0/?, data_type:str/0/str, subject:str/0/str · returned dict · level recorded 2026-09-25
normalize_screen_coordinates in 14 papers common/camera.py unverified MIT (permissive) here; the stored copy is pointer only · 82baf6aa4fb040a1 · report
world_to_camera in 8 papers common/camera.py unverified MIT (permissive) · 32eca53ede0ea499 · report

Tasks

3D Human Pose EstimationMonocular 3D Human Pose EstimationPose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Human Pose Estimation Human3.6M StridedTransformer (T=351) Average MPJPE (mm) 43.7 #31 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M StridedTransformer (T=351) Multi-View or Monocular Monocular #31 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M StridedTransformer (T=351) Using 2D ground-truth joints No #31 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M StridedTransformer (T=243) Average MPJPE (mm) 44 #32 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M StridedTransformer (T=243) Multi-View or Monocular Monocular #32 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M StridedTransformer (T=243) Using 2D ground-truth joints No #32 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M StridedTransformer (T=81) Average MPJPE (mm) 45.4 #46 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M StridedTransformer (T=81) Multi-View or Monocular Monocular #46 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M StridedTransformer (T=81) Using 2D ground-truth joints No #46 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M StridedTransformer (T=27) Average MPJPE (mm) 46.9 #50 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M StridedTransformer (T=27) Multi-View or Monocular Monocular #50 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M StridedTransformer (T=27) Using 2D ground-truth joints No #50 of 88 Archive leaderboard report
3D Human Pose Estimation HumanEva-I StridedTransformer (T=27 GT) Mean Reconstruction Error (mm) 12.2 #2 of 31 Archive leaderboard report
3D Human Pose Estimation HumanEva-I StridedTransformer (T=27 MRCNN) Mean Reconstruction Error (mm) 18.9 #9 of 31 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

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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