Papers › MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video

MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video

2 Mar 2022CVPR 2022 1arXiv:2203.00859archive 2025-07-28

Jinlu Zhang, Zhigang Tu, Jianyu Yang, Yujin Chen, Junsong Yuan

Recent transformer-based solutions have been introduced to estimate 3D human pose from 2D keypoint sequence by considering body joints among all frames globally to learn spatio-temporal correlation. We observe that the motions of different joints differ significantly. However, the previous methods cannot efficiently model the solid inter-frame correspondence of each joint, leading to insufficient learning of spatial-temporal correlation. We propose MixSTE (Mixed Spatio-Temporal Encoder), which has a temporal transformer block to separately model the temporal motion of each joint and a spatial transformer block to learn inter-joint spatial correlation. These two blocks are utilized alternately to obtain better spatio-temporal feature encoding. In addition, the network output is extended from the central frame to entire frames of the input video, thereby improving the coherence between the input and output sequences. Extensive experiments are conducted on three benchmarks (Human3.6M, MPI-INF-3DHP, and HumanEva). The results show that our model outperforms the state-of-the-art approach by 10.9% P-MPJPE and 7.6% MPJPE. The code is available at https://github.com/JinluZhang1126/MixSTE.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2203.00859")

Code

Syntology Ran 4 of 4 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 4 ran with no contract checked.

By repository: official repository: 4 samples from 1 repository, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

JinluZhang1126/MixSTE officialmentioned in papermentioned on GitHubpytorch 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

4 samples harvested; 4 ran; 0 honoured the contract we drafted; 0 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

4ran

Licence: 4 of the 4 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 JinluZhang1126/MixSTE. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

Attention JinluZhang1126/MixSTE/common/model_cross.py official repository ran · metamorphic tier: deterministic no licence file found · pointer only · a54bb4e29b966532 · report
Block JinluZhang1126/MixSTE/common/model_cross.py official repository ran · metamorphic tier: deterministic no licence file found · pointer only · 361cb029385178dc · report
MixSTE2 JinluZhang1126/MixSTE/common/model_cross.py official repository ran · metamorphic tier: deterministic no licence file found · pointer only · bff35ee778555423 · report
Mlp JinluZhang1126/MixSTE/common/model_cross.py official repository ran · metamorphic tier: deterministic no licence file found · pointer only · d1243176e8bb4111 · report

Tasks

3D Human Pose EstimationClassificationMonocular 3D Human Pose EstimationPose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Human Pose Estimation Human3.6M MixSTE (HRNet, T=243) Average MPJPE (mm) 39.8 #17 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M MixSTE (HRNet, T=243) Multi-View or Monocular Monocular #17 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M MixSTE (HRNet, T=243) Using 2D ground-truth joints No #17 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M MixSTE (CPN, T=243) Average MPJPE (mm) 40.9 #21 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M MixSTE (CPN, T=243) Multi-View or Monocular Monocular #21 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M MixSTE (CPN, T=243) Using 2D ground-truth joints No #21 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M MixSTE (CPN, T=81) Average MPJPE (mm) 42.4 #24 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M MixSTE (CPN, T=81) Multi-View or Monocular Monocular #24 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M MixSTE (CPN, T=81) Using 2D ground-truth joints No #24 of 88 Archive leaderboard report
3D Human Pose Estimation HumanEva-I MixSTE (T=43, FT) Mean Reconstruction Error (mm) 16.1 #7 of 31 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP MixSTE (T=27) AUC 66.5 #22 of 108 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP MixSTE (T=27) MPJPE 54.9 #22 of 108 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP MixSTE (T=27) PCK 94.4 #22 of 108 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP MixSTE (T=1) AUC 63.8 #24 of 108 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP MixSTE (T=1) MPJPE 57.9 #24 of 108 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP MixSTE (T=1) PCK 94.2 #24 of 108 Archive leaderboard report
Classification Full-body Parkinson’s disease dataset Mixste F1-score (weighted) 0.41 #7 of 7 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M MixSTE (HRNet, T=243) 2D detector HRNet #7 of 52 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M MixSTE (HRNet, T=243) Average MPJPE (mm) 39.8 #7 of 52 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M MixSTE (HRNet, T=243) Frames Needed 243 #7 of 52 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M MixSTE (HRNet, T=243) Need Ground Truth 2D Pose No #7 of 52 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M MixSTE (HRNet, T=243) Use Video Sequence Yes #7 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

Spatial Transformer

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