AI Paper Atlas

Research map / 3D vision / Human pose estimation

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

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

CVPR 2022 · 3D vision › Human pose estimation · approach: Temporal video pose estimation · 420 citations (OpenAlex)

Check your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use MixSTE instead of PoseFormerHuman3.6M with CPN keypoints, Protocol 1 · Human3.6M Protocol 1 (CPN)MPJPE (mm): 44.3 -> 40.9Improved
use MixSTE with ground-truth 2D keypoints instead of Wang et al.Human3.6M Protocol 1 · Human3.6M Protocol 1 (ground-truth 2D keypoints)MPJPE (mm): 25.6 -> 21.6Improved
use MixSTE instead of the strongest listed baselineMPI-INF-3DHP test set · MPI-INF-3DHP test setPCK: 88.6 -> 94.4Improved
fine-tune MixSTE from Human3.6MMixSTE on HumanEva · HumanEva Protocol 1MPJPE (mm): 28.5 -> 16.1Improved
add alternating spatial and temporal transformer blocks (ablation)Seq2seq baseline on Human3.6M · Human3.6MMPJPE (mm): 51.7 -> 45.5Improved
add joint separation in the temporal transformer (ablation)Seq2seq with alternating design on Human3.6M · Human3.6MMPJPE (mm): 45.5 -> 41.7Improved
add joint separation in the temporal transformer (ablation)Seq2seq with alternating design on Human3.6M · Human3.6MFLOPs (M): 186405 -> 645Improved
replace MPJPE loss with WMPJPE loss (ablation)MixSTE on Human3.6M · Human3.6MMPJPE (mm): 41.7 -> 41.3Improved
add TCLoss to WMPJPE loss (ablation)MixSTE on Human3.6M · Human3.6MMPJVE: 4.6 -> 3.6Improved
add MPJVE loss to WMPJPE loss (ablation)MixSTE on Human3.6M · Human3.6MMPJVE: 4.6 -> 2.6Improved
add the proposed T-Loss to WMPJPE loss (ablation)MixSTE on Human3.6M · Human3.6MMPJVE: 4.6 -> 2.3Improved
increase depth from 4 to 10 with channel 64 and T=27 (ablation)MixSTE on Human3.6M · Human3.6MMPJPE (mm): 54.3 -> 51.1Improved

Later papers that compared with this method

10 later accepted papers report MixSTE as a baseline in their results tables; 8 of them report a better number on most of the results they share with it.

2 more not listed.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy