AI Paper Atlas

Research map / 3D vision / Human pose estimation

3D Human Pose Estimation With Spatial and Temporal Transformers

Ce Zheng, Sijie Zhu, Matias Mendieta, Taojiannan Yang, Chen Chen, Zhengming Ding

ICCV 2021 · 3D vision › Human pose estimation · approach: Transformer-based multi-view 3D pose · 778 citations (OpenAlex)

Read the paperCheck 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
add spatial transformer to temporal-only transformer (ablation)PoseFormer · Human3.6M Protocol 1 (f=9)MPJPE (mm): 52.5 to 49.9Improved
add temporal positional embedding to spatial-temporal model (ablation)PoseFormer · Human3.6M Protocol 1 (f=9)MPJPE (mm): 51.6 -> 50.5Improved
add spatial positional embedding to spatial-temporal model (ablation)PoseFormer · Human3.6M Protocol 1 (f=9)MPJPE (mm): 51.6 -> 50.7Improved
add both spatial and temporal positional embeddings (ablation)PoseFormer · Human3.6M Protocol 1 (f=9)MPJPE (mm): 51.6 -> 49.9Improved
add spatial transformer to temporal baseline (Protocol 1, f=81) (ablation)PoseFormer · Human3.6M Protocol 1MPJPE (mm): 47.2 -> 44.3Improved
add spatial transformer to temporal baseline (Protocol 2, f=81) (ablation)PoseFormer · Human3.6M Protocol 2P-MPJPE (mm): 37.0 -> 34.6Improved
increase input frames from 9 to 27 (ablation)PoseFormer · Human3.6M Protocol 1MPJPE (mm): 49.9 -> 47.0Improved
increase input frames from 27 to 81 (ablation)PoseFormer · Human3.6M Protocol 1MPJPE (mm): 47.0 -> 44.3Improved
use ground-truth 2D pose instead of CPN-detected 2D posePoseFormer · Human3.6M Protocol 1MPJPE (mm): 44.3 to 31.3Improved
increase layers L_S=L_T from 2 to 4 at c=32 (ablation)PoseFormer · Human3.6M Protocol 1MPJPE (mm): 52.4 -> 49.9Improved
increase layers L_S=L_T from 4 to 6 at c=32 (ablation)PoseFormer · Human3.6M Protocol 1MPJPE (mm): 49.9 -> 50.3Hurt
increase embedding dim c from 32 to 48 at 4 layers (ablation)PoseFormer · Human3.6M Protocol 1MPJPE (mm): 49.9 -> 50.4Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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