AI Paper Atlas

Research map / 3D vision / Human pose estimation

Learning Progressive Joint Propagation for Human Motion Prediction

Yujun Cai, Lin Huang, Yiwei Wang, Tat-Jen Cham, Jianfei Cai, Junsong Yuan, Jun Liu, Xu Yang, Yiheng Zhu, Xiaohui Shen, Ding Liu, Jing Liu and 1 more

ECCV 2020 · 3D vision › Human pose estimation · approach: Human motion prediction · 176 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 DCT-encoded spatial-temporal joint modeling to the temporal transformer (ablation)progressive transformer · Human3.6M 4 actions, MPJPEMPJPE 400ms (mm): 77.7 -> 41.2Improved
add progressive central-to-peripheral decoding to the non-progressive spatio-temporal transformer (ablation)motion transformer · Human3.6M 4 actions, MPJPEMPJPE 400ms (mm): 41.2 -> 39.6Improved
add progressive decoding (ablation)motion transformer · Human3.6M 4 actions, MPJPEMPJPE 80ms (mm): 9.9 -> 8.3Improved
propagate outward (center to periphery) instead of inward (ablation)progressive decoder · Human3.6M 4 actions, MPJPEMPJPE 400ms (mm): 40.2 -> 38.5Improved
propagate outward instead of inward (ablation)progressive decoder · Human3.6M 4 actions, MPJPEMPJPE 80ms (mm): 8.7 -> 7.8Improved
add the memory-based dictionary (ablation)motion transformer · Human3.6M 4 actions, MPJPEMPJPE 400ms (mm): 39.6 -> 38.5Improved
add the memory-based dictionary (ablation)motion transformer · Human3.6M 4 actions, MPJPEMPJPE 80ms (mm): 8.3 -> 7.8Improved
train on 3D coordinates directly instead of converting predicted anglesproposed model · Human3.6M MPJPE short-termMPJPE 400ms (mm): 64.5 -> 60.2Improved
use proposed model instead of GNN 3D baselineproposed model · Human3.6M short-termMPJPE 400ms (mm): 61.3 -> 60.2Improved
use proposed model instead of GNN baselineproposed model · Human3.6M MAE short-termMean Angle Error 400ms: 0.95 -> 0.94No clear effect
use proposed 3D model instead of GNN 3D baselineproposed model · Human3.6M long-termMPJPE 1000ms (mm): 71.0 -> 67.6Improved
use proposed 3D model instead of GNN 3D baselineproposed model · CMU-MocapMPJPE 1000ms (mm): 96.5 -> 93.2Improved

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