AI Paper Atlas

Research map / 3D vision / Human pose estimation

Spatiotemporal Co-Attention Recurrent Neural Networks for Human-Skeleton Motion Prediction

Xiangbo Shu, Liyan Zhang, Guo-Jun Qi, Wei Liu, Jinhui Tang

TPAMI 2021 · 3D vision › Human pose estimation · approach: Human motion prediction · 291 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 skeleton-joint co-attention (SCA) (ablation)SC-RNN · H3.6M avg 15 actions, 1000msmean angle error: 1.52 -> 1.46Improved
add skeleton-joint co-attention (SCA) (ablation)SC-RNN · H3.6M avg 15 actions, 80msmean angle error: 0.49 -> 0.37Improved
add skeleton-joint co-attention (SCA) (ablation)SC-RNN · H3.6M avg 15 actions, 400msmean angle error: 1.20 -> 1.04Improved
add joint attention to skeleton attention (ablation)SC-RNN · H3.6M avg 15 actions, 1000msmean angle error: 1.51 -> 1.46Improved
add skeleton attention to joint attention (ablation)SC-RNN · H3.6M avg 15 actions, 1000msmean angle error: 1.49 -> 1.46Improved
add joint attention to skeleton attention at short horizon (ablation)SC-RNN · H3.6M avg 15 actions, 400msmean angle error: 1.06 -> 1.04No clear effect
use traveling-based joint sequence instead of ID-based sequence (ablation)SC-RNN · H3.6M, 1000msmean angle error: 1.50 -> 1.46Improved
use traveling-based joint sequence instead of surrounding-based sequence (ablation)SC-RNN · H3.6M, 1000msmean angle error: 1.48 -> 1.46Improved
use traveling-based joint sequence instead of ID-based sequence (ablation)SC-RNN · H3.6M, 80msmean angle error: 0.40 -> 0.37Improved
use SC-RNN instead of MHUSC-RNN · H3.6M avg 15 actions, 1000msmean angle error: 1.54 -> 1.46Improved
use SC-RNN instead of MHU at 80msSC-RNN · H3.6M avg 15 actions, 80msmean angle error: 0.37 -> 0.37No clear effect
use SC-RNN instead of MHU on greeting actionSC-RNN · H3.6M greeting, 1000msmean angle error: 1.88 -> 1.64Improved

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