AI Paper Atlas

Research map / 3D vision / Human pose estimation

A Unified 3D Human Motion Synthesis Model via Conditional Variational Auto-Encoder

Yujun Cai, Yiwei Wang, Yiheng Zhu, Tat-Jen Cham, Jianfei Cai, Junsong Yuan, Jun Liu, Chuanxia Zheng, Sijie Yan, Henghui Ding, Xiaohui Shen, Ding Liu and 1 more

ICCV 2021 · 3D vision › Human pose estimation · approach: Human motion prediction · 73 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 Action-Adaptive Modulation instead of concatenating action label (ablation)Ours w/ action · Human3.6M action classificationaverage classification accuracy: 0.65 -> 0.91Improved
add action labels (concatenation, no AAM) (ablation)Ours w/o action · Human3.6M action classificationaverage classification accuracy: 0.45 -> 0.65Improved
add cross-attention mechanism (ablation)Ours w/ action · Human3.6MFIDg: 71.3 -> 62.5Improved
add cross-attention mechanism (ablation)Ours w/ action · Human3.6MMPJPE: 104.4 -> 97.3Improved
add cross-attention mechanism (ablation)Ours w/ action · Human3.6MIS: 6.43 -> 6.87Improved
add cross-attention mechanism (ablation)Ours w/ action · Human3.6MDiversity: 0.18 -> 0.18No clear effect
add action labels with AAM and classifierOurs w/o action · Human3.6MFIDg: 88.2 -> 62.5Improved
add action labels with AAM and classifierOurs w/o action · Human3.6MMPJPE: 115.6 -> 97.3Improved
add action labels with AAM and classifierOurs w/o action · Human3.6MDiversity: 0.26 -> 0.19Hurt
add action labels with AAM and classifierOurs w/o action · CMU-MocapFIDa: 162.3 -> 97.7Improved
add action labels with AAM and classifierOurs w/o action · CMU-MocapDiversity: 0.08 -> 0.05Hurt
use CVAE ours w/o action instead of CSGNCSGN · Human3.6MFIDg: 136.8 -> 88.2Improved

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