AI Paper Atlas

Research map / Video / Video generation

Human Joint Kinematics Diffusion-Refinement for Stochastic Motion Prediction

Dong Wei, Huaijiang Sun, Bin Li, Jianfeng Lu, Weiqing Li, Xiaoning Sun, Shengxiang Hu

AAAI 2023 · Video › Video generation · approach: Text-to-motion diffusion · 51 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
use diffusion-refinement instead of DLowstochastic human motion prediction · Human3.6MAPD: 11.741 -> 15.353Improved
use diffusion-refinement instead of DLowstochastic human motion prediction · HumanEva-IAPD: 4.855 -> 5.931Improved
add the GCN refinement network to diffusion (ablation)MotionDiff · Human3.6MADE: 0.486 -> 0.411Improved
add the GCN refinement network to diffusion (ablation)MotionDiff · HumanEva-IADE: 0.273 -> 0.232Improved
add the GCN refinement network to diffusion (ablation)MotionDiff · Human3.6MAPD: 15.534 -> 15.353Hurt
add the GCN refinement network to diffusion (ablation)MotionDiff · HumanEva-IAPD: 6.508 -> 5.931Hurt
use joint embedding and spatial transformer instead of linear pose projection (ablation)MotionDiff · Human3.6MFDE: 0.535 -> 0.509Improved
replace temporal transformer with MLP (ablation)MotionDiff · Human3.6MAPD: 15.353 -> 10.943Hurt
set spatial transformer dimension to 48 instead of 32 (ablation)MotionDiff · Human3.6MAPD: 15.353 -> 15.761Improved
set spatial transformer dimension to 48 instead of 32 (ablation)MotionDiff · Human3.6MFDE: 0.509 -> 0.543Hurt
set temporal transformer dimension to 256 instead of 512 (ablation)MotionDiff · Human3.6MAPD: 15.353 -> 12.4735Hurt
use L1 instead of L2 distance (ablation)MotionDiff · Human3.6MAPD: 15.353 -> 13.894Hurt

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