AI Paper Atlas

Research map / Video / Video generation

Local Action-Guided Motion Diffusion Model for Text-to-Motion Generation

Peng Jin, Hao Li, Zesen Cheng, Kehan Li, Runyi Yu, Chang Liu, Xiangyang Ji, Li Yuan, Jie Chen

ECCV 2024 · Video › Video generation · approach: Text-to-motion diffusion · 15 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 local action guidance to the motion+action level model (ablation)GuidedMotion · HumanML3D testFID: 0.133 -> 0.119Improved
add local action guidance to the full three-level model (ablation)GuidedMotion · HumanML3D testFID: 0.107 -> 0.057Improved
add action level to motion-level-only model (ablation)GuidedMotion · HumanML3D testFID: 0.186 -> 0.133Improved
add specific level to model with motion+action levels, no guidance (ablation)GuidedMotion · HumanML3D testFID: 0.133 -> 0.107Improved
add specific level without guidance (ablation)GuidedMotion · HumanML3D testR-Precision Top-3: 0.771 -> 0.769Hurt
increase VAE token size from 2 to 8 (ablation)motion VAE · HumanML3D testFID: 1.906 -> 0.019Improved
increase VAE token size from 2 to 8 (ablation)motion VAE · KIT testR-Precision Top-3: 0.745 -> 0.760Mixed
allocate more diffusion steps per level (150 vs 300 total) (ablation)GuidedMotion · HumanML3D testFID: 0.057 vs 0.062No clear effect
use local-to-global paradigm instead of direct global generationGuidedMotion · HumanML3D complex motion subsetFID: 0.314 -> 0.144Improved
split diffusion into three levels with same total stepsGuidedMotion vs MLD · HumanML3D testinference time (s): 2.4998 -> 2.5189No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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