AI Paper Atlas

Research map / Video / Video generation

A Unified Framework for Motion Reasoning and Generation in Human Interaction

Jeongeun Park, Sungjoon Choi, Sangdoo Yun

ICCV 2025 · Video › Video generation · approach: Text-to-motion diffusion · 4 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 the Inter-MT2 dataset to training (ablation)VIM · Motion reasoningCoherence: 2.770 -> 5.252Improved
add the Inter-MT2 dataset to training (ablation)VIM · Motion reasoningMAUVE: 0.004 -> 0.794Improved
add the Inter-MT2 dataset to training (ablation)VIM · Motion editingFID: 0.080 -> 0.064Improved
add the Inter-MT2 dataset to training (ablation)VIM · Motion editingMPJPE: 0.908 -> 0.758Improved
add the Inter-MT2 dataset to training (ablation)VIM · Reaction generationMPJPE: 0.984 -> 0.691Improved
add the Inter-MT2 dataset to training (ablation)VIM · Reaction generationFID: 0.031 -> 0.019Improved
add the Inter-MT2 dataset to training (ablation)VIM · Text-to-motionFID: 0.082 -> 0.059Improved
add the Inter-MT2 dataset to training (ablation)VIM · Text-to-motionR Top3: 0.561 -> 0.568Improved
add the Inter-MT2 dataset to training (ablation)VIM · Motion-to-textR Top3: 0.894 -> 0.901Improved
use unified model instead of two-stage TM2T + GPT-4oVIM · Motion reasoningCoherence: 4.266 -> 5.252Improved
use unified VIM instead of two-stage TM2T + InterGENVIM · Motion editingFID: 0.110 -> 0.064Improved
use RQ-VAE tokenizer instead of VQ-VAE (ablation)VIM · Reaction generationMPJPE: 1.109 -> 0.691Improved

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