AI Paper Atlas

Research map / Video / Video generation

Multi-Modal Controlled Coherent Motion Generation

Yifei Liu, Qiong Cao, Hongwei Yi, Huaiguang Jiang, Changxing Ding

ECCV 2026 · Video › Video generation · approach: Text-to-motion diffusion · 0 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 spine to the audio-driven body mask (ablation)MOCO · Multi-modal benchmarkFID+: 0.862 -> 0.921Hurt
use spine and legs for the audio-driven mask instead of head and arms (ablation)MOCO · Multi-modal benchmarkR1: 24.6 -> 7.9Hurt
use spine and legs for audio mask instead of head and arms (ablation)MOCO · Multi-modal benchmarkFID-A: 3.83 -> 2.75Mixed
share weights between text and speech denoisers (ablation)MOCO · Multi-modal benchmarkR1: 24.6 -> 22.1Hurt
share weights between text and speech denoisers (ablation)MOCO · Multi-modal benchmarkFID-A: 3.83 -> 4.24Hurt
add per-step combination of body parts instead of combining only at the end (ablation)MOCO · Multi-modal benchmarkTSR: 1.17 -> 0.90Improved
add per-step combination instead of combining only at the end (ablation)MOCO · Multi-modal benchmarkBeat consistency: 2.27 -> 2.72Improved
add per-step combination instead of combining once (ablation)MOCO · User studyBetter body coherence (%): 17.0 -> 71.0Improved
use decoupled denoising instead of weighted sumMOCO vs Weighted Sum · Multi-modal benchmarkR1: 6.8 -> 24.6Improved
use decoupled denoising instead of pseudo-text trainingMOCO vs Pseudo-Text · Multi-modal benchmarkR1: 2.2 -> 24.6Improved
add post-hoc L-BFGS optimization to trajectory predictor (ablation)G_T2V · Trajectory controlLocation average difference: 0.56 -> 0.08Improved
add classifier-free guidance to trajectory predictor (ablation)G_T2V · Trajectory controlLocation average difference: 0.56 -> 0.57No clear effect

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