AI Paper Atlas

Research map / Video / Video generation

StyleMotif: Multi-Modal Motion Stylization using Style-Content Cross Fusion

Ziyu Guo, Young Yoon Lee, Joseph Liu, Yizhak Ben-Shabat, Victor Zordan, Mubbasir Kapadia

ICCV 2025 · Video › Video generation · approach: Text-to-motion diffusion · 10 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
single-branch style fusion instead of SMooDi dual-branch designStyleMotif · Efficiency (A100)learnable parameters: 13.9 M -> 7.8 MImproved
single-branch style fusion instead of dual-branch designStyleMotif · Efficiency (A100)inference time: 4.0 s -> 3.1 sImproved
style-content cross fusion with multi-modal alignment vs ChatGPT+MLDMLD · Text-guided stylizationSRA: 4.82% -> 56.71%Improved
style-content cross fusion vs SMooDiStyleMotif · Motion-guided stylizationSRA: +5.23%Improved
StyleMotif vs baseline on style transferStyleMotif · Motion style transferSRA / FID: +3.66% SRA, 0.207 FID reductionImproved
pre-train style encoder on both HumanML3D and 100STYLE rather than one (ablation)StyleMotif style encoder · Motion-guided stylizationSRA / FIDImproved
set cross-normalization scaling ratio gamma to 0.6 (ablation)StyleMotif · Text-guided stylizationSRA / FID: best at gamma=0.6Improved
use single-label text instead of brief or detailed descriptions for alignment (ablation)StyleMotif · Multi-modal alignmentstylization qualityImproved

Later papers that compared with this method

1 later accepted paper reports StyleMotif as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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