Expotion fine-tunes MusicGen with facial-expression and body-motion features plus text, and reports improved music quality and video-music alignment over text-only and video-only baselines.
Visual and Motion-Based Control Early interactive sys- tems mapped facial or bodily features directly to sound
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
EXPOTION: Facial Expression and Motion Control for Multimodal Music Generation
Expotion fine-tunes MusicGen with facial-expression and body-motion features plus text, and reports improved music quality and video-music alignment over text-only and video-only baselines.