A two-stage video-to-music model with four time-varying controls (rhythm, melody, intensity, emotion) claims better controllability and alignment than prior V2M systems.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.MM 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Controllable Video-to-Music Generation with Multiple Time-Varying Conditions
A two-stage video-to-music model with four time-varying controls (rhythm, melody, intensity, emotion) claims better controllability and alignment than prior V2M systems.