A new public-domain film dataset and a frame-by-frame dialogue-conditioning module improve video-to-music generation on paired-fidelity metrics.
First, we bench- mark video-to-music generation tasks by comparing existing video-to-music generation models trained and evaluated on identical data, using OSSL-v2
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Dialogue-Aware Video-to-Music Generation Using Public Domain Film Collections
A new public-domain film dataset and a frame-by-frame dialogue-conditioning module improve video-to-music generation on paired-fidelity metrics.