A semi-supervised contrastive learning framework with an inference-time control dial improves and tunes video-to-music and music-to-video retrieval.
It’s time for artistic correspondence in music and video,
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.MM 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Semi-Supervised Contrastive Learning for Controllable Video-to-Music Retrieval
A semi-supervised contrastive learning framework with an inference-time control dial improves and tunes video-to-music and music-to-video retrieval.