EMSYNC

model·video conditioned symbolic music generation model·active·also: EMotion and SYNChronization

Video-to-MIDI generation model aligning musical emotion and chord timing with video content and scene boundaries.

Recorded facts

Official sitehttps://arxiv.org/abs/2502.10154
GeographyPorto, Portugal
arxiv2502.10154
dedupe risklow
discovery routemultilingual official-source discovery
proposed subtypevideo_conditioned_symbolic_music_generation_model
evidence strengthstrong
recommended prompt05-models-and-apis
proposed entity typeModel
classification rationaleThe source presents EMSYNC as video_conditioned_symbolic_music_generation_model with material AI-music or audio-AI relevance.

Current

developed bySerkan SulunSource 1 VERIFIED high confidence
introduces (by)Video Soundtrack Generation by Aligning Emotions and Temporal BoundariesSource 1 VERIFIED high confidence
describes (by)Video-based Music GenerationSource 1 VERIFIED high confidence

History

described byVideo Soundtrack Generation by Aligning Emotions and Temporal BoundariesUnverifiedSource 1 VERIFIED high confidence

Sources & changes

Checked 10d ago · lowhow verification works
  • Status unknown → active
  • Official URL unknown → arxiv.org/abs/2502.10154
  • Record maintenance · 12 fields updated

Is this yours? Claim this record →·See something wrong? Report a correction →