V2Meow: Meowing to the Visual Beat via Video-to-Music Generation.
Kun SuJudith Yue LiQingqing HuangDima KuzminJoonseok LeeChris DonahueFei ShaAren JansenYu WangMauro VerzettiTimo I. DenkPublished in: AAAI (2024)
Keyphrases
- visual cues
- visual data
- video data
- visual analysis
- visual information
- video content
- visual features
- audio signals
- video sequences
- video search
- audio files
- audio features
- content based video retrieval
- video database
- audio content
- eye tracking data
- multimedia
- digital audio
- video indexing and retrieval
- computer music
- low level
- video frames
- video streams
- video segmentation
- digital video
- mid level
- video analysis
- video clips
- video retrieval
- keywords
- music information retrieval
- music recommendation
- online video
- semantic labels
- real time
- high level
- spatial and temporal
- multimedia data
- temporal information
- video indexing
- news video
- event recognition
- generation process