The Power of Sound (TPoS): Audio Reactive Video Generation with Stable Diffusion.
Yujin JeongWonjeong RyooSeunghyun LeeDabin SeoWonmin ByeonSangpil KimJinkyu KimPublished in: CoRR (2023)
Keyphrases
- multimedia
- audio content
- audio video
- audio signal
- multimedia processing
- video content analysis
- digital video
- scene change detection
- visual data
- video data
- audio files
- audio stream
- video content
- audio signals
- video analysis
- power consumption
- video sequences
- video files
- broadcast news
- soccer video
- story segmentation
- diffusion process
- audio features
- multimedia information
- space time
- closed captions
- audio visual content
- video frames
- video streams
- anisotropic diffusion
- digital audio
- content based video retrieval
- real time
- media streams
- lecture videos
- information diffusion
- video database
- video retrieval
- video surveillance
- multimedia content
- visual information
- video indexing
- reactive planning
- video copy detection
- video material
- video signals
- music information retrieval
- video clips
- signal processing
- image sequences
- social networks