Network Bending of Diffusion Models for Audio-Visual Generation.
Luke DzwonczykCarmine Emanuele CellaDavid BanPublished in: CoRR (2024)
Keyphrases
- audio visual
- diffusion models
- multi modal
- information diffusion
- visual information
- multi stream
- audio visual speech recognition
- social networks
- visual data
- three dimensional
- viral marketing
- network structure
- communication networks
- objective function
- multimedia
- metadata
- data sets
- visual features
- diffusion process
- diffusion model