DiffSal: Joint Audio and Video Learning for Diffusion Saliency Prediction.
Junwen XiongPeng ZhangTao YouChuanyue LiWei HuangYufei ZhaPublished in: CoRR (2024)
Keyphrases
- learning algorithm
- multimedia
- learning process
- prediction accuracy
- learning systems
- video data
- video sequences
- reinforcement learning
- signal processing
- learning tasks
- interactive video
- supervised learning
- online learning
- learning environment
- video frames
- video streams
- multimedia data
- anisotropic diffusion
- digital video
- audio video
- multimedia processing