Unified Audio-Visual Saliency Model for Omnidirectional Videos With Spatial Audio.
Dandan ZhuKaiwei ZhangNana ZhangQiangqiang ZhouXiongkuo MinGuangtao ZhaiXiaokang YangPublished in: IEEE Trans. Multim. (2024)
Keyphrases
- audio visual
- video summarization
- audio features
- saliency model
- visual saliency
- visual data
- multi modal
- visual information
- multimodal fusion
- spatial and temporal
- center surround
- saliency map
- multimedia
- spatial information
- audio visual speech recognition
- multi stream
- video frames
- spatio temporal
- spatial relationships
- spatial relations
- biologically inspired
- spatial data
- vision system
- region of interest
- video sequences
- computer vision
- video content
- visual attention
- key frames
- video data
- visual features