A Novel Lightweight Audio-visual Saliency Model for Videos.
Dandan ZhuXuan ShaoQiangqiang ZhouXiongkuo MinGuangtao ZhaiXiaokang YangPublished in: ACM Trans. Multim. Comput. Commun. Appl. (2023)
Keyphrases
- lightweight
- audio visual
- video summarization
- saliency model
- visual saliency
- multi modal
- visual data
- visual information
- biologically inspired
- saliency map
- video frames
- multimedia
- video sequences
- human visual system
- salient regions
- region of interest
- high dimensional
- spatio temporal
- wireless sensor networks
- video content
- object recognition
- image classification
- key frames
- eye movements
- high dimensional data
- image database
- visual features
- natural images