Lavs: A Lightweight Audio-Visual Saliency Prediction Model.
Dandan ZhuDefang ZhaoXiongkuo MinTian HanQiangqiang ZhouShaobo YuYongqing ChenGuangtao ZhaiXiaokang YangPublished in: ICME (2021)
Keyphrases
- lightweight
- prediction model
- visual saliency
- saliency map
- visual attention
- natural images
- regression model
- human detection
- eye movements
- multimedia
- visual information
- saliency model
- human visual system
- bayesian framework
- neural network
- audio visual
- visual search
- natural scenes
- focus of attention
- visual data
- salient regions
- image processing
- eye tracking data
- region of interest
- visual quality
- image quality
- input image
- feature selection