An Audio-Visual Attention Based Multimodal Network for Fake Talking Face Videos Detection.
Ganglai WangPeng ZhangLei XieWei HuangYufei ZhaYanning ZhangPublished in: CoRR (2022)
Keyphrases
- visual attention
- multimodal fusion
- eye tracking
- saliency map
- eye movements
- eye tracking data
- visual search
- audio visual
- focus of attention
- vision system
- visual perception
- multi modal
- natural scenes
- salient regions
- visual saliency
- higher level
- multimedia
- visual attention model
- detection method
- visual information
- object detection
- attention mechanism
- video sequences
- biological vision systems
- visual data
- human detection
- saliency detection
- visual scene
- high frequency
- video data
- low level
- object recognition
- keywords