Integrating Audio-Visual Features for Multimodal Deepfake Detection.
Sneha MuppallaShan JiaSiwei LyuPublished in: CoRR (2023)
Keyphrases
- visual features
- visual information
- audio visual
- image classification
- visual data
- audio features
- visual content
- image retrieval
- low level
- multimedia
- image search
- acoustic features
- image annotation
- low level features
- object detection
- global features
- keywords
- key frames
- semantic concepts
- image collections
- multi modal
- visual appearance
- video shots
- semantic features
- soccer video
- visual patterns
- bag of features
- semantic gap
- visual properties
- textual features
- content based video retrieval
- event detection
- image features
- high level