FakeOut: Leveraging Out-of-domain Self-supervision for Multi-modal Video Deepfake Detection.
Gil KnafoOhad FriedPublished in: CoRR (2022)
Keyphrases
- multi modal
- semantic concepts
- video search
- multiple modalities
- video data
- multi modality
- audio visual
- multimedia
- cross modal
- video clips
- image annotation
- video content
- event detection
- video streams
- video frames
- high dimensional
- video sequences
- video analysis
- video database
- computer vision
- spatial and temporal
- active learning
- key frames
- visual cues
- feature extraction
- fusing multiple