StyleTalker: One-shot Style-based Audio-driven Talking Head Video Generation.
Dongchan MinMinyoung SongSung Ju HwangPublished in: CoRR (2022)
Keyphrases
- multimedia
- audio video
- scene change detection
- digital video
- visual data
- multimedia processing
- real time
- video content analysis
- video files
- video data
- video material
- video sequences
- audio files
- video content
- digital audio
- video streams
- video analysis
- multimedia information
- audio signals
- audio stream
- signal processing
- media streams
- video recordings
- audio features
- video signals
- space time
- visual information
- video frames
- audio signal
- soccer video
- online video
- audio visual content
- mouth region
- video retrieval
- video surveillance
- video scene
- closed captions
- key frames
- motion estimation
- audio content
- event detection
- video copy detection
- audio visual
- face recognition
- broadcast news