TellMeTalk: Multimodal-driven talking face video generation.
Pengfei LiHuihuang ZhaoQingyun LiuPeng TangLin ZhangPublished in: Comput. Electr. Eng. (2024)
Keyphrases
- video data
- multimedia
- video sequences
- real time
- multimodal fusion
- video content
- multi modal
- video streams
- video analysis
- human faces
- data driven
- digital video
- multimodal information
- face images
- face detection and tracking
- story segmentation
- multimodal interaction
- real time video
- video images
- face biometrics
- video frames
- human activities
- video retrieval
- multimodal interfaces
- training set
- real time face tracking
- feature vectors
- space time
- images and video sequences
- multimodal biometrics
- temporal information
- key frames
- facial features
- video processing
- video surveillance
- video database
- audio visual