Real-Time Audio-Guided Multi-Face Reenactment.
Jiangning ZhangXianfang ZengChao XuYong LiuPublished in: IEEE Signal Process. Lett. (2022)
Keyphrases
- real time
- multimedia
- music score
- high speed
- signal processing
- facial feature tracking
- face images
- low cost
- human faces
- gender recognition
- facial expressions
- face detection and tracking
- multimodal fusion
- real time systems
- facial images
- audio stream
- face tracking
- complex background
- recognition algorithm
- quality of service
- multi modal
- neural network