Speech-Driven Facial Animation by LSTM-RNN for Communication Use.
Ryosuke NishimuraNobuchika SakataTomu TominagaYoshinori HijikataKensuke HaradaKiyoshi KiyokawaPublished in: APMAR (2019)
Keyphrases
- facial animation
- recurrent neural networks
- facial expressions
- human faces
- neural network
- head motion
- facial motion
- temporal coherence
- feed forward
- motion tracking
- nearest neighbor
- facial images
- active appearance models
- high resolution
- head pose estimation
- motion capture data
- video sequences
- real time
- shape model
- activity recognition
- pose estimation