Semi-supervised Speech-driven 3D Facial Animation via Cross-modal Encoding.
Peiji YangHuawei WeiYicheng ZhongZhisheng WangPublished in: ICCV (2023)
Keyphrases
- facial animation
- cross modal
- semi supervised
- multi modal
- facial expressions
- multimedia retrieval
- image retrieval
- human faces
- facial images
- active appearance models
- multimedia databases
- labeled data
- temporal coherence
- multi view
- active learning
- visual similarity
- motion capture data
- face model
- generative model
- pairwise
- visual data
- head motion
- data sets
- face images
- multiscale
- image sequences
- three dimensional
- feature selection