Real-time conversion from a single 2D face image to a 3D text-driven emotive audio-visual avatar.
Hao TangYuxiao HuYun FuMark Hasegawa-JohnsonThomas S. HuangPublished in: ICME (2008)
Keyphrases
- audio visual
- visual data
- multi modal
- image data
- input image
- visual information
- image features
- image representation
- feature points
- image retrieval
- image classification
- image content
- information retrieval
- emotion recognition
- multiscale
- face recognition
- data sets
- multi stream
- text mining
- video sequences
- spatial information
- multimedia data
- input data
- multimedia