Mining Audio, Text and Visual Information for Talking Face Generation.
Lingyun YuJun YuQiang LingPublished in: ICDM (2019)
Keyphrases
- visual information
- textual information
- statistical natural language processing
- text mining
- visual features
- low level
- audio visual
- visual data
- visual content
- semantic information
- visual cues
- semantic context
- keywords
- video segments
- eye movements
- text data
- low level features
- face images
- information retrieval
- image collections
- text documents
- high level
- visual similarity
- content based image retrieval systems
- visual information retrieval
- data mining
- image annotation
- database
- text categorization
- natural language processing
- information extraction
- content based image