Sound to Visual: Hierarchical Cross-Modal Talking Face Generation.
Lele ChenHaitian ZhengRoss K. MaddoxZhiyao DuanChenliang XuPublished in: CVPR Workshops (2019)
Keyphrases
- cross modal
- multi modal
- perceptual information
- image retrieval
- multimedia retrieval
- multimedia databases
- visual similarity
- visual data
- face images
- visual recognition
- visual information
- information retrieval
- image database
- visual features
- metadata
- information retrieval systems
- content based retrieval
- co occurrence
- object detection
- data points
- computer vision
- keywords