Speech-to-video synthesis using MPEG-4 compliant visual features.
Petar S. AleksicAggelos K. KatsaggelosPublished in: IEEE Trans. Circuits Syst. Video Technol. (2004)
Keyphrases
- visual features
- content based video retrieval
- audio features
- key frames
- visual descriptors
- semantic concepts
- visual information
- multimedia
- video shots
- video sequences
- visual data
- visual content
- image classification
- video objects
- human actions
- image retrieval
- image search
- low level
- motion features
- image annotation
- acoustic features
- facial animation
- audio visual
- low level features
- image collections
- video content
- video database
- video retrieval
- video data
- content based retrieval
- visual appearance
- compressed domain
- video signals
- web images
- video clips
- keywords
- semantic gap
- speech signal
- video streams
- multimedia databases
- global features
- bag of features
- speech recognition
- image features
- feature extraction