Data-driven vocal folds models for the representation of both acoustic and high speed video data.
Carlo DrioliGian Luca ForestiPublished in: IJCNN (2015)
Keyphrases
- video data
- data driven
- high speed
- video analysis
- video streams
- digital video
- video camera
- temporal structure
- video sequences
- video frames
- video content
- video clips
- multimedia
- video database
- video retrieval
- video shots
- surveillance videos
- video editing
- visual data
- image representation
- spatio temporal
- motion trajectories
- video indexing
- video dataset
- real time
- surveillance cameras
- video browsing
- content based indexing
- content based access