Automatic caption generation for video data. Time alignment between caption and acoustic signal.
Katsuyuki WatanabeMasahide SugiyamaPublished in: MMSP (1999)
Keyphrases
- video data
- video retrieval
- acoustic signal
- video shots
- news video
- video content
- video analysis
- video streams
- video database
- video sequences
- visual features
- acoustic signals
- video frames
- multimedia
- digital video
- video camera
- video editing
- video indexing
- surveillance cameras
- visual content
- key frames
- surveillance videos
- database
- bounding box
- content based retrieval
- video browsing
- temporal structure
- video abstraction
- multimedia systems
- video dataset
- video clips
- databases
- spatio temporal
- computer vision