Combining text and audio-visual features in video indexing.
Shih-Fu ChangR. ManmathaTat-Seng ChuaPublished in: ICASSP (5) (2005)
Keyphrases
- visual features
- video indexing
- visual information
- late fusion
- video segments
- low level features
- video shots
- keywords
- news video
- visual data
- visual content
- audio features
- video retrieval
- key frames
- image classification
- image search
- image annotation
- low level
- image retrieval
- visual and textual features
- video database
- video data
- audio visual
- semantic concepts
- multimedia content
- multimedia
- video surveillance
- video analysis
- image collections
- information retrieval
- human actions
- text documents
- color histogram
- semantic information
- text mining
- multiscale
- bag of words
- image representation
- multi modal
- image sequences