Coding video sequences of visual features.
Luca BaroffioMatteo CesanaAlessandro RedondiStefano TubaroMarco TagliasacchiPublished in: ICIP (2013)
Keyphrases
- visual features
- video sequences
- video shots
- human actions
- image classification
- visual information
- key frames
- visual data
- visual content
- image retrieval
- low level features
- image search
- keywords
- low level
- visual appearance
- semantic gap
- video objects
- image annotation
- motion estimation
- image collections
- semantic concepts
- video data
- bag of features
- video content
- web images
- acoustic features
- visual similarity
- video frames
- bridge the semantic gap
- visual patterns
- global features
- video database
- human motion
- image representation
- image database