Coding local and global binary visual features extracted from video sequences.
Luca BaroffioAntonio CancliniMatteo CesanaAlessandro RedondiMarco TagliasacchiStefano TubaroPublished in: CoRR (2015)
Keyphrases
- visual features
- video sequences
- global features
- video shots
- image classification
- visual information
- visual content
- key frames
- human actions
- sample images
- visual data
- image search
- image retrieval
- low level
- low level features
- image annotation
- image collections
- bridge the semantic gap
- keywords
- visual appearance
- video content
- image sequences
- bag of features
- web images
- motion estimation
- video data
- visual patterns
- video frames
- visual similarity
- computer vision
- hamming distance
- video database
- semantic gap
- facial expressions
- search engine