Coding Visual Features Extracted From Video Sequences.
Luca BaroffioMatteo CesanaAlessandro RedondiMarco TagliasacchiStefano TubaroPublished in: IEEE Trans. Image Process. (2014)
Keyphrases
- visual features
- video sequences
- video shots
- visual content
- visual information
- human actions
- image classification
- visual data
- key frames
- image retrieval
- low level
- image search
- semantic features
- image annotation
- keywords
- sample images
- semantic concepts
- image collections
- low level features
- web images
- bridge the semantic gap
- image sequences
- visual appearance
- video objects
- automatically extracted
- semantic gap
- global features
- visual similarity
- object recognition
- multi modal
- bag of features
- video data
- bag of words
- low level visual features
- image content
- visual descriptors
- visual properties
- multimedia data