Visual and semantic context modeling for scene-centric image annotation.
Mohsen ZandShyamala DoraisamyAlfian Abdul HalinMas Rina MustaffaPublished in: Multim. Tools Appl. (2017)
Keyphrases
- image annotation
- context modeling
- cross modal
- visual similarity
- visual features
- semantic concepts
- multi modal
- automatic image annotation
- visual concepts
- bag of features
- visual data
- low level features
- web images
- image retrieval
- image search
- scene classification
- semantic content
- image understanding
- context awareness
- semantic gap
- image content
- visual content
- image collections
- visual information
- multi label
- image classification
- semantic similarity
- video sequences
- low level
- image sequences
- computer vision
- object recognition
- high level
- image regions
- semantic information
- object categories
- image representation
- context aware
- information retrieval
- image analysis
- natural language
- keywords
- feature extraction