Generic decoding of seen and imagined objects using hierarchical visual features.
Tomoyasu HorikawaYukiyasu KamitaniPublished in: CoRR (2015)
Keyphrases
- visual features
- visual appearance
- image classification
- object models
- visual information
- visual data
- visual content
- image annotation
- image search
- low level features
- image retrieval
- keywords
- sift features
- low level
- image collections
- bridge the semantic gap
- visual attributes
- visual patterns
- global features
- semantic gap
- web images
- semantic concepts
- bag of features
- visual descriptors
- key frames
- image data
- multiscale
- higher level
- visual similarity
- multimedia data