Image and Encoded Text Fusion for Multi-Modal Classification.
Ignazio GalloAlessandro CalefatiShah NawazMuhammad Kamran JanjuaPublished in: DICTA (2018)
Keyphrases
- multi modal
- single modality
- image classification
- multiple modalities
- multi modality
- fusing multiple
- auto annotation
- uni modal
- input image
- video search
- image retrieval
- image data
- image content
- image features
- multiscale
- high dimensional
- fusion method
- classification accuracy
- low level
- image segmentation
- audio visual
- machine learning
- feature extraction
- image regions
- segmentation method
- image representation
- feature space
- web images
- image processing
- feature vectors
- image annotation
- image collections
- image search
- feature set
- edge detection
- diffusion tensor images
- high resolution
- image analysis