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