Image and Encoded Text Fusion for Deep Multi-Modal Clustering.
Truong-Dong DoKyungbaek KimHyuk Ro ParkHyung-Jeong YangPublished in: SMA (2020)
Keyphrases
- multi modal
- multi modality
- multiple modalities
- fusing multiple
- auto annotation
- single modality
- uni modal
- input image
- image classification
- image features
- image content
- video search
- fusion method
- image analysis
- multiscale
- image data
- image annotation
- audio visual
- web images
- low level
- high resolution
- image retrieval
- image collections
- image representation
- image segmentation
- cross modal
- edge detection
- information theoretic
- segmentation method
- high dimensional
- similarity measure
- semantic concepts
- image search
- automatic image annotation
- image fusion
- image processing