Leveraging multi-modal fusion for graph-based image annotation.
S. Hamid AmiriMansour JamzadPublished in: J. Vis. Commun. Image Represent. (2018)
Keyphrases
- image annotation
- multi modal fusion
- automatic image annotation
- image understanding
- image annotation and retrieval
- multi modal
- visual features
- multi label
- image content
- automatic annotation
- image retrieval
- web images
- low level features
- multi label classification
- web image annotation
- facial features
- semi supervised
- semantic concepts
- image collections
- annotated images
- multi label image annotation
- object detection
- multiscale
- training data
- visual information
- unlabeled data
- co occurrence