Show, Interpret and Tell: Entity-aware Contextualised Image Captioning in Wikipedia.
Khanh NguyenAli Furkan BitenAndrés MaflaLluís GómezDimosthenis KaratzasPublished in: CoRR (2022)
Keyphrases
- image content
- input image
- image retrieval
- single image
- image data
- image features
- multiscale
- image analysis
- image representation
- image segmentation
- image pixels
- edge detection
- image classification
- feature points
- spatial information
- low level
- segmentation method
- image regions
- knowledge base
- lighting conditions
- named entity disambiguation
- digital images
- entity ranking
- grey level
- web images
- pixel values
- test images
- multiresolution
- image matching
- hough transform
- high resolution
- image database