Show, Interpret and Tell: Entity-Aware Contextualised Image Captioning in Wikipedia.
Khanh NguyenAli Furkan BitenAndrés MaflaLluís GómezDimosthenis KaratzasPublished in: AAAI (2023)
Keyphrases
- input image
- image data
- single image
- image features
- image retrieval
- image content
- high resolution
- multiscale
- image segmentation
- image analysis
- grey level
- image pixels
- image regions
- lighting conditions
- segmentation method
- image matching
- template matching
- image representation
- hough transform
- edge detection
- image structure
- image classification
- image collections
- entity ranking
- vector field
- wikipedia articles
- computer vision
- named entities
- spatial information
- keypoints
- natural images
- feature points
- digital images
- object recognition
- image sequences
- knowledge base