Transform and Tell: Entity-Aware News Image Captioning.
Alasdair TranAlexander Patrick MathewsLexing XiePublished in: CVPR (2020)
Keyphrases
- multiscale
- input image
- image data
- image content
- single image
- image segmentation
- image features
- image representation
- image analysis
- template matching
- image classification
- feature points
- image pixels
- keywords
- image retrieval
- image collections
- computer vision
- pixel values
- keypoints
- image structure
- image matching
- laplacian pyramid
- transform coefficients
- polar coordinates
- image set
- hough transform
- image regions
- segmentation method
- image quality
- edge detection
- face recognition
- knowledge base