SemStyle: Learning to Generate Stylised Image Captions using Unaligned Text.
Alexander Patrick MathewsLexing XieXuming HePublished in: CoRR (2018)
Keyphrases
- single image
- image data
- input image
- multiscale
- image segmentation
- image content
- image retrieval
- image features
- information retrieval
- image analysis
- learning process
- supervised learning
- feature points
- learning algorithm
- spatial information
- image regions
- reinforcement learning
- face recognition
- image classification
- visual features
- high resolution
- binary images
- similarity measure
- textual information
- linear predictors