StoryDALL-E: Adapting Pretrained Text-to-Image Transformers for Story Continuation.
Adyasha MaharanaDarryl HannanMohit BansalPublished in: ECCV (37) (2022)
Keyphrases
- input image
- image features
- image data
- image pixels
- multiscale
- image analysis
- image classification
- image segmentation
- template matching
- image content
- single image
- feature points
- image representation
- segmentation method
- edge detection
- image regions
- image matching
- high resolution
- computer vision
- text mining
- information extraction
- hough transform
- spatial information
- low level
- image collections
- pixel values
- face recognition
- web images
- text information
- textual and visual information