Unsupervised Discovery of Multimodal Links in Multi-image, Multi-sentence Documents.
Jack HesselLillian LeeDavid MimnoPublished in: EMNLP/IJCNLP (1) (2019)
Keyphrases
- input image
- multiscale
- image data
- image segmentation
- image features
- image classification
- image analysis
- edge detection
- information retrieval
- multi modal
- image representation
- image content
- test images
- single image
- scanned documents
- image collections
- image regions
- segmentation method
- information retrieval systems
- xml documents
- similarity measure