Understanding Image and Text Simultaneously: a Dual Vision-Language Machine Comprehension Task.
Nan DingSebastian GoodmanFei ShaRadu SoricutPublished in: CoRR (2016)
Keyphrases
- input image
- image data
- image features
- multiscale
- image pixels
- single image
- image classification
- image representation
- image segmentation
- test images
- image content
- template matching
- image processing
- low level image processing
- region of interest
- high resolution
- low level
- image analysis
- textual and visual information
- information retrieval
- computational linguistics
- visual perception
- image retrieval
- edge detection
- segmentation method
- segmentation algorithm
- feature points
- vision system
- hough transform
- multiresolution
- image collections
- scheduling problem
- textual information
- human vision
- programming language
- text information
- text graphics