Multimodal Deep Learning using Images and Text for Information Graphic Classification.
Edward KimKathleen F. McCoyPublished in: ASSETS (2018)
Keyphrases
- deep learning
- image classification
- spatial information
- image regions
- keywords
- text classification
- pattern recognition
- machine learning
- multiple images
- unsupervised learning
- supervised learning
- input image
- image features
- feature vectors
- training set
- object recognition
- feature selection
- computer vision
- information extraction
- feature extraction
- semantic information
- learning algorithm
- data mining
- multiple modalities