Cross-Modal Self-Attention with Multi-Task Pre-Training for Medical Visual Question Answering.
Haifan GongGuanqi ChenSishuo LiuYizhou YuGuanbin LiPublished in: CoRR (2021)
Keyphrases
- question answering
- cross modal
- multi task
- multi modal
- learning tasks
- multi class
- natural language
- visual data
- feature selection
- information extraction
- natural language processing
- information retrieval
- transfer learning
- supervised learning
- image retrieval
- training set
- text mining
- training examples
- visual similarity
- learning process
- image classification
- pairwise
- object recognition
- learning algorithm
- data sets