Cross-Modal Self-Attention with Multi-Task Pre-Training for Medical Visual Question Answering.
Haifan GongGuanqi ChenSishuo LiuYizhou YuGuanbin LiPublished in: ICMR (2021)
Keyphrases
- question answering
- cross modal
- multi task
- multi modal
- learning tasks
- natural language processing
- multi class
- information retrieval
- transfer learning
- visual data
- feature selection
- information extraction
- image retrieval
- supervised learning
- multimedia databases
- visual similarity
- training set
- natural language
- training data
- multimedia
- probabilistic model
- pairwise