A Comparison of Pre-trained Vision-and-Language Models for Multimodal Representation Learning across Medical Images and Reports.
Yikuan LiHanyin WangYuan LuoPublished in: CoRR (2020)
Keyphrases
- medical images
- language model
- probabilistic model
- pre trained
- learning algorithm
- learning process
- language modeling
- medical imaging
- anatomical structures
- n gram
- test collection
- video sequences
- multi modal
- query expansion
- multimodal medical images
- language models for information retrieval
- document retrieval
- supervised learning
- active learning
- prior knowledge
- training data
- computer vision