MAMF: A Multi-Level Attention-Based Multimodal Fusion Model for Medical Visual Question Answering.
Shaopei LongZhenguo YangYong LiXiaobo QianKun ZengTianyong HaoPublished in: NCAA (2) (2023)
Keyphrases
- question answering
- fusion model
- information fusion
- information retrieval
- information extraction
- question classification
- qa clef
- natural language processing
- syntactic information
- natural language
- fusion framework
- estimation algorithm
- natural language questions
- passage retrieval
- multi source
- question answering systems
- visual information
- computer vision
- visual features
- multi modal
- image registration
- fuzzy logic
- precision and recall
- fuzzy membership functions
- data fusion
- candidate answers
- answer extraction
- training set
- feature space