MMCN: Multi-Modal Co-attention Network for Medical Visual Question Answering.
Ming SunQilong XuErcong WangWenjun WangLei TanXiu Yang ZhaoPublished in: CCRIS (2022)
Keyphrases
- multi modal
- question answering
- cross modal
- passage retrieval
- audio visual
- natural language processing
- question classification
- video search
- multi modality
- cross language
- natural language
- high dimensional
- information extraction
- qa clef
- information retrieval
- semantic concepts
- natural language questions
- single modality
- syntactic information
- visual features
- low level
- uni modal
- question answering systems
- bag of words
- image representation
- information retrieval systems
- artificial intelligence