Multi-modal Concept Alignment Pre-training for Generative Medical Visual Question Answering.
Quan YanJunwen DuanJianxin WangPublished in: ACL (Findings) (2024)
Keyphrases
- multi modal
- question answering
- cross modal
- semantic concepts
- passage retrieval
- video search
- information retrieval
- audio visual
- natural language processing
- information extraction
- visual features
- question classification
- natural language
- cross language
- syntactic information
- question answering systems
- single modality
- image annotation
- training set
- visual information
- qa clef
- natural language questions
- high dimensional
- qa systems
- semantic roles
- multimedia