Asymmetric cross-modal attention network with multimodal augmented mixup for medical visual question answering.
Yong LiQihao YangFu Lee WangLap-Kei LeeYingying QuTianyong HaoPublished in: Artif. Intell. Medicine (2023)
Keyphrases
- cross modal
- question answering
- multi modal
- natural language processing
- information extraction
- multimedia retrieval
- visual data
- information retrieval
- image retrieval
- named entities
- visual similarity
- visual recognition
- natural language
- multimedia data
- multimedia databases
- audio visual
- image search
- visual information
- high dimensional