Multi-modal Domain Adaptation for Text Visual Question Answering Tasks.
Zhiyuan LiDongnan LiuWeidong CaiPublished in: DICTA (2023)
Keyphrases
- multi modal
- question answering
- domain adaptation
- video search
- information retrieval
- transfer learning
- information extraction
- cross domain
- natural language processing
- passage retrieval
- audio visual
- labeled data
- named entities
- text mining
- natural language
- semi supervised learning
- semi supervised
- high dimensional
- visual information
- text retrieval
- document classification
- low level
- semantic information
- text documents
- image annotation
- text data
- sentiment classification