Open-Ended Visual Question Answering by Multi-Modal Domain Adaptation.
Yiming XuLin ChenZhongwei ChengLixin DuanJiebo LuoPublished in: CoRR (2019)
Keyphrases
- multi modal
- question answering
- open ended
- domain adaptation
- video search
- cross domain
- natural language processing
- semi supervised
- named entities
- information retrieval
- natural language
- learning outcomes
- information extraction
- labeled data
- transfer learning
- visual information
- high dimensional
- unlabeled data
- semi supervised learning
- low level
- audio visual
- sentiment classification
- visual features
- information retrieval systems
- document classification
- supervised learning
- machine translation
- visual data
- training data
- artificial intelligence