Cross-modal Knowledge Reasoning for Knowledge-based Visual Question Answering.
Jing YuZihao ZhuYujing WangWeifeng ZhangYue HuJianlong TanPublished in: CoRR (2020)
Keyphrases
- question answering
- cross modal
- perceptual information
- multi modal
- knowledge representation
- knowledge base
- information retrieval
- information extraction
- natural language
- domain knowledge
- answering questions
- natural language processing
- expert systems
- named entities
- visual recognition
- image retrieval
- visual data
- multimedia retrieval
- visual information
- visual similarity
- low level
- video sequences
- metadata
- data mining