Deep Modular Co-Attention Networks for Visual Question Answering.
Zhou YuJun YuYuhao CuiDacheng TaoQi TianPublished in: CVPR (2019)
Keyphrases
- question answering
- question classification
- information retrieval
- information extraction
- natural language
- natural language processing
- cross language
- named entities
- visual information
- question answering systems
- passage retrieval
- semantic roles
- qa systems
- open domain question answering
- qa clef
- relation extraction
- answering questions
- low level
- syntactic information
- natural language questions
- document collections
- visual features
- knowledge representation