Cross-modality co-attention networks for visual question answering.
Dezhi HanShuli ZhouKuan-Ching LiRodrigo Fernandes de MelloPublished in: Soft Comput. (2021)
Keyphrases
- question answering
- information retrieval
- natural language processing
- information extraction
- question classification
- natural language
- syntactic information
- qa clef
- cross language
- natural language questions
- passage retrieval
- low level
- visual features
- visual information
- relation extraction
- question answering systems
- sentence retrieval
- open domain question answering
- answer extraction
- candidate answers
- visual data
- answering questions
- multi modal
- answer validation
- artificial intelligence