Visual question answering based on local-scene-aware referring expression generation.
Jungjun KimDong-Gyu LeeJialin WuHonggyu JungSeong-Whan LeePublished in: Neural Networks (2021)
Keyphrases
- question answering
- natural language
- information extraction
- visual data
- named entities
- information retrieval
- visual information
- natural language processing
- passage retrieval
- question classification
- qa clef
- video sequences
- cross language
- relation extraction
- semantic roles
- visual features
- sentence retrieval
- answer validation
- syntactic information
- natural language questions
- open domain question answering
- question answering systems
- answer extraction
- machine learning
- structured data