Focal and Composed Vision-semantic Modeling for Visual Question Answering.
Yudong HanYangyang GuoJianhua YinMeng LiuYupeng HuLiqiang NiePublished in: ACM Multimedia (2021)
Keyphrases
- question answering
- semantic modeling
- information retrieval
- information extraction
- natural language
- question classification
- question answering systems
- natural language processing
- cross language
- passage retrieval
- qa clef
- visual features
- syntactic information
- artificial intelligence
- natural language questions
- qa systems
- knowledge representation and reasoning
- visual information
- candidate answers
- open domain question answering
- semantic roles
- data exchange
- high level