DMRFNet: Deep Multimodal Reasoning and Fusion for Visual Question Answering and explanation generation.
Weifeng ZhangJing YuWenhong ZhaoChuan RanPublished in: Inf. Fusion (2021)
Keyphrases
- question answering
- information retrieval
- information extraction
- natural language processing
- answering questions
- knowledge base
- qa clef
- natural language
- passage retrieval
- question classification
- named entities
- cross language
- question answering systems
- visual information
- syntactic information
- sentence retrieval
- visual features
- qa systems
- natural language questions
- semantic roles
- multimedia
- multiple features
- audio visual
- candidate answers
- visual data
- multi modal
- knowledge representation
- relational databases