Multi-scale relation reasoning for multi-modal Visual Question Answering.
Yirui WuYuntao MaShaohua WanPublished in: Signal Process. Image Commun. (2021)
Keyphrases
- multi modal
- question answering
- multiscale
- cross modal
- answering questions
- video search
- single modality
- natural language processing
- question classification
- natural language
- information retrieval
- information extraction
- knowledge representation
- qa clef
- natural language questions
- knowledge base
- cross language
- high dimensional
- audio visual
- passage retrieval
- question answering systems
- syntactic information
- visual information
- answer extraction
- candidate answers
- visual features
- answer validation
- image annotation
- multi modality
- image representation
- expert systems