Answer-checking in Context: A Multi-modal Fully Attention Network for Visual Question Answering.
Hantao HuangTao HanWei HanDeep YapCheng-Ming ChiangPublished in: ICPR (2020)
Keyphrases
- multi modal
- question answering
- question classification
- natural language questions
- question answering systems
- cross modal
- answer validation
- answering questions
- candidate answers
- qa systems
- video search
- answer extraction
- audio visual
- qa clef
- information extraction
- passage retrieval
- information retrieval
- natural language
- single modality
- question answer pairs
- cross language
- high dimensional
- multi modality
- natural language processing
- syntactic information
- contextual information
- visual information
- named entities
- semantic concepts
- context aware
- visual features
- textual entailment
- feature weighting
- semantic information
- image annotation
- visual data
- semantic roles