So Many Heads, So Many Wits: Multimodal Graph Reasoning for Text-Based Visual Question Answering.
Wenbo ZhengLan YanFei-Yue WangPublished in: IEEE Trans. Syst. Man Cybern. Syst. (2024)
Keyphrases
- question answering
- visual features
- answering questions
- natural language processing
- information extraction
- information retrieval
- natural language
- visual information
- passage retrieval
- structured data
- question classification
- question answering systems
- answer validation
- low level
- multimedia
- named entities
- syntactic information
- cross language
- qa clef
- open domain question answering
- multi modal
- sentence retrieval
- graph structure
- qa systems
- knowledge representation
- semantic roles
- image search
- semantic information
- probabilistic model
- knowledge base