Enhancing scene-text visual question answering with relational reasoning, attention and dynamic vocabulary integration.
Mayank AgrawalAnand Singh JalalHimanshu SharmaPublished in: Comput. Intell. (2024)
Keyphrases
- question answering
- information retrieval
- natural language
- answering questions
- information extraction
- natural language processing
- named entities
- question answering systems
- visual attention
- visual information
- visual features
- knowledge base
- knowledge representation
- relational databases
- text mining
- video search
- xml documents