Enhancing visual question answering with a two-way co-attention mechanism and integrated multimodal features.
Mayank AgrawalAnand Singh JalalHimanshu SharmaPublished in: Comput. Intell. (2024)
Keyphrases
- question answering
- low level
- question classification
- information retrieval
- natural language processing
- feature extraction
- attention mechanism
- information extraction
- cross language
- passage retrieval
- natural language
- qa clef
- question answering systems
- syntactic information
- artificial intelligence
- natural language questions
- semantic roles
- visual information
- feature space
- audio visual
- multi modal
- answering questions
- expert systems
- answer validation