ViCLEVR: A Visual Reasoning Dataset and Hybrid Multimodal Fusion Model for Visual Question Answering in Vietnamese.
Khiem Vinh TranHao Phu PhanKiet Van NguyenNgan Luu-Thuy NguyenPublished in: CoRR (2023)
Keyphrases
- question answering
- visual information
- visual features
- information extraction
- natural language processing
- information retrieval
- fusion model
- syntactic information
- databases
- knowledge representation
- image classification
- data model
- relational databases
- expert systems
- passage retrieval
- question answering systems
- question classification
- answering questions