Towards Reasoning Ability in Scene Text Visual Question Answering.
Qingqing WangLiqiang XiaoYue LuYaohui JinHao HePublished in: ACM Multimedia (2021)
Keyphrases
- image sequences
- question answering
- answering questions
- information retrieval
- named entities
- information extraction
- qa clef
- natural language processing
- visual information
- knowledge representation
- natural language
- video sequences
- natural language questions
- visual features
- question answering systems
- text detection
- answer extraction
- scene text
- knowledge base
- multi modal
- low level
- natural scene images
- artificial intelligence