Multi-grained Attention with Object-level Grounding for Visual Question Answering.
Pingping HuangJianhui HuangYuqing GuoMin QiaoYong ZhuPublished in: ACL (1) (2019)
Keyphrases
- question answering
- object level
- low level
- high level
- pixel level
- information retrieval
- higher level
- information extraction
- natural language processing
- visual information
- natural language
- passage retrieval
- question answering systems
- natural language questions
- qa clef
- object class
- visual attention
- visual features
- answer extraction
- denoising
- ground truth