Dynamic Fusion With Intra- and Inter-Modality Attention Flow for Visual Question Answering.
Peng GaoZhengkai JiangHaoxuan YouPan LuSteven C. H. HoiXiaogang WangHongsheng LiPublished in: CVPR (2019)
Keyphrases
- question answering
- information extraction
- question classification
- natural language processing
- information retrieval
- cross language
- natural language
- sentence retrieval
- named entities
- visual information
- natural language questions
- multi modal
- question answering systems
- syntactic information
- qa clef
- passage retrieval
- semantic roles
- low level
- textual entailment recognition
- relation extraction
- visual features
- artificial intelligence