Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding.
Akira FukuiDong Huk ParkDaylen YangAnna RohrbachTrevor DarrellMarcus RohrbachPublished in: EMNLP (2016)
Keyphrases
- question answering
- natural language
- visual information
- low level
- visual features
- information retrieval
- information extraction
- cross language
- named entities
- natural language processing
- relational databases
- passage retrieval
- sentence retrieval
- data mining
- relation extraction
- question answering systems
- open domain question answering