Multimodal Dual Attention Memory for Video Story Question Answering.
Kyung-Min KimSeong-Ho ChoiJin-Hwa KimByoung-Tak ZhangPublished in: ECCV (15) (2018)
Keyphrases
- question answering
- multimedia
- video data
- video sequences
- natural language processing
- natural language
- passage retrieval
- question classification
- information extraction
- qa clef
- named entities
- information retrieval
- question answering systems
- syntactic information
- relation extraction
- natural language questions
- open domain question answering
- semantic roles
- video content
- multi modal
- answer validation
- video search
- video retrieval
- sentence retrieval
- knowledge representation