Hierarchical Conditional Relation Networks for Multimodal Video Question Answering.
Thao Minh LeVuong LeSvetha VenkateshTruyen TranPublished in: CoRR (2020)
Keyphrases
- question answering
- multimedia
- information extraction
- question classification
- information retrieval
- video content
- natural language processing
- named entities
- video data
- qa clef
- question answering systems
- sentence retrieval
- passage retrieval
- natural language
- natural language questions
- multi modal
- video sequences
- cross language
- open domain question answering
- relation extraction
- video frames
- syntactic information
- video retrieval
- candidate answers
- qa systems
- semantic roles
- key frames
- text categorization
- video shots
- answering questions
- artificial intelligence