Keyword-aware Multi-modal Enhancement Attention for Video Question Answering.
Duo ChenFuwei ZhangShirou OuRuomei WangPublished in: CSAI (2021)
Keyphrases
- multi modal
- question answering
- semantic concepts
- video search
- video data
- information retrieval
- video sequences
- natural language processing
- information extraction
- keywords
- question classification
- natural language
- multiple modalities
- syntactic information
- video streams
- audio visual
- cross language
- video analysis
- multimedia
- natural language questions
- question answering systems
- passage retrieval
- video content
- video frames
- answering questions
- qa clef
- key frames
- answer validation
- image annotation
- multimedia data
- answer extraction
- keyword queries
- feature extraction
- search engine