Open-Ended Multi-Modal Relational Reason for Video Question Answering.
Haozheng LuoRuiyang QinPublished in: CoRR (2020)
Keyphrases
- multi modal
- question answering
- open ended
- video search
- semantic concepts
- passage retrieval
- learning outcomes
- audio visual
- information extraction
- video data
- question classification
- information retrieval
- natural language
- video sequences
- natural language processing
- multiple modalities
- qa clef
- natural language questions
- video analysis
- question answering systems
- data model
- relational databases
- video database
- video frames
- image annotation
- qa systems
- multimedia
- syntactic information
- video content
- key frames
- multimedia data
- high dimensional
- high level