Open-Ended Multi-Modal Relational Reasoning for Video Question Answering.
Haozheng LuoRuiyang QinChenwei XuGuo YeZening LuoPublished in: RO-MAN (2023)
Keyphrases
- multi modal
- question answering
- open ended
- video search
- semantic concepts
- answering questions
- video data
- information retrieval
- qa clef
- question classification
- multiple modalities
- multimedia
- natural language processing
- natural language
- audio visual
- passage retrieval
- video streams
- video sequences
- learning outcomes
- relational databases
- information extraction
- video content
- video frames
- video analysis
- high dimensional
- question answering systems
- natural language questions
- video retrieval
- knowledge base
- knowledge representation
- video database
- multimedia data
- data model
- syntactic information
- learning experience
- answer extraction
- learning environment