Multimodal Graph Reasoning and Fusion for Video Question Answering.
Shuai ZhangXingfu WangAmmar HawbaniLiang ZhaoSaeed Hamood AlsamhiPublished in: TrustCom (2022)
Keyphrases
- question answering
- multimedia
- answering questions
- video data
- information retrieval
- information extraction
- natural language
- natural language processing
- question classification
- syntactic information
- natural language questions
- knowledge representation
- video content
- video sequences
- question answering systems
- qa clef
- named entities
- cross language
- relation extraction
- structured data
- passage retrieval
- answer extraction
- open domain question answering
- sentence retrieval
- machine learning
- multi modal
- video search
- relational databases
- answer validation
- key frames