LiVLR: A Lightweight Visual-Linguistic Reasoning Framework for Video Question Answering.
Jingjing JiangZiyi LiuNanning ZhengPublished in: IEEE Trans. Multim. (2023)
Keyphrases
- lightweight
- question answering
- natural language processing
- information retrieval
- natural language
- information extraction
- question classification
- video sequences
- answering questions
- video data
- named entities
- answer validation
- qa clef
- evaluation methodology
- cross language
- visual information
- knowledge representation
- wireless sensor networks
- expert systems
- multimedia
- knowledge base
- search engine