Glance and Focus: Memory Prompting for Multi-Event Video Question Answering.
Ziyi BaiRuiping WangXilin ChenPublished in: NeurIPS (2023)
Keyphrases
- question answering
- question classification
- video sequences
- multimedia
- natural language
- natural language processing
- information retrieval
- question answering systems
- passage retrieval
- cross language
- information extraction
- syntactic information
- named entities
- sentence retrieval
- relation extraction
- video data
- semantic roles
- natural language questions
- qa clef
- open domain question answering
- visual data
- video retrieval
- answer extraction
- answering questions
- video frames
- answer validation
- machine learning