Knowledge-Based Video Question Answering with Unsupervised Scene Descriptions.
Noa GarciaYuta NakashimaPublished in: ECCV (18) (2020)
Keyphrases
- question answering
- video sequences
- question classification
- information retrieval
- video data
- information extraction
- video frames
- natural language processing
- question answering systems
- cross language
- visual data
- natural language
- natural language questions
- named entities
- passage retrieval
- expert systems
- video content
- qa clef
- syntactic information
- high level
- sentence retrieval
- visual information
- key frames
- multimedia
- unsupervised learning
- artificial intelligence
- textual entailment recognition
- open domain question answering
- video retrieval
- relation extraction
- machine learning
- multi modal
- information retrieval systems
- knowledge representation
- answer validation