Visual Causal Scene Refinement for Video Question Answering.
Yushen WeiYang LiuHong YanGuanbin LiLiang LinPublished in: CoRR (2023)
Keyphrases
- question answering
- visual data
- video sequences
- visual information
- information retrieval
- natural language
- video data
- question classification
- cross language
- information extraction
- natural language processing
- qa clef
- question answering systems
- passage retrieval
- video content
- video search
- named entities
- audio visual
- low level
- syntactic information
- news video
- video database
- open domain question answering
- relation extraction
- machine learning
- video retrieval
- video frames
- bayesian networks
- visual features
- image sequences
- speech transcripts
- natural language questions
- qa systems
- semantic roles
- search engine
- expert systems
- answering questions
- answer validation
- video shots
- textual entailment recognition
- co occurrence