Visual Causal Scene Refinement for Video Question Answering.
Yushen WeiYang LiuHong YanGuanbin LiLiang LinPublished in: ACM Multimedia (2023)
Keyphrases
- question answering
- visual data
- video sequences
- visual information
- video data
- information retrieval
- named entities
- question classification
- natural language processing
- video content
- natural language
- information extraction
- visual features
- qa clef
- video search
- passage retrieval
- relation extraction
- natural language questions
- question answering systems
- low level
- multimedia
- syntactic information
- audio visual
- open domain question answering
- cross language
- image sequences
- multimedia data
- video retrieval
- machine learning
- bayesian networks
- video frames
- key frames
- video database
- visual content
- news video
- video shots
- semantic roles
- multi modal
- knowledge representation
- candidate answers
- automatically generated
- data mining