Invariant Grounding for Video Question Answering.
Yicong LiXiang WangJunbin XiaoWei JiTat-Seng ChuaPublished in: CVPR (2022)
Keyphrases
- question answering
- video sequences
- natural language processing
- information extraction
- information retrieval
- multimedia
- cross language
- video data
- video content
- question classification
- video frames
- named entities
- natural language
- passage retrieval
- natural language questions
- semantic roles
- syntactic information
- qa clef
- sentence retrieval
- open domain question answering
- key frames
- knowledge representation
- qa systems
- candidate answers