Equivariant and Invariant Grounding for Video Question Answering.
Yicong LiXiang WangJunbin XiaoTat-Seng ChuaPublished in: CoRR (2022)
Keyphrases
- question answering
- information retrieval
- video sequences
- information extraction
- natural language processing
- video data
- video frames
- qa clef
- question classification
- cross language
- multimedia
- named entities
- passage retrieval
- natural language
- video content
- natural language questions
- syntactic information
- answer validation
- candidate answers
- question answering systems
- key frames
- test collection
- answering questions
- co occurrence
- artificial intelligence