Video Question Answering with Iterative Video-Text Co-tokenization.
A. J. PiergiovanniKairo MortonWeicheng KuoMichael S. RyooAnelia AngelovaPublished in: ECCV (36) (2022)
Keyphrases
- question answering
- information retrieval
- video data
- video sequences
- multimedia
- named entities
- video content
- natural language
- natural language processing
- video frames
- information extraction
- passage retrieval
- cross language
- text summarization
- syntactic information
- question answering systems
- key frames
- text retrieval
- textual entailment recognition
- video retrieval
- text mining
- probabilistic model
- artificial intelligence