Dynamic self-attention with vision synchronization networks for video question answering.
Yun LiuXiaoming ZhangFeiran HuangShixun ShenPeng TianLang LiZhoujun LiPublished in: Pattern Recognit. (2022)
Keyphrases
- question answering
- information retrieval
- question classification
- natural language processing
- natural language
- passage retrieval
- multimedia
- question answering systems
- sentence retrieval
- natural language questions
- video data
- information extraction
- qa clef
- answering questions
- relation extraction
- video sequences
- answer extraction
- cross language
- named entities
- answer validation
- open domain question answering
- syntactic information
- semantic roles
- video frames
- textual entailment recognition
- artificial intelligence
- video content
- multi modal