Cascade transformers with dynamic attention for video question answering.
Yimin JiangTingfei YanMingze YaoHuibing WangWenzhe LiuPublished in: Comput. Vis. Image Underst. (2024)
Keyphrases
- question answering
- syntactic information
- named entities
- natural language processing
- question classification
- information retrieval
- qa clef
- natural language
- video sequences
- passage retrieval
- relation extraction
- question answering systems
- cross language
- sentence retrieval
- natural language questions
- video frames
- open domain question answering
- semantic roles
- candidate answers
- information extraction
- artificial intelligence
- dependency parsing
- probabilistic model
- expert systems
- multimedia
- speech transcripts