Encoding and Controlling Global Semantics for Long-form Video Question Answering.
Thong Thanh NguyenZhiyuan HuXiaobao WuCong-Duy T. NguyenSee-Kiong NgAnh Tuan LuuPublished in: CoRR (2024)
Keyphrases
- question answering
- natural language processing
- information retrieval
- video sequences
- natural language
- question classification
- question answering systems
- named entities
- qa clef
- cross language
- passage retrieval
- video data
- syntactic information
- information extraction
- answer validation
- answering questions
- semantic information
- multimedia
- semantic roles
- semantic representation
- probabilistic model
- keywords
- natural language questions
- artificial intelligence