Advancing Video Question Answering with a Multi-modal and Multi-layer Question Enhancement Network.
Meng LiuFenglei ZhangXin LuoFan LiuYinwei WeiLiqiang NiePublished in: ACM Multimedia (2023)
Keyphrases
- multi modal
- question answering
- multi layer
- question classification
- question answering systems
- qa clef
- answer extraction
- natural language questions
- video search
- qa systems
- semantic concepts
- candidate answers
- answer validation
- natural language processing
- answering questions
- natural language
- information extraction
- passage retrieval
- neural network
- audio visual
- multimedia
- information retrieval
- video data
- neural nets
- multiple modalities
- video sequences
- high dimensional
- syntactic information
- question answer pairs
- information retrieval systems
- high level