K-armed Bandit based Multi-Modal Network Architecture Search for Visual Question Answering.
Yiyi ZhouRongrong JiXiaoshuai SunGen LuoXiaopeng HongJinsong SuXinghao DingLing ShaoPublished in: ACM Multimedia (2020)
Keyphrases
- multi modal
- question answering
- network architecture
- video search
- cross modal
- neural network
- information extraction
- question classification
- information retrieval
- natural language processing
- answering questions
- multi modality
- qa clef
- cross language
- passage retrieval
- natural language
- question answering systems
- neural network model
- natural language questions
- high dimensional
- candidate answers
- image annotation
- semantic concepts
- low level
- audio visual
- syntactic information
- single modality
- answer validation
- visual features
- information access
- qa systems
- artificial intelligence