FedVQA: Personalized Federated Visual Question Answering over Heterogeneous Scenes.
Mingrui LaoNan PuZhun ZhongNicu SebeMichael S. LewPublished in: ACM Multimedia (2023)
Keyphrases
- question answering
- information extraction
- information retrieval
- natural language processing
- named entities
- question classification
- natural language
- visual information
- cross language
- qa clef
- syntactic information
- question answering systems
- relation extraction
- passage retrieval
- digital libraries
- visual features
- sentence retrieval
- artificial intelligence
- semantic roles
- low level
- machine translation
- multimedia
- natural language questions
- answer validation
- open domain question answering