Reasoning on the Relation: Enhancing Visual Representation for Visual Question Answering and Cross-Modal Retrieval.
Jing YuWeifeng ZhangYuhang LuZengchang QinYue HuJianlong TanQi WuPublished in: IEEE Trans. Multim. (2020)
Keyphrases
- cross modal
- question answering
- visual representation
- multi modal
- perceptual information
- multimedia retrieval
- passage retrieval
- information retrieval
- image retrieval
- visual similarity
- information extraction
- user interface
- multimedia databases
- natural language processing
- natural language
- visual data
- question answering systems
- knowledge representation
- answer extraction
- visual features
- visual information
- multimedia
- knowledge base
- language model
- image database
- low level