Knowledge-Enhanced Visual Question Answering with Multi-modal Joint Guidance.
Jianfeng WangAnda ZhangHuifang DuHaofen WangWenqiang ZhangPublished in: IJCKG (2022)
Keyphrases
- multi modal
- question answering
- cross modal
- multi modality
- natural language
- question classification
- video search
- cross language
- information retrieval
- named entities
- domain knowledge
- natural language processing
- passage retrieval
- syntactic information
- knowledge base
- high dimensional
- visual features
- information extraction
- knowledge representation
- single modality
- image annotation
- low level
- audio visual
- expert systems
- high level
- question answering systems
- machine learning
- multiple modalities
- answering questions
- natural language questions