Visual Question Answering via Combining Inferential Attention and Semantic Space Mapping.
Yun LiuXiaoming ZhangFeiran HuangZhibo ZhouZhonghua ZhaoZhoujun LiPublished in: Knowl. Based Syst. (2020)
Keyphrases
- question answering
- semantic space
- mapping function
- cross modal
- visual features
- latent semantic analysis
- co occurrence
- natural language processing
- text summarization
- information retrieval
- natural language
- information extraction
- multi modal
- named entities
- semantic concepts
- visual information
- machine learning
- semantic features
- named entity recognition
- visual data
- image classification
- multimedia