Cross-Modal Feature Distribution Calibration for Few-Shot Visual Question Answering.
Jing ZhangXiaoqiang LiuMingzhe ChenZhe WangPublished in: AAAI (2024)
Keyphrases
- question answering
- cross modal
- multi modal
- multimedia retrieval
- information retrieval
- natural language
- information extraction
- multimedia databases
- visual similarity
- visual features
- natural language processing
- visual data
- image retrieval
- visual information
- feature vectors
- feature space
- image classification
- video sequences
- knowledge base
- machine learning