Paired Cross-Modal Data Augmentation for Fine-Grained Image-to-Text Retrieval.
Hao WangGuosheng LinSteven C. H. HoiChunyan MiaoPublished in: CoRR (2022)
Keyphrases
- fine grained
- coarse grained
- text retrieval
- image data
- image retrieval
- access control
- multi modal
- cross modal
- information retrieval
- multimedia retrieval
- visual data
- image representation
- image classification
- image features
- text categorization
- image regions
- natural language processing
- data points
- digital libraries
- data structure