Cross-modal Contrastive Learning for Generalizable and Efficient Image-text Retrieval.
Haoyu LuYuqi HuoMingyu DingNanyi FeiZhiwu LuPublished in: Mach. Intell. Res. (2023)
Keyphrases
- text retrieval
- image retrieval
- cross modal
- image data
- learning algorithm
- learning process
- image content
- image features
- perceptual information
- multimedia retrieval
- low level
- multi modal
- document collections
- image collections
- image representation
- image regions
- image classification
- visual data
- visual recognition
- feature vectors
- high dimensional
- information retrieval