More Than Just Attention: Improving Cross-Modal Attentions with Contrastive Constraints for Image-Text Matching.
Yuxiao ChenJianbo YuanLong ZhaoTianlang ChenRui LuoLarry DavisDimitris N. MetaxasPublished in: WACV (2023)
Keyphrases
- cross modal
- image retrieval
- image matching
- image data
- input image
- image features
- image content
- image segmentation
- visual similarity
- keypoints
- visual data
- image set
- image representation
- web images
- multiscale
- image collections
- information retrieval
- multiple modalities
- image regions
- low level
- multi modal
- test images
- semantic similarity
- visual features
- feature space
- metadata