Fine-grained Image-text Matching by Cross-modal Hard Aligning Network.
Zhengxin PanFangyu WuBailing ZhangPublished in: CVPR (2023)
Keyphrases
- fine grained
- cross modal
- coarse grained
- image retrieval
- image matching
- image features
- image data
- keypoints
- visual similarity
- multi modal
- image set
- image segmentation
- web images
- access control
- image classification
- low level
- image content
- visual data
- image collections
- image representation
- multimedia retrieval
- scene classification
- perceptual information
- information retrieval
- visual recognition
- text retrieval
- image regions
- semantic information
- text mining
- high level
- search engine