A Fusion Encoder with Multi-Task Guidance for Cross-Modal Text-Image Retrieval in Remote Sensing.
Xiong ZhangWeipeng LiXu WangLuyao WangFuzhong ZhengLong WangHaisu ZhangPublished in: Remote. Sens. (2023)
Keyphrases
- remote sensing
- cross modal
- multi task
- image retrieval
- text retrieval
- multi modal
- multimedia retrieval
- learning tasks
- image processing
- high resolution
- multi class
- image analysis
- visual features
- transfer learning
- text mining
- learning problems
- feature selection
- image content
- visual similarity
- information retrieval
- low level features
- visual content
- content based retrieval
- automatic image annotation
- unsupervised learning
- feature space
- web images
- keywords
- image representation
- data points
- pattern recognition
- data mining