TCSA: A Text-Guided Cross-View Medical Semantic Alignment Framework for Adaptive Multi-view Visual Representation Learning.
Hongyang LeiHuazhen HuangBokai YangGuosheng CuiRuxin WangDan WuYe LiPublished in: ISBRA (2023)
Keyphrases
- multi view
- multi view learning
- visual representation
- multiple views
- camera calibration
- learning process
- multiple cameras
- d objects
- three dimensional
- co training
- depth map
- supervised learning
- semi supervised
- learning algorithm
- unsupervised learning
- range images
- dynamic scenes
- learning tasks
- active learning
- user interface
- viewpoint
- graph embedding
- cross view