GA-DAN: Geometry-Aware Domain Adaptation Network for Scene Text Detection and Recognition.
Fangneng ZhanChuhui XueShijian LuPublished in: ICCV (2019)
Keyphrases
- domain adaptation
- text detection
- urban scenes
- object recognition
- outdoor scenes
- three dimensional
- cross domain
- scene understanding
- labeled data
- target domain
- d scene
- geometric constraints
- transfer learning
- video analysis
- semi supervised
- video sequences
- multiple sources
- semi supervised learning
- input image
- active learning
- text lines
- text information
- image sequences
- connected components
- image matching
- action recognition
- viewpoint
- urban environments
- feature extraction
- image based rendering
- learning algorithm