GA-DAN: Geometry-Aware Domain Adaptation Network for Scene Text Detection and Recognition.
Fangneng ZhanChuhui XueShijian LuPublished in: CoRR (2019)
Keyphrases
- domain adaptation
- text detection
- urban scenes
- object recognition
- outdoor scenes
- cross domain
- three dimensional
- multiple sources
- text information
- video sequences
- semi supervised
- d scene
- feature extraction
- transfer learning
- geometric constraints
- target domain
- scene understanding
- labeled data
- complex scenes
- action recognition
- unlabeled data
- semi supervised learning
- machine learning
- single image
- text categorization
- complex background
- training data
- image based rendering
- image sequences
- feature selection
- computer vision