I3CL: Intra- and Inter-Instance Collaborative Learning for Arbitrary-shaped Scene Text Detection.
Jian YeJing ZhangJuhua LiuBo DuDacheng TaoPublished in: CoRR (2021)
Keyphrases
- text detection
- arbitrary shaped
- collaborative learning
- urban scenes
- outdoor scenes
- natural scene images
- object recognition
- d scene
- video analysis
- scene understanding
- video sequences
- image sequences
- vanishing points
- arbitrary shape
- single image
- connected components
- text information
- urban environments
- moving objects
- packing problem
- video database
- image regions
- aerial images
- dynamic scenes
- point cloud
- input image
- learning process
- photorealistic
- computer vision
- e learning