Looking from a Higher-Level Perspective: Attention and Recognition Enhanced Multi-scale Scene Text Segmentation.
Yujin RenJiaxin ZhangBangdong ChenXiaoyi ZhangLianwen JinPublished in: ACCV (7) (2022)
Keyphrases
- text segmentation
- higher level
- multiscale
- character recognition
- object recognition
- visual attention
- low level
- video sequences
- high level
- sentence level
- document analysis
- image segmentation
- text lines
- dynamic scenes
- human activities
- information retrieval
- moving objects
- image sequences
- scale space
- multiple objects
- complex scenes
- document set
- image processing
- search engine