CA-STD: Scene Text Detection in Arbitrary Shape Based on Conditional Attention.
Xing WuYangyang QiJun SongJunfeng YaoYanzhong WangYang LiuYuexing HanQuan QianPublished in: Inf. (2022)
Keyphrases
- text detection
- urban scenes
- object recognition
- outdoor scenes
- scene understanding
- natural scene images
- scene text
- d scene
- text information
- video analysis
- urban environments
- object detection
- connected components
- three dimensional
- video sequences
- level set
- single image
- point cloud
- structure from motion
- planar surfaces
- visual attention
- input image
- computer vision
- photorealistic
- depth map
- binary images
- range data
- image based rendering
- document images
- dynamic scenes
- scene images
- natural scenes