3 papers
cs.CV2016
Shape Recognition by Bag of Skeleton-associated Contour Parts
Wei Shen, Yuan Jiang, Wenjing Gao +2
Contour and skeleton are two complementary representations for shape recognition. However combining them in a principal way is nontrivial, as they are generally abstracted by diffe…
cs.CV2016
Multi-Oriented Text Detection with Fully Convolutional Networks
Zheng Zhang, Chengquan Zhang, Wei Shen +3
In this paper, we propose a novel approach for text detec- tion in natural images. Both local and global cues are taken into account for localizing text lines in a coarse-to-fine p…
cs.CV2016
Object Skeleton Extraction in Natural Images by Fusing Scale-associated Deep Side Outputs
Wei Shen, Kai Zhao, Yuan Jiang +3
Object skeleton is a useful cue for object detection, complementary to the object contour, as it provides a structural representation to describe the relationship among object part…