Filters








3 Hits in 1.7 sec

ContourNet: Taking a Further Step toward Accurate Arbitrary-shaped Scene Text Detection [article]

Yuxin Wang, Hongtao Xie, Zhengjun Zha, Mengting Xing, Zilong Fu, Yongdong Zhang
2020 arXiv   pre-print
In this paper, we propose the ContourNet, which effectively handles these two problems taking a further step toward accurate arbitrary-shaped text detection.  ...  Scene text detection has witnessed rapid development in recent years.  ...  In this paper, we propose a novel text detector to effectively solve these two problems achieving accurate arbitrary-shaped scene text detection, which is called Con-tourNet.  ... 
arXiv:2004.04940v1 fatcat:zk4lgp6xffcf7nzlhmuumhz5wu

ContourNet: Taking a Further Step Toward Accurate Arbitrary-Shaped Scene Text Detection

Yuxin Wang, Hongtao Xie, Zheng-Jun Zha, Mengting Xing, Zilong Fu, Yongdong Zhang
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
In this paper, we propose the ContourNet, which effectively handles these two problems taking a further step toward accurate arbitrary-shaped text detection.  ...  Scene text detection has witnessed rapid development in recent years.  ...  In this paper, we propose a novel text detector to effectively solve these two problems achieving accurate arbitrary-shaped scene text detection, which is called Con-tourNet.  ... 
doi:10.1109/cvpr42600.2020.01177 dblp:conf/cvpr/WangXZXFZ20 fatcat:aztsvaoyfbeznih53nmfy7rkui

What's Wrong with the Bottom-up Methods in Arbitrary-shape Scene Text Detection [article]

Chengpei Xu, Wenjing Jia, Tingcheng Cui, Ruomei Wang, Yuan-fang Zhang, Xiangjian He
2021 arXiv   pre-print
The latest trend in the bottom-up perspective for arbitrary-shape scene text detection is to reason the links between text segments using Graph Convolutional Network (GCN).  ...  (FD) module to enhance the representation of text regions for the second step suppression.  ...  INTRODUCTION D EEP learning based arbitrary-shape scene text detection methods generally follow two streams, i.e., top-down approaches and bottom-up approaches.  ... 
arXiv:2108.01809v1 fatcat:ee256bfdkzhf5ks45b3fgvlina