Authors: Yingying Jiang, Xiaobing Wang, Xiangyu Zhu, Shuli Yang, Wei Li, Zhenbo Luo
Description: Samsung R&D Institute China - Beijing. Machine Learning Lab. Our methods is CNN based. The paper is in preparation.
Description: CNN based model, but not based on Faster-RCNN.
Authors: Jianqi Ma, Weiyuan Shao, Hao Ye, Li Wang, Hong Wang, Yingbin Zheng, Xiangyang Xue
Description: Arbitrary-Oriented Scene Text Detection via Rotation Proposals. arXiv:1703.01086
Authors: Frank Jiang; Zhihui Hao; Xin-Ran Liu
Description: Amap Vision Lab, AutoNavi, Alibaba Group. Deep scene text detection with a hybrid of segmentation and detection. This version is trained with a consistency loss.
Authors: Hefei OCR Team of Tencent Youtu
Description: Based on Faster RCNN model with recurrent layers, and the paper is in preparation.
Authors: wei wu, junjie yan
Description: A combination of FCN and RPN.