Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Zecheng Xie

Aggregation Cross-Entropy for Sequence Recognition


Apr 18, 2019
Zecheng Xie, Yaoxiong Huang, Yuanzhi Zhu, Lianwen Jin, Yuliang Liu, Lele Xie

* 10 pages, 6 figures, Accepted by CVPR2019 

  Access Paper or Ask Questions

Tightness-aware Evaluation Protocol for Scene Text Detection


Mar 27, 2019
Yuliang Liu, Lianwen Jin, Zecheng Xie, Canjie Luo, Shuaitao Zhang, Lele Xie

* Accepted to appear in CVPR 2019 

  Access Paper or Ask Questions

DeRPN: Taking a further step toward more general object detection


Nov 16, 2018
Lele Xie, Yuliang Liu, Lianwen Jin, Zecheng Xie

* 8pages, 4 figures, 6 tables, accepted to appear in AAAI 2019 

  Access Paper or Ask Questions

Learning Spatial-Semantic Context with Fully Convolutional Recurrent Network for Online Handwritten Chinese Text Recognition


May 25, 2017
Zecheng Xie, Zenghui Sun, Lianwen Jin, Hao Ni, Terry Lyons

* 14 pages, 9 figures 

  Access Paper or Ask Questions

Fully Convolutional Recurrent Network for Handwritten Chinese Text Recognition


Apr 18, 2016
Zecheng Xie, Zenghui Sun, Lianwen Jin, Ziyong Feng, Shuye Zhang

* 6 pages, 3 figures, 5 tables 

  Access Paper or Ask Questions

Improved Deep Convolutional Neural Network For Online Handwritten Chinese Character Recognition using Domain-Specific Knowledge


May 28, 2015
Weixin Yang, Lianwen Jin, Zecheng Xie, Ziyong Feng

* 5 pages, 4 figures, 3 tables. Accepted to appear at ICDAR 2015 

  Access Paper or Ask Questions

DropSample: A New Training Method to Enhance Deep Convolutional Neural Networks for Large-Scale Unconstrained Handwritten Chinese Character Recognition


May 20, 2015
Weixin Yang, Lianwen Jin, Dacheng Tao, Zecheng Xie, Ziyong Feng

* 18 pages, 8 figures, 5 tables 

  Access Paper or Ask Questions

High Performance Offline Handwritten Chinese Character Recognition Using GoogLeNet and Directional Feature Maps


May 19, 2015
Zhuoyao Zhong, Lianwen Jin, Zecheng Xie

* 5 pages, 4 figures, 2 tables. Manuscript is accepted to appear in ICDAR 2015 

  Access Paper or Ask Questions