most citedToward high-performance online HCCR: a CNN approach with DropDistortion, path signature and spatial stochastic max-pooling

53 citations · 81 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CV20175 cited

Online Signature Verification using Recurrent Neural Network and Length-normalized Path Signature

Songxuan Lai, Lianwen Jin, Weixin Yang

Inspired by the great success of recurrent neural networks (RNNs) in sequential modeling, we introduce a novel RNN system to improve the performance of online signature verificatio…

cs.CV20171 cited

Building Fast and Compact Convolutional Neural Networks for Offline Handwritten Chinese Character Recognition

Xuefeng Xiao, Lianwen Jin, Yafeng Yang +3

Like other problems in computer vision, offline handwritten Chinese character recognition (HCCR) has achieved impressive results using convolutional neural network (CNN)-based meth…

cs.CV201753 cited

Toward high-performance online HCCR: a CNN approach with DropDistortion, path signature and spatial stochastic max-pooling

Songxuan Lai, Lianwen Jin, Weixin Yang

This paper presents an investigation of several techniques that increase the accuracy of online handwritten Chinese character recognition (HCCR). We propose a new training strategy…

cs.CV20159 cited

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

Weixin Yang, Lianwen Jin, Zecheng Xie +1

Deep convolutional neural networks (DCNNs) have achieved great success in various computer vision and pattern recognition applications, including those for handwritten Chinese char…

cs.CV20154 cited

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

Weixin Yang, Lianwen Jin, Dacheng Tao +2

Inspired by the theory of Leitners learning box from the field of psychology, we propose DropSample, a new method for training deep convolutional neural networks (DCNNs), and apply…

cs.CV20159 cited

Character-level Chinese Writer Identification using Path Signature Feature, DropStroke and Deep CNN

Weixin Yang, Lianwen Jin, Manfei Liu

Most existing online writer-identification systems require that the text content is supplied in advance and rely on separately designed features and classifiers. The identification…