activity
20152026
most citedToward high-performance online HCCR: a CNN approach with DropDistortion, path signature and spatial stochastic max-pooling

53 citations · 92 across the 7 of their papers we have counts for

collaborators
Showing cs.CVShow all

8 papers · 1 filter

cs.CV202111 cited

Logsig-RNN: a novel network for robust and efficient skeleton-based action recognition

Shujian Liao, Terry Lyons, Weixin Yang +2

This paper contributes to the challenge of skeleton-based human action recognition in videos. The key step is to develop a generic network architecture to extract discriminative fe…

cs.CV2018

Skeleton-based Gesture Recognition Using Several Fully Connected Layers with Path Signature Features and Temporal Transformer Module

Chenyang Li, Xin Zhang, Lufan Liao +2

The skeleton based gesture recognition is gaining more popularity due to its wide possible applications. The key issues are how to extract discriminative features and how to design…

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…