Search Results - "Shao, Yunxue"

A data efficient transformer based on Swin Transformer by Yao, Dazhi, Shao, Yunxue

“…Almost all Vision Transformer-based models need to pre-train on the massive datasets and costly computation. Suppose researchers do not have enough data to…”
Get full text

A hierarchical and data-efficient network based on patch-based representation by Yao, Dazhi, Shao, Yunxue

“…With the rise of Transformers in computer vision, more and more people believe Transformer-based models would serve as a standard in various vision tasks…”
Get full text

Nonlinear discriminant analysis based on vanishing component analysis by Yunxue Shao, Gao, Guanglai, Wang, Chunheng

“…Most kernel-based nonlinear discriminant analysis methods need to compute the kernel distance between test samples and all of the training samples, but this…”
Get full text

Fast self-generation voting for handwritten Chinese character recognition by Shao, Yunxue, Wang, Chunheng, Xiao, Baihua

“…In this paper, a fast self-generation voting method is proposed for further improving the performance in handwritten Chinese character recognition. In this…”
Get full text

Visual word density-based nonlinear shape normalization method for handwritten Chinese character recognition by Shao, Yunxue, Wang, Chunheng, Xiao, Baihua

“…In handwritten Chinese character recognition, the performance of a system is largely dependent on the character normalization method. In this paper, a visual…”
Get full text

MURA-objects: a radioactive bone imaging lesion detection dataset by Shao, Yunxue, Wang, Xin

“…The computer-aided diagnosis technology needs to determine whether the bone image is abnormal and needs to locate the location of the lesions accurately…”
Get full text

Soft-signed sparse coding for ground-based cloud classification by Shuang Liu, Chunheng Wang, Baihua Xiao, Zhong Zhang, Yunxue Shao

“…Traditional sparse coding has been successfully applied in texture and image classification in the past years. Yet such kind of method neglects the influence…”
Get full text

Teaching machines to write like humans using L-attributed grammar by Shao, Yunxue, Liu, Cheng-Lin

“…Reading and writing are easy for humans. The automatic reading of handwritten characters has been studied for several decades. Machine learning algorithms for…”
Get full text

Supervised Feature Learning via Within-Class Reconstruction by Yunxue Shao, Jiantao Zhou, Guanglai Gao

“…Feature representation of data is a key issue for recognition related tasks. Inspired by the creative ability of human beings, in this paper we propose a novel…”
Get full text

A Connection Reduced Network for Similar Handwritten Chinese Character Discrimination by Yunxue Shao, Guanglai Gao, Chunheng Wang

“…One difficulty in handwritten Chinese character recognition (HCCR) is due to the large number of similar characters. In this study, we propose a connection…”
Get full text

A character image restoration method for unconstrained handwritten Chinese character recognition by Shao, Yunxue, Wang, Chunheng, Xiao, Baihua

“…Despite the success of methods on constrained handwriting databases, recognition of unconstrained handwritten Chinese characters remains a big challenge. One…”
Get full text

Ground-based cloud classification using multiple random projections by Shuang Liu, Chunheng Wang, Baihua Xiao, Zhong Zhang, Yunxue Shao

“…Ground-based cloud classification plays an essential role in meteorological research and has received great concern in recent years. In this paper, a novel…”
Get full text

Illumination-invariant completed LTP descriptor for cloud classification by Shuang Liu, Chunheng Wang, Baihua Xiao, Zhong Zhang, Yunxue Shao

“…Cloud classification plays an essential role in a large number of applications. However, this issue is particularly challenging due to the extreme appearance…”
Get full text

Multiple Instance Learning Based Method for Similar Handwritten Chinese Characters Discrimination by Yunxue Shao, Chunheng Wang, Baihua Xiao, Rongguo Zhang, Yang Zhang

“…This paper proposes a Multiple Instance Learning based method for similar handwritten Chinese characters discrimination. The similar handwritten Chinese…”
Get full text

Modified Two-Class LDA Based Compound Distance for Similar Handwritten Chinese Characters Discrimination by Yunxue Shao, Chunheng Wang, Baihua Xiao, Rongguo Zhang, Linbo Zhang

“…This paper proposes a modified two-class LDA based compound distance for similar handwritten Chinese characters discrimination. First the definition of the…”
Get full text

An efficient strategy for features combination by Linbo Zhang, Baihua Xiao, Chunheng Wang, Gang Cheng, Yunxue Shao

“…An important consideration in designing of visual object classification systems is the representation of images. In the past decades, significant improvement…”
Get full text

Scene Text Recognition Based on Deep Learning: A Brief Survey by Chen, Yuxin, Shao, Yunxue

“…Scene text recognition is a universal text recognition technology, which has become a research hotspot in computer field in recent years. Compared with the…”
Get full text