Wei Xu

Prof. Wei Xu


Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2024
Verified
Conference Paper
Open access
PDF file
RXRongwu Xu
Rongwu Xu
BLBrian Lin
Brian Lin
SYShujian Yang
Shujian Yang
TZTianqi Zhang
Tianqi Zhang
WSWeiyan Shi
Weiyan Shi
HQHan Qiu
Han Qiu
Rongwu Xu, Brian Lin, Shujian Yang, Tianqi Zhang, Weiyan Shi, Tianwei Zhang, Zhixuan Fang, Wei Xu, Han Qiu. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

21 January 2021 in Journal of Clinical Microbiology
Verified
Journal Article
Closed access
PDF file
ZWZhongxiao Wang
Zhongxiao Wang
LZLei Zhang
Lei Zhang
MZMin Zhao
Min Zhao
YWYing Wang
Ying Wang
HBHuihui Bai
Huihui Bai
WXWei Xu
Wei Xu
Bacterial vaginosis (BV) is caused by the excessive and imbalanced growth of bacteria in vagina, affecting 30 to 50% of women. Gram staining followed by Nugent scoring based on bacterial morphotypes under the microscope is considered the gold standard for BV diagnosis; this method is often labor-intensive and time-consuming, and results vary from person to person. We developed and optimized a convolutional neural network (CNN) model and evaluated its ability to automatically identify and classify three categories of Nugent scores from microscope images.

26 April 2022 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
WXWei Xu
Wei Xu
QZQing Zhu
Qing Zhu
NQNa Qi
Na Qi
DCDongpan Chen
Dongpan Chen
As a powerful statistical signal modeling technique, sparse representation has been widely used in various image restoration (IR) applications. The sparsity-based methods have achieved leading performance in the past few decades. However, in recent years it has been surpassed by other methods, especially the recent deep learning based methods. In this paper, we address the question that whether sparse representation can be competitive again. The way we answer this question is to redesign it with a deep architecture. To be specific, we propose an end-to-end deep architecture that follows the process of the sparse representation based IR. In particular, we learn a sparse convolutional dictionary to replace the traditional dictionary, and a convolutional neural network (CNN) denoising prior to replace the image prior. Through end-to-end training, the parameters in convolutional dictionary and CNN denoiser can be jointly optimized. Experimental results on several representative IR tasks, including image denoising, deblurring and super-resolution, demonstrate that the proposed deep network can achieve superior performance against state-of-the-art model-based and learning-based methods.

1 January 2021
Verified
Conference Paper
Open access
PDF file
JKJoongwon Kim
Joongwon Kim
MMMounica Maddela
Mounica Maddela
RKReno Kriz
Reno Kriz
WXWei Xu
Wei Xu
CCChris Callison-Burch
Chris Callison-Burch
Joongwon Kim, Mounica Maddela, Reno Kriz, Wei Xu, Chris Callison-Burch. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. 2021.

26 February 2024 in Journal of Information Security and Applications
Verified
Journal Article
Closed access
JTJunwei Tang
Junwei Tang
WXWei Xu
Wei Xu
TPTao Peng
Tao Peng
SZSijie Zhou
Sijie Zhou
QPQiaosen Pi
Qiaosen Pi
XHXinrong Hu
Xinrong Hu

1 January 2025
Verified
Conference Paper
Open access
PDF file
RXRongwu Xu
Rongwu Xu
XLXiaojian Li
Xiaojian Li
SCShuo Chen
Shuo Chen
WXWei Xu
Wei Xu
Rongwu Xu, Xiaojian Li, Shuo Chen, Wei Xu. Findings of the Association for Computational Linguistics: ACL 2025. 2025.