Wenzhong Lin

Wenzhong Lin

Auto-generated profile, based on publicly available information

Wenzhong Lin

Fujian Provincial Key Laboratory of Information Processing and Intelligent Control, College of Computer and Control Engineering, Minjiang University, Fuzhou 350108, China

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
11 May 2023 in Biomimetics
Verified
Journal Article
Open access
PDF file
ZWZhengyao Wen
Zhengyao Wen
WLWenzhong Lin
Wenzhong Lin
TWTao Wang
Tao Wang
GXGe Xu
Ge Xu
This paper presents a novel facial expression recognition network, called Distract your Attention Network (DAN). Our method is based on two key observations in biological visual perception. Firstly, multiple facial expression classes share inherently similar underlying facial appearance, and their differences could be subtle. Secondly, facial expressions simultaneously exhibit themselves through multiple facial regions, and for recognition, a holistic approach by encoding high-order interactions among local features is required. To address these issues, this work proposes DAN with three key components: Feature Clustering Network (FCN), Multi-head Attention Network (MAN), and Attention Fusion Network (AFN). Specifically, FCN extracts robust features by adopting a large-margin learning objective to maximize class separability. In addition, MAN instantiates a number of attention heads to simultaneously attend to multiple facial areas and build attention maps on these regions. Further, AFN distracts these attentions to multiple locations before fusing the feature maps to a comprehensive one. Extensive experiments on three public datasets (including AffectNet, RAF-DB, and SFEW 2.0) verified that the proposed method consistently achieves state-of-the-art facial expression recognition performance. The DAN code is publicly available.

17 April 2019 in Frontiers in Neuroscience
Verified
Journal Article
Open access
PDF file
ZZZuchang Zhang
Zuchang Zhang
DLDongliang Lin
Dongliang Lin
XWXingyi Wang
Xingyi Wang
ZSZhenhua Shao
Zhenhua Shao
WLWenzhong Lin
Wenzhong Lin
Periodic event-triggered control (PETC) is a control strategy consisting of event-triggered control (ETC) and conventional periodic sampled-data control. By using event-triggering mechanisms (ETM) to periodically verify whether or not to transmit and compute the measured output, communication and computational datum are significantly reduced while still retaining a satisfactory performance. This paper investigates the PETC scheme of robust H∞ filtering for a class of uncertain discrete-time Takagi-Sugeno (T-S) fuzzy systems, where the sample time is assumed to be a constant. To analyze the filtering problems of the PETC strategy, we present two frameworks based on perturbed linear and piecewise linear systems, to model filtering error systems. Sufficient conditions for the existence of a robust H∞ filter are derived in the form of matrix inequalities (LMIs) under these two frameworks, respectively. Finally, a simulation example is used to testify to the effectiveness of the proposed approach.

31 August 2020 in Mathematical Problems in Engineering
Verified
Journal Article
Open access
HLHui Li
Hui Li
YLYapeng Liu
Yapeng Liu
WLWenzhong Lin
Wenzhong Lin
Lingwei XuLingwei Xu
Lingwei Xu
JWJunyin Wang
Junyin Wang
In 5G scenarios, there are a large number of video signals that need to be processed. Multiobject tracking is one of the main directions in video signal processing. Data association is a very important link in tracking algorithms. Complexity and efficiency of association method have a direct impact on the performance of multiobject tracking. Breakthroughs have been made in data association methods based on deep learning, and the performance has been greatly improved compared with traditional methods. However, there is a lack of overviews about data association methods. Therefore, this article first analyzes characteristics and performance of three traditional data association methods and then focuses on data association methods based on deep learning, which is divided into different deep network structures: SOT methods, end-to-end methods, and Wasserstein metric methods. The performance of each tracking method is compared and analyzed. Finally, it summarizes the current common datasets and evaluation criteria for multiobject tracking and discusses challenges and development trends of data association technology and data association methods which ensure robust and real time need to be continuously improved.