Zhuo Li

Beijing University of Technology

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

Xiaoguang Li

Beijing University of Technology

Jing Zhang

Beijing University of Technology

Jiafeng Li

University of Minnesota

Hui Zhang

Beijing University of Technology

Charles J. Alpert

Cadence Design Systems (United States)

Shen Lan-sun

Beijing University of Technology

Hongxia Yin

Beijing Friendship Hospital

Jing Zhang

University of Sydney

Yingdi Zhao

Beijing University of Technology

Chunjie Ma

Shandong Academy of Sciences

Cooperative Institutions

Chinese Academy of Sciences

814

Institute of High Energy Physics

453

University of Chinese Academy of Sciences

370

University of Science and Technology of China

234

Southwest Jiaotong University

191

Beijing University of Technology

159

Gansu Great Wall Electrical and Electronics Engineering Research Institute

150

Campbell Collaboration

148

Sun Yat-sen University

147

Shandong University

147

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

Human operator modeling based on fractional order calculus in the manual control system with second-order controlled element

2022 34th Chinese Control and Decision Conference (CCDC) (2015)

Jiacai Huang YangQuan Chen Zhuo Li

The modeling for human operator behaviour is an important issue in the analysis and design for closed-loop manual control system, and the existing models for human operator are usually based on integer order calculus. In this paper, the manual control system with second-order controlled element is considered, and a kind of fractional order model for human operator is proposed. Based on the actual data, the effectiveness of the proposed model is validated, and the comparison results show that the proposed fractional order model is more suitable to describe the human operator behavior in the manual control process.

Operator (biology)

10.1109/ccdc.2015.7162802

Cite

Citations (5)

USID-Net: Unsupervised Single Image Dehazing Network via Disentangled Representations

IEEE Transactions on Multimedia (2022)

Jiafeng Li Yaopeng Li Zhuo Li Lingyan Kuang Tianjian Yu

Captured images of outdoor scenes usually exhibit low visibility in cases of severe haze, which interferes with optical imaging and degrades image quality. Most of the existing methods solve the single-image dehazing problem by applying supervised training on paired images; however, in practice, the pairing of real-world images is not viable. Additionally, the processing speed of individual dehazing models is important in practical applications. In this study, a novel unsupervised single image dehazing network (USID-Net) based on disentangled representations without paired training images is explored. Furthermore, considering the trade-off between performance and memory storage, a compact multi-scale feature attention (MFA) module is developed, integrating multi-scale feature representation and attention mechanism to facilitate feature representation. To effectively extract haze information, a mechanism referred to as OctEncoder is designed to include multi-frequency representations that can capture more global information. Extensive experiments show that USID-Net achieves competitive dehazing results and a relatively high processing speed compared to state-of-the-art methods. The source code is available at https://github.com/dehazing/USID-Net .

Feature (linguistics)

Representation

Visibility

Feature Learning

Code (set theory)

Net (polyhedron)

10.1109/tmm.2022.3163554

Cite

Citations (65)

Path smoothing via discrete optimization

Michael D. Moffitt David Papa Zhuo Li Charles J. Alpert

A fundamental problem in timing-driven physical synthesis is the reduction of critical paths in a design. In this work, we propose a powerful new technique that moves (and can also resize) multiple cells simultaneously to smooth critical paths, thereby reducing delay and improving worst negative slack or a figure-of-merit. Our approach offers several key advantages over previous formulations, including the accurate modeling of objectives and constraints in the true timing model, and a guarantee of legality for all cell locations.

Smoothing

Critical path method

10.1145/1391469.1391655

Cite

Citations (23)

The preliminary research on feature extraction and classification of acne tongue picture in TCM

Hong Wang Xinfeng Zhang Wenqiang Wu Yiheng Cai Zhuo Li

Acne has become a problem which people increasingly focus on since its high incidence and the scar after cure, etc. With the advantage of no scar and no side effects, Traditional Chinese Medicine (TCM) in treatment of acne by tongue diagnosis has gained more and more attention. Due to its qualitative, subjective and experience-based nature, and the type of acne is various, traditional diagnosis has a very limited application in clinical medicine. Moreover, traditional tongue diagnosis is always concerned with the identification of syndromes rather than with the connection between tongue abnormal appearances and diseases. In this paper, we proposed a novel tongue diagnosis analysis method based on HSV color space aiming to diagnose three common type of acne tongue. With this method, not only can extract the color characteristics of the tongue, it also preliminarily integrates the information of tongue coating, tongue body and color characteristics into the one-dimensional histogram; Meanwhile, Gray level Co-occurrence Matrix(GLCM) is applied to extract five commonly used features of tongue coating. Results show that the method can get the desired classification effect successfully.

Gray level

10.1145/2499788.2499806

Cite

Citations (2)

Management of mitral regurgitation in Marfan syndrome: Outcomes of valve repair versus replacement and comparison with myxomatous mitral valve disease

Journal of Thoracic and Cardiovascular Surgery (2014)

Meghana R.K. Helder Hartzell V. Schaff Joseph A. Dearani Zhuo Li John M. Stulak

Mitral valve replacement

Concomitant

10.1016/j.jtcvs.2014.06.046

Cite

Citations (24)

MPLA-Net: Multiple Pseudo Label Aggregation Network for Weakly Supervised Video Salient Object Detection

IEEE Transactions on Circuits and Systems for Video Technology (2023)

Chunjie Ma Lina Du Zhuo Li Jiafeng Li

Weakly Supervised Video Salient Object Detection (WSVSOD) only requires coarse-grained manual annotations, which can achieve a good trade-off between labeling efficiency and detection performance. In this paper, a Multiple Pseudo Label Aggregation Network (MPLA-Net) is proposed for WSVSOD. Firstly, the video frames that can obtain high-quality pseudo labels are selected to generate multiple pseudo labels, so as to avoid the prejudice of the single label. Moreover, the pseudo label with fine edge information is used to generate the Edge Information Map (EIM). Secondly, MPLA-Net is designed to adequately excavate and utilize the comprehensive saliency cues in multiple pseudo labels to improve the detection accuracy, in which ResNet-50 is adopted as the backbone network. Edge loss, pseudo label loss, self-supervised loss and fusion loss are exploited to jointly supervise and optimize the network training to obtain a robust detection model. Experimental results on five benchmark datasets demonstrate that, compared with existing weakly supervised methods, the proposed method can achieve state-of-the-art detection accuracy with less model parameters and higher detection speed. And the detected salient objects have fine boundaries.

Benchmark (surveying)

Backbone network

Information loss

Net (polyhedron)

10.1109/tcsvt.2023.3324708

Cite

Citations (3)

Research on pornographic images recognition method based on visual words in a compressed domain

IET Image Processing (2012)

Longfei Sui Ji Zhang Zhuo Li Yutuo Yang

In order to recognise and filter pornographic images, visual-word-based image representation has attracted more and more attention. An image can be represented as a bag of visual words, which is analogous to the bag-of-words representation of text documents. However, most of the existing approaches create visual words from images in the pixel domain, which requires extra processing time to decompress images, since most images are stored in compressed formats. A novel pornographic images recognition method based on visual words in a compressed domain is proposed in this study. There are four steps in this method: (i) low-resolution image is constructed from compressed data; (ii) scale-invariant feature transform (SIFT) descriptors are extracted from this low-resolution image; (iii) a visual vocabulary is created based on SIFT descriptors; (iv) pornographic images are identified by using a support vector machine (SVM) classifier. The experimental results indicate that the proposed method can recognise pornographic images accurately with much less computational time.

Scale-invariant feature transform

10.1049/iet-ipr.2011.0005

Cite

Citations (35)

Vehicle Color Recognition with Vehicle-Color Saliency Detection and Dual-Orientational Dimensionality Reduction of CNN Deep Features

Sensing and Imaging (2017)

Qiang Zhang Jiafeng Li Zhuo Li Hui Zhang Xiaoguang Li

RGB color model

10.1007/s11220-017-0173-8

Cite

Citations (6)

Low-Illumination Road Image Enhancement by Fusing Retinex Theory and Histogram Equalization

Electronics (2023)

Yi Han Xiangyong Chen Yi Zhong Yanqing Huang Zhuo Li

Low-illumination image enhancement can provide more information than the original image in low-light scenarios, e.g., nighttime driving. Traditional deep-learning-based image enhancement algorithms struggle to balance the performance between the overall illumination enhancement and local edge details, due to limitations of time and computational cost. This paper proposes a histogram equalization–multiscale Retinex combination approach (HE-MSR-COM) that aims at solving the blur edge problem of HE and the uncertainty in selecting parameters for image illumination enhancement in MSR. The enhanced illumination information is extracted from the low-frequency component in the HE-enhanced image, and the enhanced edge information is obtained from the high-frequency component in the MSR-enhanced image. By designing adaptive fusion weights of HE and MSR, the proposed method effectively combines enhanced illumination and edge information. The experimental results show that HE-MSR-COM improves the image quality by 23.95% and 10.6% in two datasets, respectively, compared with HE, contrast-limited adaptive histogram equalization (CLAHE), MSR, and gamma correction (GC).

Adaptive histogram equalization

Color Constancy

10.3390/electronics12040990

Cite

Citations (8)

Research on a Method of PID Error Compensation in Turning

Advanced materials research (2012)

Zhuo Li Jun Lü Yu Kun Wang

An error compensation model in turning based on PID adjustment was investigated in this paper. A new method is proposed to eliminate the effects of probe radius. Simultaneously, PID error compensation model is used to regulate the comprehensive error to obtain the actual quantity of error compensation. Computer-aided technology is applied to complete the algorithm, and then a new processing path is generated. The experimental results indicate that the precision of workpiece can be improved from 0.01mm to 0.003mm after three steps of error compensation.

Error Analysis

10.4028/scientific5/amr.452-453.110

Cite

Citations (0)