Chen Xu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Chen Xu has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Jian Lu
Shenzhen Key Laboratory of Advanced Machine Learning and Applications, School of Mathematical Sciences, Shenzhen University, Shenzhen, China
9 shared publications - Lixin Shen
Department of Mathematics, Syracuse University, Syracuse, NY 13244, USA
3 shared publications - Hu Zhang
Shenzhen Key Laboratory of Advanced Machine Learning and Applications, Shenzhen University, Shenzhen, China
2 shared publications - Yuesheng Xu
Department of Mathematics and Statistics, Old Dominion University, Norfolk, USA
2 shared publications - Yuru Zou
Shenzhen Key Laboratory of Advanced Machine Learning and Applications, School of Mathematical Sciences, Shenzhen University, Shenzhen 518060, P. R. China
2 shared publications - Ahmed Elazab
Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China
1 shared publication
Latest Publications
- 7 May 2026
- Published by Springer Nature in The Visual Computer
- Vol. 42 (7) , 286
Dual-feature attention for robust point cloud registration: integrating transformation-variant and invariant features
- 7 May 2026
- Published by Springer Nature in The Visual Computer
- Vol. 42 (7) , 286
Dual-feature attention for robust point cloud registration: integrating transformation-variant and invariant features
- Open Access
- 5 December 2025
- Published by Global Science Press in Journal of Computational Mathematics
Stochastic Variance Reduced Gradient for Tensor Recovery
Low-rank tensor recovery is pivotal in numerous applications, including image and video processing, machine learning, and data analysis. A common approach to this problem involves convex relaxation, where the tensor rank function is minimized by using the tensor nuclear norm. However, this method can be significantly suboptimal. In addition, the stochastic variance reduced gradient (SVRG) method, a variant of stochastic gradient descent, has been applied to matrix recovery problems. In this paper, we extend the SVRG method to the tensor framework, introducing the tensor stochastic variance reduced gradient (TSVRG) algorithm for tensor recovery with CP or Tucker rank constraints. TSVRG is designed to achieve higher precision solutions by escaping local minima and identifying superior global optima. Moreover, TSVRG offers reduced computational complexity compared to traditional gradient descent methods. We establish a convergence theorem for TSVRG under the tensor restricted isometry condition when the measurements are linear. Finally, we present numerical results using both synthetic and real data, demonstrating the competitive performance of TSVRG compared to other advanced algorithms.
- 5 December 2025
- Published by Global Science Press in Journal of Computational Mathematics
Open AccessStochastic Variance Reduced Gradient for Tensor Recovery
Low-rank tensor recovery is pivotal in numerous applications, including image and video processing, machine learning, and data analysis. A common approach to this problem involves convex relaxation, where the tensor rank function is minimized by using the tensor nuclear norm. However, this method can be significantly suboptimal. In addition, the stochastic variance reduced gradient (SVRG) method, a variant of stochastic gradient descent, has been applied to matrix recovery problems. In this paper, we extend the SVRG method to the tensor framework, introducing the tensor stochastic variance reduced gradient (TSVRG) algorithm for tensor recovery with CP or Tucker rank constraints. TSVRG is designed to achieve higher precision solutions by escaping local minima and identifying superior global optima. Moreover, TSVRG offers reduced computational complexity compared to traditional gradient descent methods. We establish a convergence theorem for TSVRG under the tensor restricted isometry condition when the measurements are linear. Finally, we present numerical results using both synthetic and real data, demonstrating the competitive performance of TSVRG compared to other advanced algorithms.
- 25 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 22 (4) , 4315-4329
BERT-PhishFinder: A Robust Model for Accurate Phishing URL Detection With Optimized DistilBERT
Phishing URL detection has become a critical challenge in cybersecurity, with existing methods often struggling to maintain high accuracy while generalizing across diverse datasets. In this paper, we introduce BERT-PhishFinder, a novel and efficient transformer-based model designed to tackle this problem. While most traditional approaches rely heavily on lexical features or complex convolutional architectures, BERT-PhishFinder leverages the power of DistilBERT, a lightweight yet highly effective transformer, to capture rich contextual representations of URL sequences. To enhance the model’s robustness and reduce overfitting, we strategically incorporate SpatialDropout1D in the embedding layers, along with global average pooling and global max pooling techniques to extract both comprehensive and key discriminative features. The pooled representations are thoughtfully concatenated to form a comprehensive feature representation. Through this carefully crafted design, our model adopts ensemble learning, as it undergoes multiple parallel dense layers, each with distinct parameters and dropout regularization. This facilitates learning diverse patterns and features from the input URL sequence, culminating in exceptional phishing URL detection performance. Extensive evaluations against conventional deep learning algorithms, transformer models (XLNet, RoBERTa, ALBERT), and other existing methods on five benchmark datasets show that BERT-PhishFinder not only achieves the state of-the-art real phishing URL detection but also accomplishes this with reduced label dependency.
- 25 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 22 (4) , 4315-4329
BERT-PhishFinder: A Robust Model for Accurate Phishing URL Detection With Optimized DistilBERT
Phishing URL detection has become a critical challenge in cybersecurity, with existing methods often struggling to maintain high accuracy while generalizing across diverse datasets. In this paper, we introduce BERT-PhishFinder, a novel and efficient transformer-based model designed to tackle this problem. While most traditional approaches rely heavily on lexical features or complex convolutional architectures, BERT-PhishFinder leverages the power of DistilBERT, a lightweight yet highly effective transformer, to capture rich contextual representations of URL sequences. To enhance the model’s robustness and reduce overfitting, we strategically incorporate SpatialDropout1D in the embedding layers, along with global average pooling and global max pooling techniques to extract both comprehensive and key discriminative features. The pooled representations are thoughtfully concatenated to form a comprehensive feature representation. Through this carefully crafted design, our model adopts ensemble learning, as it undergoes multiple parallel dense layers, each with distinct parameters and dropout regularization. This facilitates learning diverse patterns and features from the input URL sequence, culminating in exceptional phishing URL detection performance. Extensive evaluations against conventional deep learning algorithms, transformer models (XLNet, RoBERTa, ALBERT), and other existing methods on five benchmark datasets show that BERT-PhishFinder not only achieves the state of-the-art real phishing URL detection but also accomplishes this with reduced label dependency.
- Open Access
- 11 February 2025
- Published by Elsevier in Neural Networks
- Vol. 185, 107248
EMBANet: A flexible efficient multi-branch attention network
- 11 February 2025
- Published by Elsevier in Neural Networks
- Vol. 185, 107248
Open AccessEMBANet: A flexible efficient multi-branch attention network
- 23 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Imaging
- Vol. 10 (25730436) , 1571-1587
Fixed-Point Convergence of Multi-Block PnP ADMM and Its Application to Hyperspectral Image Restoration
Coupling methods of integrating multiple priors have emerged as a pivotal research focus in hyperspectral image (HSI) restoration. Among these methods, the Plug-and-Play (PnP) framework stands out and pioneers a novel coupling approach, enabling flexible integration of diverse methods into model-based approaches. However, the current convergence analyses of the PnP framework are highly unexplored, as they are limited to 2-block composite optimization problems, failing to meet the need of coupling modeling for incorporating multiple priors. This paper focuses on the convergence analysis of PnP-based algorithms for multi-block composite optimization problems. In this work, under the PnP framework and utilizing the alternating direction method of multipliers (ADMM) of the continuation scheme, we propose a unified multi-block PnP ADMM algorithm framework for HSI restoration. Inspired by the fixed-point convergence theory of the 2-block PnP ADMM, we establish a similar fixed-point convergence guarantee for the multi-block PnP ADMM with extended condition and provide a feasible parameter tuning methodology. Based on this framework, we design an effective mixed noise removal algorithm incorporating global, nonlocal and deep priors. Extensive experiments validate the algorithm's superiority and competitiveness. The open-source code is available online at https://github.com/Weijie-Liang/FBGND .
- 23 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Imaging
- Vol. 10 (25730436) , 1571-1587
Fixed-Point Convergence of Multi-Block PnP ADMM and Its Application to Hyperspectral Image Restoration
Coupling methods of integrating multiple priors have emerged as a pivotal research focus in hyperspectral image (HSI) restoration. Among these methods, the Plug-and-Play (PnP) framework stands out and pioneers a novel coupling approach, enabling flexible integration of diverse methods into model-based approaches. However, the current convergence analyses of the PnP framework are highly unexplored, as they are limited to 2-block composite optimization problems, failing to meet the need of coupling modeling for incorporating multiple priors. This paper focuses on the convergence analysis of PnP-based algorithms for multi-block composite optimization problems. In this work, under the PnP framework and utilizing the alternating direction method of multipliers (ADMM) of the continuation scheme, we propose a unified multi-block PnP ADMM algorithm framework for HSI restoration. Inspired by the fixed-point convergence theory of the 2-block PnP ADMM, we establish a similar fixed-point convergence guarantee for the multi-block PnP ADMM with extended condition and provide a feasible parameter tuning methodology. Based on this framework, we design an effective mixed noise removal algorithm incorporating global, nonlocal and deep priors. Extensive experiments validate the algorithm's superiority and competitiveness. The open-source code is available online at https://github.com/Weijie-Liang/FBGND .
- Open Access
EMBANet: A Flexible Efffcient Multi-branch Attention Network
This work presents a novel module, namely multi-branch concat (MBC), to process the input tensor and obtain the multi-scale feature map. The proposed MBC module brings new degrees of freedom (DoF) for the design of attention networks by allowing the type of transformation operators and the number of branches to be flexibly adjusted. Two important transformation operators, multiplex and split, are considered in this work, both of which can represent multi-scale features at a more granular level and increase the range of receptive fields. By integrating the MBC and attention module, a multi-branch attention (MBA) module is consequently developed to capture the channel-wise interaction of feature maps for establishing the long-range channel dependency. By substituting the 3x3 convolutions in the bottleneck blocks of the ResNet with the proposed MBA, a novel block namely efficient multi-branch attention (EMBA) is obtained, which can be easily plugged into the state-of-the-art backbone CNN models. Furthermore, a new backbone network called EMBANet is established by stacking the EMBA blocks. The proposed EMBANet is extensively evaluated on representative computer vision tasks including: classification, detection, and segmentation. And it demonstrates consistently superior performance over the popular backbones.
Open AccessEMBANet: A Flexible Efffcient Multi-branch Attention Network
This work presents a novel module, namely multi-branch concat (MBC), to process the input tensor and obtain the multi-scale feature map. The proposed MBC module brings new degrees of freedom (DoF) for the design of attention networks by allowing the type of transformation operators and the number of branches to be flexibly adjusted. Two important transformation operators, multiplex and split, are considered in this work, both of which can represent multi-scale features at a more granular level and increase the range of receptive fields. By integrating the MBC and attention module, a multi-branch attention (MBA) module is consequently developed to capture the channel-wise interaction of feature maps for establishing the long-range channel dependency. By substituting the 3x3 convolutions in the bottleneck blocks of the ResNet with the proposed MBA, a novel block namely efficient multi-branch attention (EMBA) is obtained, which can be easily plugged into the state-of-the-art backbone CNN models. Furthermore, a new backbone network called EMBANet is established by stacking the EMBA blocks. The proposed EMBANet is extensively evaluated on representative computer vision tasks including: classification, detection, and segmentation. And it demonstrates consistently superior performance over the popular backbones.
- Open Access
OSRE: Object-to-Spot Rotation Estimation for Bike Parking Assessment
Current deep models provide remarkable object detection in terms of object classification and localization. However, estimating object rotation with respect to other visual objects in the visual context of an input image still lacks deep studies due to the unavailability of object datasets with rotation annotations. This paper tackles these two challenges to solve the rotation estimation of a parked bike with respect to its parking area. First, we leverage the power of 3D graphics to build a camera-agnostic well-annotated Synthetic Bike Rotation Dataset (SynthBRSet). Then, we propose an object-to-spot rotation estimator (OSRE) by extending the object detection task to further regress the bike rotations in two axes. Since our model is purely trained on synthetic data, we adopt image smoothing techniques when deploying it on real-world images. The proposed OSRE is evaluated on synthetic and real-world data providing promising results. Our data and code are available at \href{https://github.com/saghiralfasly/OSRE-Project}{https://github.com/saghiralfasly/OSRE-Project}.
Open AccessOSRE: Object-to-Spot Rotation Estimation for Bike Parking Assessment
Current deep models provide remarkable object detection in terms of object classification and localization. However, estimating object rotation with respect to other visual objects in the visual context of an input image still lacks deep studies due to the unavailability of object datasets with rotation annotations. This paper tackles these two challenges to solve the rotation estimation of a parked bike with respect to its parking area. First, we leverage the power of 3D graphics to build a camera-agnostic well-annotated Synthetic Bike Rotation Dataset (SynthBRSet). Then, we propose an object-to-spot rotation estimator (OSRE) by extending the object detection task to further regress the bike rotations in two axes. Since our model is purely trained on synthetic data, we adopt image smoothing techniques when deploying it on real-world images. The proposed OSRE is evaluated on synthetic and real-world data providing promising results. Our data and code are available at \href{https://github.com/saghiralfasly/OSRE-Project}{https://github.com/saghiralfasly/OSRE-Project}.
- Open Access
Learnable Irrelevant Modality Dropout for Multimodal Action Recognition on Modality-Specific Annotated Videos
With the assumption that a video dataset is multimodality annotated in which auditory and visual modalities both are labeled or class-relevant, current multimodal methods apply modality fusion or cross-modality attention. However, effectively leveraging the audio modality in vision-specific annotated videos for action recognition is of particular challenge. To tackle this challenge, we propose a novel audio-visual framework that effectively leverages the audio modality in any solely vision-specific annotated dataset. We adopt the language models (e.g., BERT) to build a semantic audio-video label dictionary (SAVLD) that maps each video label to its most K-relevant audio labels in which SAVLD serves as a bridge between audio and video datasets. Then, SAVLD along with a pretrained audio multi-label model are used to estimate the audio-visual modality relevance during the training phase. Accordingly, a novel learnable irrelevant modality dropout (IMD) is proposed to completely drop out the irrelevant audio modality and fuse only the relevant modalities. Moreover, we present a new two-stream video Transformer for efficiently modeling the visual modalities. Results on several vision-specific annotated datasets including Kinetics400 and UCF-101 validated our framework as it outperforms most relevant action recognition methods.
Open AccessLearnable Irrelevant Modality Dropout for Multimodal Action Recognition on Modality-Specific Annotated Videos
With the assumption that a video dataset is multimodality annotated in which auditory and visual modalities both are labeled or class-relevant, current multimodal methods apply modality fusion or cross-modality attention. However, effectively leveraging the audio modality in vision-specific annotated videos for action recognition is of particular challenge. To tackle this challenge, we propose a novel audio-visual framework that effectively leverages the audio modality in any solely vision-specific annotated dataset. We adopt the language models (e.g., BERT) to build a semantic audio-video label dictionary (SAVLD) that maps each video label to its most K-relevant audio labels in which SAVLD serves as a bridge between audio and video datasets. Then, SAVLD along with a pretrained audio multi-label model are used to estimate the audio-visual modality relevance during the training phase. Accordingly, a novel learnable irrelevant modality dropout (IMD) is proposed to completely drop out the irrelevant audio modality and fuse only the relevant modalities. Moreover, we present a new two-stream video Transformer for efficiently modeling the visual modalities. Results on several vision-specific annotated datasets including Kinetics400 and UCF-101 validated our framework as it outperforms most relevant action recognition methods.
- Open Access
Multiplicative Noise Removal: Nonlocal Low-Rank Model and Its Proximal Alternating Reweighted Minimization Algorithm
The goal of this paper is to develop a novel numerical method for efficient multiplicative noise removal. The nonlocal self-similarity of natural images implies that the matrices formed by their nonlocal similar patches are low-rank. By exploiting this low-rank prior with application to multiplicative noise removal, we propose a nonlocal low-rank model for this task and develop a proximal alternating reweighted minimization (PARM) algorithm to solve the optimization problem resulting from the model. Specifically, we utilize a generalized nonconvex surrogate of the rank function to regularize the patch matrices and develop a new nonlocal low-rank model, which is a nonconvex nonsmooth optimization problem having a patchwise data fidelity and a generalized nonlocal low-rank regularization term. To solve this optimization problem, we propose the PARM algorithm, which has a proximal alternating scheme with a reweighted approximation of its subproblem. A theoretical analysis of the proposed PARM algorithm is conducted to guarantee its global convergence to a critical point. Numerical experiments demonstrate that the proposed method for multiplicative noise removal significantly outperforms existing methods such as the benchmark SAR-BM3D method in terms of the visual quality of the denoised images, and the PSNR (the peak-signal-to-noise ratio) and SSIM (the structural similarity index measure) values.
Open AccessMultiplicative Noise Removal: Nonlocal Low-Rank Model and Its Proximal Alternating Reweighted Minimization Algorithm
The goal of this paper is to develop a novel numerical method for efficient multiplicative noise removal. The nonlocal self-similarity of natural images implies that the matrices formed by their nonlocal similar patches are low-rank. By exploiting this low-rank prior with application to multiplicative noise removal, we propose a nonlocal low-rank model for this task and develop a proximal alternating reweighted minimization (PARM) algorithm to solve the optimization problem resulting from the model. Specifically, we utilize a generalized nonconvex surrogate of the rank function to regularize the patch matrices and develop a new nonlocal low-rank model, which is a nonconvex nonsmooth optimization problem having a patchwise data fidelity and a generalized nonlocal low-rank regularization term. To solve this optimization problem, we propose the PARM algorithm, which has a proximal alternating scheme with a reweighted approximation of its subproblem. A theoretical analysis of the proposed PARM algorithm is conducted to guarantee its global convergence to a critical point. Numerical experiments demonstrate that the proposed method for multiplicative noise removal significantly outperforms existing methods such as the benchmark SAR-BM3D method in terms of the visual quality of the denoised images, and the PSNR (the peak-signal-to-noise ratio) and SSIM (the structural similarity index measure) values.
- Open Access
- 1 January 2017
- Published by American Institute of Mathematical Sciences (AIMS) in Inverse Problems and Imaging
- Vol. 11 (6) , 949-974
Multiplicative noise removal with a sparsity-aware optimization model
Restoration of images contaminated by multiplicative noise (also known as speckle noise) is a key issue in coherent image processing. Notice that images under consideration are often highly compressible in certain suitably chosen transform domains. By exploring this intrinsic feature embedded in images, this paper introduces a variational restoration model for multiplicative noise reduction that consists of a term reflecting the observed image and multiplicative noise, a quadratic term measuring the closeness of the underlying image in a transform domain to a sparse vector, and a sparse regularizer for removing multiplicative noise. Being different from popular existing models which focus on pursuing convexity, the proposed sparsity-aware model may be nonconvex depending on the conditions of the parameters of the model for achieving the optimal denoising performance. An algorithm for finding a critical point of the objective function of the model is developed based on coupled fixed-point equations expressed in terms of the proximity operator of functions that appear in the objective function. Convergence analysis of the algorithm is provided. Experimental results are shown to demonstrate that the proposed iterative algorithm is sensitive to some initializations for obtaining the best restoration results. We observe that the proposed method with SAR-BM3D filtering images as initial estimates can remarkably outperform several state-of-art methods in terms of the quality of the restored images.
- 1 January 2017
- Published by American Institute of Mathematical Sciences (AIMS) in Inverse Problems and Imaging
- Vol. 11 (6) , 949-974
Open AccessMultiplicative noise removal with a sparsity-aware optimization model
Restoration of images contaminated by multiplicative noise (also known as speckle noise) is a key issue in coherent image processing. Notice that images under consideration are often highly compressible in certain suitably chosen transform domains. By exploring this intrinsic feature embedded in images, this paper introduces a variational restoration model for multiplicative noise reduction that consists of a term reflecting the observed image and multiplicative noise, a quadratic term measuring the closeness of the underlying image in a transform domain to a sparse vector, and a sparse regularizer for removing multiplicative noise. Being different from popular existing models which focus on pursuing convexity, the proposed sparsity-aware model may be nonconvex depending on the conditions of the parameters of the model for achieving the optimal denoising performance. An algorithm for finding a critical point of the objective function of the model is developed based on coupled fixed-point equations expressed in terms of the proximity operator of functions that appear in the objective function. Convergence analysis of the algorithm is provided. Experimental results are shown to demonstrate that the proposed iterative algorithm is sensitive to some initializations for obtaining the best restoration results. We observe that the proposed method with SAR-BM3D filtering images as initial estimates can remarkably outperform several state-of-art methods in terms of the quality of the restored images.