Lei Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Lei Liu has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Shuai Wang
School of Computer Science and Technology, Huaibei Normal University, Huaibei 235000, China
8 shared publications - Jun Wang
College of Electronic and Information Engineering, HeBei University, BaoDing, China
7 shared publications - Silas Nogueira de Melo
Universidade Estadual do Maranhão
4 shared publications - Kongfen Zhu
Huaibei Normal University
3 shared publications - Aolin Zhang
School of Mathematics and Information Science, Hebei University, Baoding 071000, China
2 shared publications Baosen Liu
Affiliation Huaibei People’s Hospital, Huaibei, Anhui, China
2 shared publications
Latest Publications
- 27 August 2026
- Published by ELS Publishing Co. Limited in Proceedings: Computer Science
- Vol. 4, 1
An intelligent soft–voting based early warning model for loan risk
Against the backdrop of fintech driven intelligent risk control, traditional manual loan review, hindered by low efficiency and high subjectivity, struggles to meet the massive demand for credit risk assessment. This paper proposes a multi–model fusion framework based on soft–voting, integrating Feedforward Neural Network (FNN), LightGBM, and CatBoost, and combining with scorecard technology to achieve precise prediction of loan default risks and their operational implementation. Using more than 1 million loan records from Alibaba Cloud Tianchi, the study employs data cleaning, clustering binning (10 bins), standardization, and construction of 10 composite features (e.g., ratio of income to loan amount). The core features are selected using chi–square test (p), Population Stability Index (PSI), and Information Value (IV). Through exhaustive experiments, the soft–voting mechanism determines optimal weights (0.1:0.1:0.8), allowing the integrated model to achieve an AUC of 0.739, significantly improving the generalization while maintaining high accuracy. The scorecard model converts probabilities into credit scores, classifying customers into four tiers (A to D). This study transcends the limitations of single models, achieving deep integration of technical interpretability and business implementation through the dual mechanism of model fusion and scorecard. It provides financial institutions with end–to–end solutions from risk quantification to strategy execution, facilitating dynamic monitoring and management of in–lending behavioral risks.
- 27 August 2026
- Published by ELS Publishing Co. Limited in Proceedings: Computer Science
- Vol. 4, 1
An intelligent soft–voting based early warning model for loan risk
Against the backdrop of fintech driven intelligent risk control, traditional manual loan review, hindered by low efficiency and high subjectivity, struggles to meet the massive demand for credit risk assessment. This paper proposes a multi–model fusion framework based on soft–voting, integrating Feedforward Neural Network (FNN), LightGBM, and CatBoost, and combining with scorecard technology to achieve precise prediction of loan default risks and their operational implementation. Using more than 1 million loan records from Alibaba Cloud Tianchi, the study employs data cleaning, clustering binning (10 bins), standardization, and construction of 10 composite features (e.g., ratio of income to loan amount). The core features are selected using chi–square test (p), Population Stability Index (PSI), and Information Value (IV). Through exhaustive experiments, the soft–voting mechanism determines optimal weights (0.1:0.1:0.8), allowing the integrated model to achieve an AUC of 0.739, significantly improving the generalization while maintaining high accuracy. The scorecard model converts probabilities into credit scores, classifying customers into four tiers (A to D). This study transcends the limitations of single models, achieving deep integration of technical interpretability and business implementation through the dual mechanism of model fusion and scorecard. It provides financial institutions with end–to–end solutions from risk quantification to strategy execution, facilitating dynamic monitoring and management of in–lending behavioral risks.
- 10 March 2026
- Published by Springer Nature in Multimedia Systems
- Vol. 32 (3) , 175
Mamba-driven context-aware tracking with dual prompts
- 10 March 2026
- Published by Springer Nature in Multimedia Systems
- Vol. 32 (3) , 175
Mamba-driven context-aware tracking with dual prompts
- 7 February 2026
- Published by Springer Nature
- p. 296-310
SDFTrack: Exploring Semantic Information Fusion for Image-Level Object Tracking
- 7 February 2026
- Published by Springer Nature
- p. 296-310
SDFTrack: Exploring Semantic Information Fusion for Image-Level Object Tracking
- Open Access
Video Coding Based on Ladder Subband Recovery and ResGroup Module
With the rapid development of video encoding technology in the field of computer vision, the demand for tasks such as video frame reconstruction, denoising, and super-resolution has been continuously increasing. However, traditional video encoding methods typically focus on extracting spatial or temporal domain information, often facing challenges of insufficient accuracy and information loss when reconstructing high-frequency details, edges, and textures of images. To address this issue, this paper proposes an innovative LadderConv framework, which combines discrete wavelet transform (DWT) with spatial and channel attention mechanisms. By progressively recovering wavelet subbands, it effectively enhances the video frame encoding quality. Specifically, the LadderConv framework adopts a stepwise recovery approach for wavelet subbands, first processing high-frequency detail subbands with relatively less information, then enhancing the interaction between these subbands, and ultimately synthesizing a high-quality reconstructed image through inverse wavelet transform. Moreover, the framework introduces spatial and channel attention mechanisms, which further strengthen the focus on key regions and channel features, leading to notable improvements in detail restoration and image reconstruction accuracy. To optimize the performance of the LadderConv framework, particularly in detail recovery and high-frequency information extraction tasks, this paper designs an innovative ResGroup module. By using multi-layer convolution operations along with feature map compression and recovery, the ResGroup module enhances the network’s expressive capability and effectively reduces computational complexity. The ResGroup module captures multi-level features from low level to high level and retains rich feature information through residual connections, thus improving the overall reconstruction performance of the model. In experiments, the combination of the LadderConv framework and the ResGroup module demonstrates superior performance in video frame reconstruction tasks, particularly in recovering high-frequency information, image clarity, and detail representation.
Open AccessVideo Coding Based on Ladder Subband Recovery and ResGroup Module
With the rapid development of video encoding technology in the field of computer vision, the demand for tasks such as video frame reconstruction, denoising, and super-resolution has been continuously increasing. However, traditional video encoding methods typically focus on extracting spatial or temporal domain information, often facing challenges of insufficient accuracy and information loss when reconstructing high-frequency details, edges, and textures of images. To address this issue, this paper proposes an innovative LadderConv framework, which combines discrete wavelet transform (DWT) with spatial and channel attention mechanisms. By progressively recovering wavelet subbands, it effectively enhances the video frame encoding quality. Specifically, the LadderConv framework adopts a stepwise recovery approach for wavelet subbands, first processing high-frequency detail subbands with relatively less information, then enhancing the interaction between these subbands, and ultimately synthesizing a high-quality reconstructed image through inverse wavelet transform. Moreover, the framework introduces spatial and channel attention mechanisms, which further strengthen the focus on key regions and channel features, leading to notable improvements in detail restoration and image reconstruction accuracy. To optimize the performance of the LadderConv framework, particularly in detail recovery and high-frequency information extraction tasks, this paper designs an innovative ResGroup module. By using multi-layer convolution operations along with feature map compression and recovery, the ResGroup module enhances the network’s expressive capability and effectively reduces computational complexity. The ResGroup module captures multi-level features from low level to high level and retains rich feature information through residual connections, thus improving the overall reconstruction performance of the model. In experiments, the combination of the LadderConv framework and the ResGroup module demonstrates superior performance in video frame reconstruction tasks, particularly in recovering high-frequency information, image clarity, and detail representation.
- 5 July 2025
- Published by Springer Nature
- p. 391-399
Point Cloud Compression Based on Multi-level Vein Extraction
- 5 July 2025
- Published by Springer Nature
- p. 391-399
Point Cloud Compression Based on Multi-level Vein Extraction
- 5 July 2025
- Published by Springer Nature
- p. 69-85
FSACNN: Fourier Supervised Attention Convolutional Neural Network for the Denoising of Low-Dose CT Images
- 5 July 2025
- Published by Springer Nature
- p. 69-85
FSACNN: Fourier Supervised Attention Convolutional Neural Network for the Denoising of Low-Dose CT Images
- Open Access
- 12 June 2025
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 20 (6) , e0325899
SA-UMamba: Spatial attention convolutional neural networks for medical image segmentation
Medical image segmentation plays an important role in medical diagnosis and treatment. Most recent medical image segmentation methods are based on a convolutional neural network (CNN) or Transformer model. However, CNN-based methods are limited by locality, whereas Transformer-based methods are constrained by the quadratic complexity of attention computations. Alternatively, the state-space model-based Mamba architecture has garnered widespread attention owing to its linear computational complexity for global modeling. However, Mamba and its variants are still limited in their ability to extract local receptive field features. To address this limitation, we propose a novel residual spatial state-space (RSSS) block that enhances spatial feature extraction by integrating global and local representations. The RSSS block combines the Mamba module for capturing global dependencies with a receptive field attention convolution (RFAC) module to extract location-sensitive local patterns. Furthermore, we introduce a residual adjust strategy to dynamically fuse global and local information, improving spatial expressiveness. Based on the RSSS block, we design a U-shaped SA-UMamba segmentation framework that effectively captures multi-scale spatial context across different stages. Experiments conducted on the Synapse, ISIC17, ISIC18 and CVC-ClinicDB datasets validate the segmentation performance of our proposed SA-UMamba framework.
- 12 June 2025
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 20 (6) , e0325899
Open AccessSA-UMamba: Spatial attention convolutional neural networks for medical image segmentation
Medical image segmentation plays an important role in medical diagnosis and treatment. Most recent medical image segmentation methods are based on a convolutional neural network (CNN) or Transformer model. However, CNN-based methods are limited by locality, whereas Transformer-based methods are constrained by the quadratic complexity of attention computations. Alternatively, the state-space model-based Mamba architecture has garnered widespread attention owing to its linear computational complexity for global modeling. However, Mamba and its variants are still limited in their ability to extract local receptive field features. To address this limitation, we propose a novel residual spatial state-space (RSSS) block that enhances spatial feature extraction by integrating global and local representations. The RSSS block combines the Mamba module for capturing global dependencies with a receptive field attention convolution (RFAC) module to extract location-sensitive local patterns. Furthermore, we introduce a residual adjust strategy to dynamically fuse global and local information, improving spatial expressiveness. Based on the RSSS block, we design a U-shaped SA-UMamba segmentation framework that effectively captures multi-scale spatial context across different stages. Experiments conducted on the Synapse, ISIC17, ISIC18 and CVC-ClinicDB datasets validate the segmentation performance of our proposed SA-UMamba framework.
- Open Access
MRCA-UNet: A Multiscale Recombined Channel Attention U-Net Model for Medical Image Segmentation
Deep learning techniques play a crucial role in medical image segmentation for diagnostic purposes, with traditional convolutional neural networks (CNNs) and emerging transformers having achieved satisfactory results. CNN-based methods focus on extracting the local features of an image, which are beneficial for handling image details and textural features. However, the receptive fields of CNNs are relatively small, resulting in poor performance when processing images with long-range dependencies. Conversely, transformer-based methods are effective in handling global information; however, they suffer from significant computational complexity arising from the building of long-range dependencies. Additionally, they lack the ability to perceive image details and adopt channel features. These problems can result in unclear image segmentation and blurred boundaries. Accordingly, in this study, a multiscale recombined channel attention (MRCA) module is proposed, which can simultaneously extract both global and local features and has the capability of exploring channel features during feature fusion. Specifically, the proposed MRCA first employs multibranch extraction of image features and performs operations such as blocking, shifting, and aggregating the image at different scales. This step enables the model to recognize multiscale information locally and globally. Feature selection is then performed to enhance the predictive capability of the model. Finally, features from different branches are connected and recombined across channels to complete the feature fusion. Benefiting from fully exploring the channel features, an MRCA-based U-Net (MRCA-UNet) framework is proposed for medical image segmentation. Experiments conducted on the Synapse multi-organ segmentation (Synapse) dataset and the International Skin Imaging Collaboration (ISIC-2018) dataset demonstrate the competitive segmentation performance of the proposed MRCA-UNet, achieving an average Dice Similarity Coefficient (DSC) of 81.61% and a Hausdorff Distance (HD) of 23.36 on Synapse and an Accuracy of 95.94% on ISIC-2018.
Open AccessMRCA-UNet: A Multiscale Recombined Channel Attention U-Net Model for Medical Image Segmentation
Deep learning techniques play a crucial role in medical image segmentation for diagnostic purposes, with traditional convolutional neural networks (CNNs) and emerging transformers having achieved satisfactory results. CNN-based methods focus on extracting the local features of an image, which are beneficial for handling image details and textural features. However, the receptive fields of CNNs are relatively small, resulting in poor performance when processing images with long-range dependencies. Conversely, transformer-based methods are effective in handling global information; however, they suffer from significant computational complexity arising from the building of long-range dependencies. Additionally, they lack the ability to perceive image details and adopt channel features. These problems can result in unclear image segmentation and blurred boundaries. Accordingly, in this study, a multiscale recombined channel attention (MRCA) module is proposed, which can simultaneously extract both global and local features and has the capability of exploring channel features during feature fusion. Specifically, the proposed MRCA first employs multibranch extraction of image features and performs operations such as blocking, shifting, and aggregating the image at different scales. This step enables the model to recognize multiscale information locally and globally. Feature selection is then performed to enhance the predictive capability of the model. Finally, features from different branches are connected and recombined across channels to complete the feature fusion. Benefiting from fully exploring the channel features, an MRCA-based U-Net (MRCA-UNet) framework is proposed for medical image segmentation. Experiments conducted on the Synapse multi-organ segmentation (Synapse) dataset and the International Skin Imaging Collaboration (ISIC-2018) dataset demonstrate the competitive segmentation performance of the proposed MRCA-UNet, achieving an average Dice Similarity Coefficient (DSC) of 81.61% and a Hausdorff Distance (HD) of 23.36 on Synapse and an Accuracy of 95.94% on ISIC-2018.
- Open Access
- 3 December 2024
- Published by PeerJ in PeerJ Computer Science
- Vol. 10, e2563
MSR-UNet: enhancing multi-scale and long-range dependencies in medical image segmentation
Transformer-based technology has attracted widespread attention in medical image segmentation. Due to the diversity of organs, effective modelling of multi-scale information and establishing long-range dependencies between pixels are crucial for successful medical image segmentation. However, most studies rely on a fixed single-scale window for modeling, which ignores the potential impact of window size on performance. This limitation can hinder window-based models’ ability to fully explore multi-scale and long-range relationships within medical images. To address this issue, we propose a multi-scale reconfiguration self-attention (MSR-SA) module that accurately models multi-scale information and long-range dependencies in medical images. The MSR-SA module first divides the attention heads into multiple groups, each assigned an ascending dilation rate. These groups are then uniformly split into several non-overlapping local windows. Using dilated sampling, we gather the same number of keys to obtain both long-range and multi-scale information. Finally, dynamic information fusion is achieved by integrating features from the sampling points at corresponding positions across different windows. Based on the MSR-SA module, we propose a multi-scale reconfiguration U-Net (MSR-UNet) framework for medical image segmentation. Experiments on the Synapse and automated cardiac diagnosis challenge (ACDC) datasets show that MSR-UNet can achieve satisfactory segmentation results. The code is available at https://github.com/davidsmithwj/MSR-UNet (DOI: 10.5281/zenodo.13969855).
- 3 December 2024
- Published by PeerJ in PeerJ Computer Science
- Vol. 10, e2563
Open AccessMSR-UNet: enhancing multi-scale and long-range dependencies in medical image segmentation
Transformer-based technology has attracted widespread attention in medical image segmentation. Due to the diversity of organs, effective modelling of multi-scale information and establishing long-range dependencies between pixels are crucial for successful medical image segmentation. However, most studies rely on a fixed single-scale window for modeling, which ignores the potential impact of window size on performance. This limitation can hinder window-based models’ ability to fully explore multi-scale and long-range relationships within medical images. To address this issue, we propose a multi-scale reconfiguration self-attention (MSR-SA) module that accurately models multi-scale information and long-range dependencies in medical images. The MSR-SA module first divides the attention heads into multiple groups, each assigned an ascending dilation rate. These groups are then uniformly split into several non-overlapping local windows. Using dilated sampling, we gather the same number of keys to obtain both long-range and multi-scale information. Finally, dynamic information fusion is achieved by integrating features from the sampling points at corresponding positions across different windows. Based on the MSR-SA module, we propose a multi-scale reconfiguration U-Net (MSR-UNet) framework for medical image segmentation. Experiments on the Synapse and automated cardiac diagnosis challenge (ACDC) datasets show that MSR-UNet can achieve satisfactory segmentation results. The code is available at https://github.com/davidsmithwj/MSR-UNet (DOI: 10.5281/zenodo.13969855).
- Open Access
- 27 November 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (23) , 12712
Transformer-Based Visual Object Tracking with Global Feature Enhancement
With the rise of general models, transformers have been adopted in visual object tracking algorithms as feature fusion networks. In these trackers, self-attention is used for global feature enhancement. Cross-attention is applied to fuse the features of the template and the search regions to capture the global information of the object. However, studies have found that the feature information fused by cross-attention does not pay enough attention to the object region. In order to enhance cross-attention for the object region, an enhanced cross-attention (ECA) module is proposed for global feature enhancement. By calculating the average attention score for each position in the fused feature sequence and assigning higher weights to the positions with higher attention scores, the proposed ECA module can improve the feature information in the object region and further enhance the matching accuracy. In addition, to reduce the computational complexity of self-attention, orthogonal random features are introduced to implement a fast attention operation. This decomposes the attention matrix into the product of a random non-linear function between the original query and key. This module can reduce the spatial complexity and improve the inference speed by avoiding the explicit construction of a quadratic attention matrix. Finally, a tracking method named GFETrack is proposed, which comprises a Siamese backbone network and an enhanced attention mechanism. Experimental results show that the proposed GFETrack achieves competitive results on four challenging datasets.
- 27 November 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (23) , 12712
Open AccessTransformer-Based Visual Object Tracking with Global Feature Enhancement
With the rise of general models, transformers have been adopted in visual object tracking algorithms as feature fusion networks. In these trackers, self-attention is used for global feature enhancement. Cross-attention is applied to fuse the features of the template and the search regions to capture the global information of the object. However, studies have found that the feature information fused by cross-attention does not pay enough attention to the object region. In order to enhance cross-attention for the object region, an enhanced cross-attention (ECA) module is proposed for global feature enhancement. By calculating the average attention score for each position in the fused feature sequence and assigning higher weights to the positions with higher attention scores, the proposed ECA module can improve the feature information in the object region and further enhance the matching accuracy. In addition, to reduce the computational complexity of self-attention, orthogonal random features are introduced to implement a fast attention operation. This decomposes the attention matrix into the product of a random non-linear function between the original query and key. This module can reduce the spatial complexity and improve the inference speed by avoiding the explicit construction of a quadratic attention matrix. Finally, a tracking method named GFETrack is proposed, which comprises a Siamese backbone network and an enhanced attention mechanism. Experimental results show that the proposed GFETrack achieves competitive results on four challenging datasets.