Long Peng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Long Peng has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
- Yang Cao
University of Science and Technology of China, Hefei, China
3 shared publications - Aiwen Jiang
School of Artificial Intelligence, Jiang Xi Normal University, NanChang, China
2 shared publications - Yang Wang
University of Science and Technology of China
2 shared publications - Yuejin Sun
School of Information Science and Technology, University of Science and Technology of China, Hefei, China
2 shared publications - Anran Wu
University of Science and Technology of China, Hefei, China
1 shared publication Bo Liu
1 shared publication
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8829-8838
GS-STVSR: Ultra-Efficient Continuous Spatio-Temporal Video Super-Resolution via 2D Gaussian Splatting
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 8829-8838
Open AccessGS-STVSR: Ultra-Efficient Continuous Spatio-Temporal Video Super-Resolution via 2D Gaussian Splatting
- 27 April 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (5)
Efficient Real-World Image Super-Resolution Via Adaptive Directional Gradient Convolution
- 27 April 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (5)
Efficient Real-World Image Super-Resolution Via Adaptive Directional Gradient Convolution
- 11 May 2025
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 155
Textual prompt guided image restoration
- 11 May 2025
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 155
Textual prompt guided image restoration
- 15 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 6424-6436
Lightweight Adaptive Feature De-Drifting for Compressed Image Classification
JPEG is a widely used compression scheme to efficiently reduce the volume of the transmitted images at the expense of visual perception drop. The artifacts appear among blocks due to the information loss in the compression process, which not only affects the quality of images but also harms the subsequent high-level tasks in terms of feature drifting. High-level vision models trained on high-quality images will suffer performance degradation when dealing with compressed images, especially on mobile devices. In recent years, numerous learning-based JPEG artifacts removal methods have been proposed to handle visual artifacts. However, it is not an ideal choice to use these JPEG artifacts removal methods as a pre-processing for compressed image classification for the following reasons: 1) These methods are designed for human vision rather than high-level vision models. 2) These methods are not efficient enough to serve as a pre-processing on resource-constrained devices. To address these issues, this paper proposes a novel lightweight adaptive feature de-drifting module (AFD-Module) to boost the performance of pre-trained image classification models when facing compressed images. First, a Feature Drifting Estimation Network (FDE-Net) is devised to generate the spatial-wise Feature Drifting Map (FDM) in the DCT domain. Next, the estimated FDM is transmitted to the Feature Enhancement Network (FE-Net) to generate the mapping relationship between degraded features and corresponding high-quality features. Specially, a simple but effective RepConv block equipped with structural re-parameterization is utilized in FE-Net, which enriches feature representation in the training phase while keeping efficiency in the deployment phase. After training on limited compressed images, the AFD-Module can serve as a “plug-and-play” module for pre-trained classification models to improve their performance on compressed images. Experiments on images compressed once ( i.e. ImageNet-C) and multiple times demonstrate that our proposed AFD-Module can comprehensively improve the accuracy of the pre-trained classification models and significantly outperform the existing methods.
- 15 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 6424-6436
Lightweight Adaptive Feature De-Drifting for Compressed Image Classification
JPEG is a widely used compression scheme to efficiently reduce the volume of the transmitted images at the expense of visual perception drop. The artifacts appear among blocks due to the information loss in the compression process, which not only affects the quality of images but also harms the subsequent high-level tasks in terms of feature drifting. High-level vision models trained on high-quality images will suffer performance degradation when dealing with compressed images, especially on mobile devices. In recent years, numerous learning-based JPEG artifacts removal methods have been proposed to handle visual artifacts. However, it is not an ideal choice to use these JPEG artifacts removal methods as a pre-processing for compressed image classification for the following reasons: 1) These methods are designed for human vision rather than high-level vision models. 2) These methods are not efficient enough to serve as a pre-processing on resource-constrained devices. To address these issues, this paper proposes a novel lightweight adaptive feature de-drifting module (AFD-Module) to boost the performance of pre-trained image classification models when facing compressed images. First, a Feature Drifting Estimation Network (FDE-Net) is devised to generate the spatial-wise Feature Drifting Map (FDM) in the DCT domain. Next, the estimated FDM is transmitted to the Feature Enhancement Network (FE-Net) to generate the mapping relationship between degraded features and corresponding high-quality features. Specially, a simple but effective RepConv block equipped with structural re-parameterization is utilized in FE-Net, which enriches feature representation in the training phase while keeping efficiency in the deployment phase. After training on limited compressed images, the AFD-Module can serve as a “plug-and-play” module for pre-trained classification models to improve their performance on compressed images. Experiments on images compressed once ( i.e. ImageNet-C) and multiple times demonstrate that our proposed AFD-Module can comprehensively improve the accuracy of the pre-trained classification models and significantly outperform the existing methods.
- 4 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 5 (6) , 3034-3045
Brightness Perceiving for Recursive Low-Light Image Enhancement
Due to the wide dynamic range in real low-light scenes, there will be large differences in the degree of contrast degradation and detail blurring of captured images, making it difficult for existing end-to-end methods to enhance low-light images to normal exposure. To address the above issue, we decompose low-light image enhancement into a recursive enhancement task and propose a brightness-perceiving-based recursive enhancement framework for high dynamic range low-light image enhancement. Specifically, our recursive enhancement framework consists of two parallel sub-networks: Adaptive Contrast and Texture enhancement network (ACT-Net) and Brightness Perception network (BP-Net). The ACT-Net is proposed to adaptively enhance image contrast and details under the guidance of the brightness adjustment branch and gradient adjustment branch, which are proposed to perceive the degradation degree of contrast and details in low-light images. To adaptively enhance images captured under different brightness levels, BP-Net is proposed to control the recursive enhancement times of ACT-Net by exploring the image brightness distribution properties. Finally, in order to coordinate ACT-Net and BP-Net, we design a novel unsupervised training strategy to facilitate the training procedure. To further validate the effectiveness of the proposed method, we construct a new dataset with a broader brightness distribution by mixing three low-light datasets. Compared with eleven existing representative methods, the proposed method achieves new SOTA performance on six reference and no reference metrics. Specifically, the proposed method improves the PSNR by 0.9 dB compared to the existing SOTA method.
- 4 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 5 (6) , 3034-3045
Brightness Perceiving for Recursive Low-Light Image Enhancement
Due to the wide dynamic range in real low-light scenes, there will be large differences in the degree of contrast degradation and detail blurring of captured images, making it difficult for existing end-to-end methods to enhance low-light images to normal exposure. To address the above issue, we decompose low-light image enhancement into a recursive enhancement task and propose a brightness-perceiving-based recursive enhancement framework for high dynamic range low-light image enhancement. Specifically, our recursive enhancement framework consists of two parallel sub-networks: Adaptive Contrast and Texture enhancement network (ACT-Net) and Brightness Perception network (BP-Net). The ACT-Net is proposed to adaptively enhance image contrast and details under the guidance of the brightness adjustment branch and gradient adjustment branch, which are proposed to perceive the degradation degree of contrast and details in low-light images. To adaptively enhance images captured under different brightness levels, BP-Net is proposed to control the recursive enhancement times of ACT-Net by exploring the image brightness distribution properties. Finally, in order to coordinate ACT-Net and BP-Net, we design a novel unsupervised training strategy to facilitate the training procedure. To further validate the effectiveness of the proposed method, we construct a new dataset with a broader brightness distribution by mixing three low-light datasets. Compared with eleven existing representative methods, the proposed method achieves new SOTA performance on six reference and no reference metrics. Specifically, the proposed method improves the PSNR by 0.9 dB compared to the existing SOTA method.
- 1 November 2021
- Published by Elsevier in Signal Processing: Image Communication
- Vol. 99
Ensemble single image deraining network via progressive structural boosting constraints
- 1 November 2021
- Published by Elsevier in Signal Processing: Image Communication
- Vol. 99
Ensemble single image deraining network via progressive structural boosting constraints
- 1 May 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 19489439,p. 5453-5458
Implementation of active training for an upper-limb rehabilitation robot based on impedance control
Many rehabilitation robots have been designed to alleviate the conflict between increasing number of post-stroke patients and shortage of therapists. Active training is the main feature of advanced rehabilitation robots, which has been proved to be more effective than simple passive movement training. This paper presents the implementation of active training on a 2-DOF upper-limb rehabilitation robot, which can assist the shoulder and elbow joint rehabilitation training of post-stroke patients. The controller is built based on impedance control, which can provide a compliant human-robot reaction. The implementation of active training is combined with a virtual reality game, and the average error between the actual and target reaction force is 1.41 ± 0.79 N in the X axis, and 1.22 ± 0.91 N in the Y axis.
- 1 May 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 19489439,p. 5453-5458
Implementation of active training for an upper-limb rehabilitation robot based on impedance control
Many rehabilitation robots have been designed to alleviate the conflict between increasing number of post-stroke patients and shortage of therapists. Active training is the main feature of advanced rehabilitation robots, which has been proved to be more effective than simple passive movement training. This paper presents the implementation of active training on a 2-DOF upper-limb rehabilitation robot, which can assist the shoulder and elbow joint rehabilitation training of post-stroke patients. The controller is built based on impedance control, which can provide a compliant human-robot reaction. The implementation of active training is combined with a virtual reality game, and the average error between the actual and target reaction force is 1.41 ± 0.79 N in the X axis, and 1.22 ± 0.91 N in the Y axis.