Yongli Ma
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
Yongli Ma has a total of 53 co-authors. Here are the top co-authors by number of shared publications:
Yanping Ma
School of Information Engineering, Wuhan University of Technology, Wuhan, Hubei, China
2 shared publications- Zhenrui Ji
School of Information Engineering, Wuhan University of Technology, Wuhan, Hubei, China
2 shared publications - Zude Zhou
School of Mechanical and Electronic Engineering, Wuhan University of Technology, Wuhan, China
2 shared publications - Andrew Yeh Ching Nee
Department of Mechanical Engineering, National University of Singapore, Singapore, Singapore
1 shared publication Baofu Han
School of Cyber Science and Engineering, Southeast University, Nanjing, China
1 shared publication- Bing Li
School of Cyber Science and Engineering, Southeast University, Nanjing, China
1 shared publication
Latest Publications
- 15 October 2026
- Published by Springer Nature in Pattern Analysis and Applications
- Vol. 29 (4) , 209
CCD-GFSOD: centroid calibration and dynamic constraint for generalized few-shot object detection
- 15 October 2026
- Published by Springer Nature in Pattern Analysis and Applications
- Vol. 29 (4) , 209
CCD-GFSOD: centroid calibration and dynamic constraint for generalized few-shot object detection
- Open Access
- 10 March 2026
- Published by Springer Nature in Cybersecurity
- Vol. 9 (1) , 41
A Scalable Group Authentication Protocol for IoT Based on PUF-Derived Bases in Inner Product Spaces
This paper presents a scalable group authentication and key agreement protocol for dynamic IoT environments that integrates Physical Unclonable Function (PUF)-derived device bases with inner product space projections. During registration, each device is assigned a private basis $${\mathcal {B}}_i$$ derived from its PUF responses, enabling efficient group authentication without per-device centralized verification and thereby mitigating long-term reliance on the group manager (GM). The protocol provides single-broadcast operations for member joining and leaving as well as decentralized group key updates. Formal security analysis under the Real-or-Random (ROR) model and experimental evaluation demonstrate robustness against common attacks, low communication overhead (6.5- $$-$$ 7.9 KB for 100 devices), and low authentication latency (1.135 ms for members and 0.051 ms for guests).- 10 March 2026
- Published by Springer Nature in Cybersecurity
- Vol. 9 (1) , 41
Open AccessA Scalable Group Authentication Protocol for IoT Based on PUF-Derived Bases in Inner Product Spaces
This paper presents a scalable group authentication and key agreement protocol for dynamic IoT environments that integrates Physical Unclonable Function (PUF)-derived device bases with inner product space projections. During registration, each device is assigned a private basis $${\mathcal {B}}_i$$ derived from its PUF responses, enabling efficient group authentication without per-device centralized verification and thereby mitigating long-term reliance on the group manager (GM). The protocol provides single-broadcast operations for member joining and leaving as well as decentralized group key updates. Formal security analysis under the Real-or-Random (ROR) model and experimental evaluation demonstrate robustness against common attacks, low communication overhead (6.5- $$-$$ 7.9 KB for 100 devices), and low authentication latency (1.135 ms for members and 0.051 ms for guests). - Open Access
- 3 March 2022
- Published by Institution of Engineering and Technology (IET) in IET Image Processing
- Vol. 16 (7) , 1897-1907
Single image dehazing using generative adversarial networks based on an attention mechanism
Most existing image dehazing methods rely on the solution of the atmospheric scattering model or supervised learning based on paired images. However, owing to incomplete prior knowledge and the lack of paired hazy and haze‐free images of the same scenes as training samples, their performances for single image dehazing are unsatisfactory. Here, the authors present an unpaired image learning method based on the attention mechanism for single image dehazing problems. The method uses the constraint transfer learning ability and circulatory structure of CycleGAN to carry out an unsupervised image dehazing task for unpaired data. Considering the complexity of the haze distribution in actual imaging and human visual characteristics, the improved channel attention and domain attention mechanisms are integrated into the network to process different features and different regions non‐uniformly. The experimental results show that the proposed method achieves good results on both synthetic datasets and real hazy images.
- 3 March 2022
- Published by Institution of Engineering and Technology (IET) in IET Image Processing
- Vol. 16 (7) , 1897-1907
Open AccessSingle image dehazing using generative adversarial networks based on an attention mechanism
Most existing image dehazing methods rely on the solution of the atmospheric scattering model or supervised learning based on paired images. However, owing to incomplete prior knowledge and the lack of paired hazy and haze‐free images of the same scenes as training samples, their performances for single image dehazing are unsatisfactory. Here, the authors present an unpaired image learning method based on the attention mechanism for single image dehazing problems. The method uses the constraint transfer learning ability and circulatory structure of CycleGAN to carry out an unsupervised image dehazing task for unpaired data. Considering the complexity of the haze distribution in actual imaging and human visual characteristics, the improved channel attention and domain attention mechanisms are integrated into the network to process different features and different regions non‐uniformly. The experimental results show that the proposed method achieves good results on both synthetic datasets and real hazy images.
- Open Access
- 11 October 2021
- Published by MDPI AG in Applied Sciences
- Vol. 11 (20) , 9416
Blind Image Separation Method Based on Cascade Generative Adversarial Networks
To solve the challenge of single-channel blind image separation (BIS) caused by unknown prior knowledge during the separation process, we propose a BIS method based on cascaded generative adversarial networks (GANs). To ensure that the proposed method can perform well in different scenarios and to address the problem of an insufficient number of training samples, a synthetic network is added to the separation network. This method is composed of two GANs: a U-shaped GAN (UGAN), which is used to learn image synthesis, and a pixel-to-attention GAN (PAGAN), which is used to learn image separation. The two networks jointly complete the task of image separation. UGAN uses the unpaired mixed image and the unmixed image to learn the mixing style, thereby generating an image with the “true” mixing characteristics which addresses the problem of an insufficient number of training samples for the PAGAN. A self-attention mechanism is added to the PAGAN to quickly extract important features from the image data. The experimental results show that the proposed method achieves good results on both synthetic image datasets and real remote sensing image datasets. Moreover, it can be used for image separation in different scenarios which lack prior knowledge and training samples.
- 11 October 2021
- Published by MDPI AG in Applied Sciences
- Vol. 11 (20) , 9416
Open AccessBlind Image Separation Method Based on Cascade Generative Adversarial Networks
To solve the challenge of single-channel blind image separation (BIS) caused by unknown prior knowledge during the separation process, we propose a BIS method based on cascaded generative adversarial networks (GANs). To ensure that the proposed method can perform well in different scenarios and to address the problem of an insufficient number of training samples, a synthetic network is added to the separation network. This method is composed of two GANs: a U-shaped GAN (UGAN), which is used to learn image synthesis, and a pixel-to-attention GAN (PAGAN), which is used to learn image separation. The two networks jointly complete the task of image separation. UGAN uses the unpaired mixed image and the unmixed image to learn the mixing style, thereby generating an image with the “true” mixing characteristics which addresses the problem of an insufficient number of training samples for the PAGAN. A self-attention mechanism is added to the PAGAN to quickly extract important features from the image data. The experimental results show that the proposed method achieves good results on both synthetic image datasets and real remote sensing image datasets. Moreover, it can be used for image separation in different scenarios which lack prior knowledge and training samples.