Lirui Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Lirui Chen has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Baohua Qiang
Guangxi Key Laboratory of Image and Graphic Intelligent Processing, Guilin University of Electronic Technology, Guilin, China
4 shared publications - Ruidong Chen
Guangxi Key Laboratory of Image and Graphic Intelligent Processing, Guilin University of Electronic Technology, Guilin, China
4 shared publications - Shihao Zhang
Guangxi Key Laboratory of Image and Graphic Intelligent Processing, Guilin University of Electronic Technology, Guilin, China
3 shared publications - Xianyi Yang
Guangxi Key Laboratory of Image and Graphic Intelligent Processing, Guilin University of Electronic Technology, Guilin, China
3 shared publications - Yuan Xie
Guangxi Key Laboratory of Image and Graphic Intelligent Processing, Guilin University of Electronic Technology, Guilin, China
2 shared publications - Mingliang Zhou
School of Computer Science, Chongqing University, Chongqing, China
1 shared publication
Latest Publications
- 7 January 2026
- Published by Springer Nature in Journal of Intelligent Information Systems
- Vol. 64 (2) , 715-734
Cross-modal quaternion relation mining and gap bridging for image-text retrieval
- 7 January 2026
- Published by Springer Nature in Journal of Intelligent Information Systems
- Vol. 64 (2) , 715-734
Cross-modal quaternion relation mining and gap bridging for image-text retrieval
- 7 May 2025
- Published by Springer Nature in Applied Intelligence
- Vol. 55 (10) , 1-15
Linear self-attention with multi-relational graph for knowledge graph completion
- 7 May 2025
- Published by Springer Nature in Applied Intelligence
- Vol. 55 (10) , 1-15
Linear self-attention with multi-relational graph for knowledge graph completion
- 13 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 23 (22) , 27709-27719
Efficient Pose Estimation via a Lightweight Single-Branch Pose Distillation Network
Accurate lightweight pose estimation is still a difficult challenging task influenced by different human poses and various complex backgrounds in 2D human images. To address the above problems, we propose a Lightweight Single-branch Pose Distillation network, termed LSPD, which is a lightweight powerful fully convolutional pose network that can be executed quickly with a low computational cost for accurate pose estimation. First, we introduced an efficient end-to-end pose distillation sequence framework, which utilizes a small number of lightweight and strong pose estimation stages to effectively transfer the pose knowledge of our teacher model. Second, we constructed a compact and strong pose estimation stage that uses a type of lightweight multi-scale residual block to enhance the image features and the image-dependent spatial features representation ability of the model. At the same time, it reduces the computational cost. Finally, when training is complete, we used the backbone network and the first student stage as the simple architecture to deploy. Extensive experiments demonstrated that the proposed method obtains excellent performance with high accuracy and low model parameters.
- 13 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 23 (22) , 27709-27719
Efficient Pose Estimation via a Lightweight Single-Branch Pose Distillation Network
Accurate lightweight pose estimation is still a difficult challenging task influenced by different human poses and various complex backgrounds in 2D human images. To address the above problems, we propose a Lightweight Single-branch Pose Distillation network, termed LSPD, which is a lightweight powerful fully convolutional pose network that can be executed quickly with a low computational cost for accurate pose estimation. First, we introduced an efficient end-to-end pose distillation sequence framework, which utilizes a small number of lightweight and strong pose estimation stages to effectively transfer the pose knowledge of our teacher model. Second, we constructed a compact and strong pose estimation stage that uses a type of lightweight multi-scale residual block to enhance the image features and the image-dependent spatial features representation ability of the model. At the same time, it reduces the computational cost. Finally, when training is complete, we used the backbone network and the first student stage as the simple architecture to deploy. Extensive experiments demonstrated that the proposed method obtains excellent performance with high accuracy and low model parameters.
- Open Access
- 8 June 2023
- Published by MDPI AG in Electronics
- Vol. 12 (12) , 2593
Human Pose Estimation via an Ultra-Lightweight Pose Distillation Network
Most current pose estimation methods have a high resource cost that makes them unusable in some resource-limited devices. To address this problem, we propose an ultra-lightweight end-to-end pose distillation network, which applies some helpful techniques to suitably balance the number of parameters and predictive accuracy. First, we designed a lightweight one-stage pose estimation network, which learns from an increasingly refined sequential expert network in an online knowledge distillation manner. Then, we constructed an ultra-lightweight re-parameterized pose estimation subnetwork that uses a multi-module design with weight sharing to improve the multi-scale image feature acquisition capability of the single-module design. When training was complete, we used the first re-parameterized module as the deployment network to retain the simple architecture. Finally, extensive experimental results demonstrated the detection precision and low parameters of our method.
- 8 June 2023
- Published by MDPI AG in Electronics
- Vol. 12 (12) , 2593
Open AccessHuman Pose Estimation via an Ultra-Lightweight Pose Distillation Network
Most current pose estimation methods have a high resource cost that makes them unusable in some resource-limited devices. To address this problem, we propose an ultra-lightweight end-to-end pose distillation network, which applies some helpful techniques to suitably balance the number of parameters and predictive accuracy. First, we designed a lightweight one-stage pose estimation network, which learns from an increasingly refined sequential expert network in an online knowledge distillation manner. Then, we constructed an ultra-lightweight re-parameterized pose estimation subnetwork that uses a multi-module design with weight sharing to improve the multi-scale image feature acquisition capability of the single-module design. When training was complete, we used the first re-parameterized module as the deployment network to retain the simple architecture. Finally, extensive experimental results demonstrated the detection precision and low parameters of our method.