Xiaopeng Hu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xiaopeng Hu has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Fan Wang
School of Computer Science and Technology, Dalian University of Technology, Dalian 116024, China
8 shared publications - Xiang Gao
College of Computer Science and Technology, Dalian University of Technology, Dalian 116081, China
7 shared publications - Sining Wu
School of Computer Science and Technology, Dalian University of Technology, Dalian City, China
4 shared publications - Ying Zhou
Dalian University of Technology
4 shared publications - Xinrong Wu
College of Computer Science and Technology, Dalian University of Technology, Dalian 116081, China
3 shared publications - Fan Wang
School of Computer Science and Technology, Dalian University of Technology, Dalian, China
2 shared publications
Latest Publications
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 19, 27420-27434
MISA: M ultiframe I nfrared S patiotemporal A ggregation for Small Target Detection Under Imperfect Interframe Correspondence
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 19, 27420-27434
Open AccessMISA: M ultiframe I nfrared S patiotemporal A ggregation for Small Target Detection Under Imperfect Interframe Correspondence
- Open Access
IRWT-YOLO: A Background Subtraction-Based Method for Anti-Drone Detection
To effectively separate low-contrast weak drone objects from complex backgrounds, the IRWT-YOLO model is proposed, in which image segmentation algorithms are leveraged to reduce background interference. The model integrates object detection and image segmentation, with segmentation utilized to extract additional image information. Furthermore, to address the challenges of limited receptive fields and weak contextual communication in infrared weak object detection, the DCPPA and RCSCAA modules are introduced. The DCPPA module employs dual convolutions to expand the receptive field and enhance feature extraction for weak drone objects. The RCSCAA module incorporates a contextual attention mechanism to capture long-range dependencies and extract multi-scale texture features. Extensive experiments on three datasets demonstrate the superiority of IRWT-YOLO, with a precision improvement of 15.5% on the SIRSTv2 dataset, a recall improvement of 14.5% on the IRSTD-1k dataset, and a 21.0% improvement in on the 3rd Anti-UAV dataset compared to YOLOv8. These results highlight the model’s robustness and effectiveness in detecting weak objects under complex infrared conditions.Open AccessIRWT-YOLO: A Background Subtraction-Based Method for Anti-Drone Detection
To effectively separate low-contrast weak drone objects from complex backgrounds, the IRWT-YOLO model is proposed, in which image segmentation algorithms are leveraged to reduce background interference. The model integrates object detection and image segmentation, with segmentation utilized to extract additional image information. Furthermore, to address the challenges of limited receptive fields and weak contextual communication in infrared weak object detection, the DCPPA and RCSCAA modules are introduced. The DCPPA module employs dual convolutions to expand the receptive field and enhance feature extraction for weak drone objects. The RCSCAA module incorporates a contextual attention mechanism to capture long-range dependencies and extract multi-scale texture features. Extensive experiments on three datasets demonstrate the superiority of IRWT-YOLO, with a precision improvement of 15.5% on the SIRSTv2 dataset, a recall improvement of 14.5% on the IRSTD-1k dataset, and a 21.0% improvement in on the 3rd Anti-UAV dataset compared to YOLOv8. These results highlight the model’s robustness and effectiveness in detecting weak objects under complex infrared conditions. - 25 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Letters
- Vol. 9 (12) , 1-4
Fed-RAM: Federated Learning-Based Robust and Adaptive Method for Anomaly Detection in Industrial IoT Systems
Traditional machine learning (ML) approaches for anomaly detection rely on centralized data and struggle to manage the complexity, privacy, and scale of data generated by the industrial Internet of Things (IIoT). Recently, Federated learning (FL) offers a viable solution by enabling diverse IIoT devices and smart machines to collaboratively train high-quality ML models without transmitting sensitive data to ensure privacy and data security. However, the widespread adoption of FL in heterogeneous IIoT systems is primarily caused by model training inefficiencies, delays, and communication overhead, specifically for time-sensitive IIoT applications. With this focus, in this letter, an FL-based robust and adaptive method for anomaly detection, Fed-RAM, is proposed for edge-assisted IIoT. Specifically, we design adaptive mechanisms aiming to improve anomaly detection through an adaptive anomaly score technique based on the reconstruction error that enables local models to dynamically adjust the anomaly threshold according to the unique data distribution of individual edge devices. By incorporating adaptive mechanisms at each edge device, Fed-RAM ensures that only significant and critical updates are communicated to the server for aggregation. The experimental results obtained on two widely known datasets, i.e., MNIST and CIFAR-10, demonstrate that Fed-RAM reduces communication costs by approximately 50$\%$ and improves anomaly detection accuracy by 14$\%$ compared to baseline models.
- 25 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Letters
- Vol. 9 (12) , 1-4
Fed-RAM: Federated Learning-Based Robust and Adaptive Method for Anomaly Detection in Industrial IoT Systems
Traditional machine learning (ML) approaches for anomaly detection rely on centralized data and struggle to manage the complexity, privacy, and scale of data generated by the industrial Internet of Things (IIoT). Recently, Federated learning (FL) offers a viable solution by enabling diverse IIoT devices and smart machines to collaboratively train high-quality ML models without transmitting sensitive data to ensure privacy and data security. However, the widespread adoption of FL in heterogeneous IIoT systems is primarily caused by model training inefficiencies, delays, and communication overhead, specifically for time-sensitive IIoT applications. With this focus, in this letter, an FL-based robust and adaptive method for anomaly detection, Fed-RAM, is proposed for edge-assisted IIoT. Specifically, we design adaptive mechanisms aiming to improve anomaly detection through an adaptive anomaly score technique based on the reconstruction error that enables local models to dynamically adjust the anomaly threshold according to the unique data distribution of individual edge devices. By incorporating adaptive mechanisms at each edge device, Fed-RAM ensures that only significant and critical updates are communicated to the server for aggregation. The experimental results obtained on two widely known datasets, i.e., MNIST and CIFAR-10, demonstrate that Fed-RAM reduces communication costs by approximately 50$\%$ and improves anomaly detection accuracy by 14$\%$ compared to baseline models.
- 1 August 2024
- Published by Springer Nature in Multimedia Systems
- Vol. 30 (4) , 1-18
LCFormer: linear complexity transformer for efficient image super-resolution
- 1 August 2024
- Published by Springer Nature in Multimedia Systems
- Vol. 30 (4) , 1-18
LCFormer: linear complexity transformer for efficient image super-resolution
- 23 May 2024
- Published by Springer Nature in Machine Vision and Applications
- Vol. 35 (4) , 1-17
EEA-Net: edge-enhanced assistance network for infrared small target detection
- 23 May 2024
- Published by Springer Nature in Machine Vision and Applications
- Vol. 35 (4) , 1-17
EEA-Net: edge-enhanced assistance network for infrared small target detection
- 15 February 2024
- Published by Springer Nature in Multimedia Tools and Applications
- p. 1-25
Residual multi-branch distillation network for efficient image super-resolution
- 15 February 2024
- Published by Springer Nature in Multimedia Tools and Applications
- p. 1-25
Residual multi-branch distillation network for efficient image super-resolution
- 28 January 2024
- Published by Springer Nature
- p. 169-183
Differentiable Neural Architecture Search Based on Efficient Architecture for Lightweight Image Super-Resolution
- 28 January 2024
- Published by Springer Nature
- p. 169-183
Differentiable Neural Architecture Search Based on Efficient Architecture for Lightweight Image Super-Resolution
- 28 January 2024
- Published by Springer Nature
- p. 70-85
Non-Local Spatial-Wise and Global Channel-Wise Transformer for Efficient Image Super-Resolution
- 28 January 2024
- Published by Springer Nature
- p. 70-85
Non-Local Spatial-Wise and Global Channel-Wise Transformer for Efficient Image Super-Resolution
- 28 December 2023
- Published by Springer Nature in Neural Computing and Applications
- Vol. 36 (10) , 5285-5303
Lightweight image super-resolution via multi-branch aware CNN and efficient transformer
- 28 December 2023
- Published by Springer Nature in Neural Computing and Applications
- Vol. 36 (10) , 5285-5303
Lightweight image super-resolution via multi-branch aware CNN and efficient transformer
- 8 September 2022
- Published by Springer Nature in Multimedia Systems
- Vol. 29 (1) , 289-303
Multi-branch aware module with channel shuffle pixel-wise attention for lightweight image super-resolution
- 8 September 2022
- Published by Springer Nature in Multimedia Systems
- Vol. 29 (1) , 289-303
Multi-branch aware module with channel shuffle pixel-wise attention for lightweight image super-resolution