Yang Wang
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
Yang Wang has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Jiakai Zhou
College of Mechanical and Electrical Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing, China
4 shared publications Jiakai Zhou
3 shared publicationsWanlin Zhou
3 shared publicationsXiaoliang Wu
Duolun Technology Company Ltd., Nanjing, China
3 shared publicationsChao Dai
Academy of Medical Engineering and Translational Medicine, Tianjin University, Tianjin, China
2 shared publicationsChaolin Huang
School of Electrical Engineering and Automation, Jiangxi University of Science and Technology, Ganzhou, China
2 shared publications
Latest Publications
- 12 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 45 (5) , 2283-2294
CeLR: A Transformer-Based Regression Network for Accurate Cephalometric Landmark Detection in High-Resolution X-Ray Imaging
Reliable localization of cephalometric landmarks is essential for automated orthodontic analysis. Existing approaches are limited by high computational cost or complex multi-stage pipelines, hindering end-to-end optimization. In this work, we propose an end-to-end Transformer-based Cephalometric Landmark Regression network (CeLR) for high-resolution X-ray images. First, a feature extractor captures both low-level anatomical details and high-level semantic information. Then, a reference encoder models global dependencies and generates coarse landmark estimates. Next, a finetune decoder employs cross-attention mechanisms to refine these predictions. Additionally, a denoising module is introduced to enhance the robustness of the model. Experiments on multiple public cephalometric datasets demonstrate that CeLR achieves state-of-the-art performance. Specifically, on the ISBI 2015 Challenge Test1 dataset, CeLR achieves an Mean Radial Error (MRE) of 0.98 mm and a 2 mm Success Detection Rate (SDR) of 89.82%. Moreover, it maintains a computational cost of only 91.3 GFLOPs, demonstrating a satisfactory balance between accuracy and efficiency. These results highlight the effectiveness and clinical potential of the proposed method. Code is available at: https://github.com/huang229/D-CeLR.
- 12 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 45 (5) , 2283-2294
CeLR: A Transformer-Based Regression Network for Accurate Cephalometric Landmark Detection in High-Resolution X-Ray Imaging
Reliable localization of cephalometric landmarks is essential for automated orthodontic analysis. Existing approaches are limited by high computational cost or complex multi-stage pipelines, hindering end-to-end optimization. In this work, we propose an end-to-end Transformer-based Cephalometric Landmark Regression network (CeLR) for high-resolution X-ray images. First, a feature extractor captures both low-level anatomical details and high-level semantic information. Then, a reference encoder models global dependencies and generates coarse landmark estimates. Next, a finetune decoder employs cross-attention mechanisms to refine these predictions. Additionally, a denoising module is introduced to enhance the robustness of the model. Experiments on multiple public cephalometric datasets demonstrate that CeLR achieves state-of-the-art performance. Specifically, on the ISBI 2015 Challenge Test1 dataset, CeLR achieves an Mean Radial Error (MRE) of 0.98 mm and a 2 mm Success Detection Rate (SDR) of 89.82%. Moreover, it maintains a computational cost of only 91.3 GFLOPs, demonstrating a satisfactory balance between accuracy and efficiency. These results highlight the effectiveness and clinical potential of the proposed method. Code is available at: https://github.com/huang229/D-CeLR.
- 11 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 26 (2) , 2721-2733
ETR: Enhancing Taillight Recognition via Transformer-Based Video Classification
In autonomous driving, efficiently and accurately recognizing taillight states using dashcams is essential for interpreting other vehicles’ intentions. Recent video-based taillight recognition methods outperform earlier image-based approaches. However, they face challenges in efficiently integrating spatiotemporal information and managing high computational costs. In this paper, we introduce ETR, an accurate and efficient Transformer-based video classification model designed to enhance taillight recognition. Specifically, we first design a lightweight backbone to extract temporal and spatial features from videos and generate queries with prior information. Next, we develop a hierarchical progressive Transformer decoder that integrates feature maps from different levels of the backbone to enhance the model’s global information. Finally, we employ a classification head to predict the taillight state of the video. Additionally, we introduce a public dataset, ETR-Taillights, to address the current lack of open datasets for vehicle taillight recognition. The dataset contains 28,799 dashcam video clips, making it the largest public taillight recognition dataset. Experiments show that our method achieves a 91.69% F-measure on the ETR-Taillights dataset, surpassing the latest taillight recognition methods, VIF by 6.94% and CNN-LSTM by 10.82%. Additionally, it achieves an inference speed of 45.06 FPS, being 3.6 times faster than VIF. Furthermore, we conduct real-world road tests to demonstrate our method’s robustness and effectiveness in practical scenarios. Our model and dataset are available at https://github.com/yang590/ vehicle-taillight.
- 11 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 26 (2) , 2721-2733
ETR: Enhancing Taillight Recognition via Transformer-Based Video Classification
In autonomous driving, efficiently and accurately recognizing taillight states using dashcams is essential for interpreting other vehicles’ intentions. Recent video-based taillight recognition methods outperform earlier image-based approaches. However, they face challenges in efficiently integrating spatiotemporal information and managing high computational costs. In this paper, we introduce ETR, an accurate and efficient Transformer-based video classification model designed to enhance taillight recognition. Specifically, we first design a lightweight backbone to extract temporal and spatial features from videos and generate queries with prior information. Next, we develop a hierarchical progressive Transformer decoder that integrates feature maps from different levels of the backbone to enhance the model’s global information. Finally, we employ a classification head to predict the taillight state of the video. Additionally, we introduce a public dataset, ETR-Taillights, to address the current lack of open datasets for vehicle taillight recognition. The dataset contains 28,799 dashcam video clips, making it the largest public taillight recognition dataset. Experiments show that our method achieves a 91.69% F-measure on the ETR-Taillights dataset, surpassing the latest taillight recognition methods, VIF by 6.94% and CNN-LSTM by 10.82%. Additionally, it achieves an inference speed of 45.06 FPS, being 3.6 times faster than VIF. Furthermore, we conduct real-world road tests to demonstrate our method’s robustness and effectiveness in practical scenarios. Our model and dataset are available at https://github.com/yang590/ vehicle-taillight.
- 3 November 2024
- Published by Springer Nature
- p. 93-109
A Cephalometric Landmark Regression Method Based on Dual-Encoder for High-Resolution X-Ray Image
- 3 November 2024
- Published by Springer Nature
- p. 93-109
A Cephalometric Landmark Regression Method Based on Dual-Encoder for High-Resolution X-Ray Image
- 28 October 2024
- Published by Elsevier in Advanced Engineering Informatics
- Vol. 62
CWPR: An optimized transformer-based model for construction worker pose estimation on construction robots
- 28 October 2024
- Published by Elsevier in Advanced Engineering Informatics
- Vol. 62
CWPR: An optimized transformer-based model for construction worker pose estimation on construction robots
- 28 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 25 (12) , 19995-20005
TrVLR: A Transformer-Based Vehicle Light Recognition Method in Vehicle Inspection
Vehicle light inspection is a crucial aspect of vehicle inspection, as vehicle lights play a vital role in understanding vehicle behavior. Due to diverse ambient illumination, non-uniform vehicle light standards, and complex light states, existing vehicle light recognition methods perform poorly, especially in turn signals. To realize intelligent vehicle light inspection, an accurate and real-time intelligent vehicle light recognition method is urgently needed. To address this issue, we propose a Transformer-based vehicle light recognition method, TrVLR, which effectively models sequential information and global relationships of the vehicle light image sequence, resulting in precise recognition. Specifically, we first utilize a convolutional neural network (CNN) backbone to extract features from vehicle light area video. Then, we adopt a Transformer encoder to encapsulate the long sequential information of the entire video. Next, a Transformer decoder is used to contextualize each image throughout the video and output the classification information of each image. Finally, we predict the state of the lights in each image by feed-forward networks (FFNs). Experiments demonstrate that our method obtains state-of-the-art results in headlights, taillights, and turn signals with F-measures of 93.34%, 91.64%, and 88.17%, respectively. Notably, TrVLR surpasses CNN-LSTM by 7.01% in turn signal recognition. Our method has been successfully applied to intelligent vehicle light inspection, and the video demo is shown at https://www.youtube.com/watch?v $=$ p8E78Pwkcxo.
- 28 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 25 (12) , 19995-20005
TrVLR: A Transformer-Based Vehicle Light Recognition Method in Vehicle Inspection
Vehicle light inspection is a crucial aspect of vehicle inspection, as vehicle lights play a vital role in understanding vehicle behavior. Due to diverse ambient illumination, non-uniform vehicle light standards, and complex light states, existing vehicle light recognition methods perform poorly, especially in turn signals. To realize intelligent vehicle light inspection, an accurate and real-time intelligent vehicle light recognition method is urgently needed. To address this issue, we propose a Transformer-based vehicle light recognition method, TrVLR, which effectively models sequential information and global relationships of the vehicle light image sequence, resulting in precise recognition. Specifically, we first utilize a convolutional neural network (CNN) backbone to extract features from vehicle light area video. Then, we adopt a Transformer encoder to encapsulate the long sequential information of the entire video. Next, a Transformer decoder is used to contextualize each image throughout the video and output the classification information of each image. Finally, we predict the state of the lights in each image by feed-forward networks (FFNs). Experiments demonstrate that our method obtains state-of-the-art results in headlights, taillights, and turn signals with F-measures of 93.34%, 91.64%, and 88.17%, respectively. Notably, TrVLR surpasses CNN-LSTM by 7.01% in turn signal recognition. Our method has been successfully applied to intelligent vehicle light inspection, and the video demo is shown at https://www.youtube.com/watch?v $=$ p8E78Pwkcxo.
- Open Access
- 8 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 260-264
A Novel Annotation Method on RGB Images for Head Pose Estimation
Head pose estimation, a critical task in computer vision, involves predicting the head's Euler angles in an image. Recent advancements have seen CNN-based methods excel in this area, typically trained using RGB images with facial landmarks or depth data from RGBD cameras. In this paper, we introduce an innovative and user-friendly approach for annotating head poses' Euler angles in RGB images. This technique employs a 3D virtual human head model to replicate head poses in RGB images. By tracking the coordinate changes of the 3D virtual head, we can accurately determine the corresponding Euler angles in the image. Utilizing Unity 3D for implementation, we applied this method to annotate a standard RGB dataset with head pose Euler angles, resulting in the creation of a 2DHeadpose dataset. Our experimental results confirm the effectiveness of both our annotation approach and the datasets generated.
- 8 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 260-264
Open AccessA Novel Annotation Method on RGB Images for Head Pose Estimation
Head pose estimation, a critical task in computer vision, involves predicting the head's Euler angles in an image. Recent advancements have seen CNN-based methods excel in this area, typically trained using RGB images with facial landmarks or depth data from RGBD cameras. In this paper, we introduce an innovative and user-friendly approach for annotating head poses' Euler angles in RGB images. This technique employs a 3D virtual human head model to replicate head poses in RGB images. By tracking the coordinate changes of the 3D virtual head, we can accurately determine the corresponding Euler angles in the image. Utilizing Unity 3D for implementation, we applied this method to annotate a standard RGB dataset with head pose Euler angles, resulting in the creation of a 2DHeadpose dataset. Our experimental results confirm the effectiveness of both our annotation approach and the datasets generated.