A5050273648- Human Pose and Action Recognition
- Video Surveillance and Tracking Methods
- Hand Gesture Recognition Systems
- Facial Nerve Paralysis Treatment and Research
- Cerebrovascular and Carotid Artery Diseases
- Human Motion and Animation
- Anomaly Detection Techniques and Applications
- Non-Invasive Vital Sign Monitoring
- Concrete Corrosion and Durability
- Advanced X-ray and CT Imaging
- Structural Health Monitoring Techniques
- Face recognition and analysis
- Biometric Identification and Security
- Infrastructure Maintenance and Monitoring
- Advanced MRI Techniques and Applications
- ECG Monitoring and Analysis
- EEG and Brain-Computer Interfaces
South China University of Technology
2025
Zhejiang University
2024
Anhui University
2023-2024
Hefei Institutes of Physical Science
2023-2024
Chinese Academy of Sciences
2024
Chongqing Jiaotong University
2021
The automatic classification of electrocardiograms (ECGs) plays a crucial role in the early diagnosis cardiovascular diseases. In recent research, deep neural network (DNN)-based methods have garnered significant attention due to their exceptional feature extraction capabilities. However, these face challenges dealing with complex inter- and intra-class dependencies inherent different arrhythmias. We propose model for based on Graph Convolutional Neural Network (EGCNet) address this. our...
Abstract Structural damage identification has been the focus of engineering fields, while existing methods heavily depend on extracted “hand-crafted” features. Recently, due to powerful feature learning capability deep learning, it widely used in structural identification. However, those only consider local dependence or temporal relation data. Thus, this paper, a method by combining convolutional neural network (CNN) and gated recurrent unit (GRU) is proposed. The CNN model extract data,...
Abstract With the exponential growth of video data, action recognition has become an increasingly important area study. Despite various advancements, achieving a balance between detection accuracy and lightness remains formidable challenge, primarily due to complexity existing models. To address this issue, DenseGCN is developed, lightweight network designed optimize efficiency. The aim was create model that high while remaining for real‐world applications. operates via unique three‐level...
In environments where RGB images are inadequate, pressure maps is a viable alternative, garnering scholarly attention. This study introduces novel self-supervised map keypoint detection (SPMKD) method, addressing the current gap in specialized designs for human extraction from maps. Central to our contribution Encoder-Fuser-Decoder (EFD) model, which robust framework that integrates lightweight encoder precise detection, fuser efficient gradient propagation, and decoder transforms keypoints...
In environments where RGB images are inadequate, pressure maps is a viable alternative, garnering scholarly attention. This study introduces novel self-supervised map keypoint detection (SPMKD) method, addressing the current gap in specialized designs for human extraction from maps. Central to our contribution Encoder-Fuser-Decoder (EFD) model, which robust framework that integrates lightweight encoder precise detection, fuser efficient gradient propagation, and decoder transforms keypoints...