Hong Cheng
This is a likely match — the affiliation was inferred from OpenAlex, ORCID, and web sources but has not been fully confirmed. Treat with appropriate caution.
Researcher
Also affiliated: Changchun University of Science and Technology (2012); Hebei Agricultural University (2016); Anhui University (2023); Kwangwoon University (2018–2021); PLA Air Force Aviation University (2012)
Faculty Researcher
Research Areas
Biomedical Subjects
Links
Biography and Research Information
OverviewAI-generated summary
Hong Cheng's research interests lie at the intersection of computer vision, machine learning, and medical applications. His work includes developing advanced algorithms for object detection, particularly in challenging scenarios like camouflaged objects, utilizing techniques such as mutual graph learning and uncertainty-guided transformer reasoning. Cheng has also investigated the application of deep learning, including dilated convolution and attention mechanisms, for millimeter wave path loss modeling in 5G communications. His research extends to health sciences, with studies on the impact of exoskeleton-assisted walking on individuals with spinal cord injury, in vitro fluidic systems for applying shear stress on endothelial cells, and the development of nomogram models to predict postpartum stress urinary incontinence. Furthermore, he has explored machine learning for phase prediction in high entropy alloys.
Metrics
- h-index: 4
- Publications: 23
- Citations: 165
Selected Publications
-
CFCT: A Framework Using ConvNeXt With FPN, CBAM and A Topology Enhanced Loss Function for Skin Lesion Segmentation (2026)
-
Skin Lesion Segmentation Using Unet With A Topology Term in Loss Function (2025)
-
Multi-Class Label Detection and Bounding Box Regression Using Transformer with a Customized Loss Function (2024)
-
Object Localization Using Vision Transformer with a Loss Function Based on IOU and Mean Squared Error (2023)
-
A Topological Data Analysis-Based Approach to Object Localization: A Comparison with ViT and Yolov7 (2023)
Collaboration Network
Top Collaborators
- A Topological Data Analysis-Based Approach to Object Localization: A Comparison with ViT and Yolov7
- Object Localization Using Vision Transformer with a Loss Function Based on IOU and Mean Squared Error
- Multi-Class Label Detection and Bounding Box Regression Using Transformer with a Customized Loss Function
- Skin Lesion Segmentation Using Unet With A Topology Term in Loss Function
- CFCT: A Framework Using ConvNeXt With FPN, CBAM and A Topology Enhanced Loss Function for Skin Lesion Segmentation
Similar Researchers
Based on overlapping research topics