Jinsheng Deng

National University of Defense Technology

Papers

Total Citations

H-Index

About

Jinsheng Deng is a researcher at the National University of Defense Technology, China, whose work focuses on computer vision, particularly image deblurring and object detection in challenging real-world environments. His major contributions include pioneering a joint generative approach to image deblurring that leverages edge attention priors and dynamic kernel selection, addressing the complex mixed blurring types—such as motion blur—common in industrial applications like aviation photo restoration, robotics, and autonomous vehicles. This work has garnered 5 citations, highlighting its relevance to practical vision systems. Deng also co-developed Rotated YOLOv4, an advanced object detector enhanced with attention mechanisms specifically designed for aerial imagery, which has received 2 citations and demonstrates his expertise in adapting deep learning models for remote sensing tasks. By tackling both low-level image restoration and high-level recognition, Deng’s research bridges critical gaps in real-world vision, offering robust solutions for autonomous systems. His achievements reflect a commitment to improving visual perception under non-ideal conditions, making his work valuable for students and researchers advancing computer vision in robotics, surveillance, and autonomous navigation.