Dingkang Li

National University of Defense Technology

Papers

Total Citations

H-Index

About

Dingkang Li is a rising researcher in the field of computer vision and marine engineering, with a primary focus on underwater target detection and lightweight neural network design. His most notable contribution is the development of YOLOv11-MSE, a multi-scale dilated attention-enhanced lightweight network that addresses critical challenges in real-time underwater object detection. This work tackles persistent issues such as optical attenuation, scattering, and the detection of densely distributed small targets in complex underwater environments—problems that have long hindered marine resource management and ecological protection efforts. Although early in his career, Li’s research has already garnered attention, with his flagship paper accumulating 4 citations shortly after publication in 2025. His approach combines architectural innovations in attention mechanisms with practical efficiency, making deep learning models more deployable in resource-constrained underwater systems. Li’s work represents a meaningful step toward bridging the gap between state-of-the-art computer vision algorithms and the harsh realities of underwater sensing, positioning him as a promising contributor to both applied marine science and efficient deep learning design.