Lei Tong

Papers

Total Citations

129

H-Index

About

Lei Tong is a researcher whose work sits at the dynamic intersection of deep learning, computer vision, and underwater imaging — a challenging domain that pushes the boundaries of conventional object detection methods. His most recognized contribution, "Underwater Object Detection using Invert Multi-Class Adaboost with Deep Learning" (2020), addresses critical limitations in applying standard deep learning frameworks to underwater environments, where objects are frequently small, blurry, and visually degraded by complex aquatic conditions. By innovatively combining Invert Multi-Class Adaboost with deep learning architectures, Tong and his collaborators developed a more robust detection pipeline capable of handling the unique difficulties posed by real-world underwater imagery. This work has garnered nearly 130 citations across its publications, reflecting its meaningful influence within the marine technology and computer vision communities. Tong's research demonstrates a clear commitment to bridging the gap between theoretical deep learning advances and practical, domain-specific applications — particularly in environments where reliable automated detection has significant implications for marine biology, underwater robotics, and ocean exploration. His contributions offer valuable methodological foundations for researchers tackling object recognition in visually complex, non-standard settings.