Linlin Tang

Papers

Total Citations

H-Index

About

Linlin Tang is a researcher specializing in computer vision and underwater image analysis, with a particular focus on small object detection in challenging marine environments. Her most notable contribution is the development of the Underwater Small Target Detection (USTD) network, a two-stage framework that addresses severe deformation, occlusion, and scenario diversity in underwater imagery. By integrating a Deformable Convolutional Pyramid, Tang’s work overcomes the limitations of general object detectors, achieving robust performance where conventional methods fail. This key paper, published in 2022, has already garnered 29 citations, underscoring its impact on advancing autonomous underwater systems and marine monitoring. Tang’s research is instrumental in enabling reliable detection of small, obscured targets—critical for applications in underwater robotics, environmental surveillance, and search operations. Her innovative approach to deformable convolutions and multi-scale feature extraction marks a significant step forward in adapting deep learning to complex, real-world underwater conditions, making her a rising contributor to the field of visual perception in extreme environments.