Qinglin Liu
Papers
1
Total Citations
18
H-Index
1
About
Qinglin Liu is a leading researcher in computer vision and underwater image analysis, with a focus on weakly supervised object detection. His most-cited work, "Proposal-Refined Weakly Supervised Object Detection in Underwater Images" (2019, 18 citations), introduces a novel framework that leverages proposal refinement to overcome the challenge of limited labeled data in underwater environments. This contribution is pivotal for advancing autonomous underwater systems, enabling more accurate detection of marine objects without extensive manual annotation. Liu’s research bridges the gap between deep learning and real-world underwater applications, addressing issues like low visibility and complex backgrounds. His work has been recognized for its practical impact, with citations from fields ranging from marine biology to robotics. By refining weakly supervised methods, Liu has opened new pathways for scalable object detection in data-scarce domains, making his research a cornerstone for future studies in underwater vision and beyond.
Research Focus
Key Achievements
Top Papers
- 1Proposal-Refined Weakly Supervised Object Detection in Underwater Images18 citations · 2019