Xingfan Yang
Papers
2
Total Citations
61
H-Index
2
About
Xingfan Yang is a leading researcher in marine computer vision, specializing in deep learning methods for underwater image analysis and object detection. His major contributions center on overcoming the unique challenges of marine environments—such as image noise, complex backgrounds, and class imbalances in datasets. In his highly cited 2024 work, Yang introduced a YOLO-based marine organism detection framework that integrates a two-terminal attention mechanism and difficult-sample resampling, achieving robust detection in noisy, imbalanced underwater imagery (44 citations). His earlier 2022 research pioneered a hybrid approach combining convolutional neural networks with optimized extreme learning machines for underwater image classification, effectively filtering noise and improving target recognition accuracy in complex scenes (17 citations). Yang’s work directly addresses critical bottlenecks in automated marine monitoring, enabling more reliable species identification and ecosystem surveillance. His innovative fusion of attention mechanisms and resampling strategies has set a new standard for object detection in challenging aquatic environments, making his research highly influential among engineers and ecologists working on autonomous underwater systems and marine conservation.
Research Focus
Key Achievements
Top Papers
- 1
- 2