Hai Qin

Papers

Total Citations

H-Index

About

Hai Qin is a researcher at the forefront of intelligent robotics and computer vision, with a focused expertise in automated waste sorting and robotic grasping. His work addresses the critical challenge of applying deep learning to real-world, data-scarce environments, particularly in the domain of kitchen waste management. Qin’s major contributions include the development of **Active Learning-DETR**, a cost-effective object detection framework that tackles the high annotation costs and complex visual variability of kitchen waste, achieving 13 citations. He further advanced the field with **MCS-ResNet**, a generative robot grasping network that innovatively fuses RGB and depth modalities to improve grasp detection accuracy, cited 9 times. Most recently, his **Efficient Generative Intelligent Multiobjective Grasping Model** (2025, 5 citations) overcomes data scarcity and algorithmic inefficiency to enable robust robotic sorting on conveyor belts. By integrating active learning, multi-modal fusion, and generative architectures, Qin’s work directly addresses the practical bottlenecks of deploying AI in automated sorting systems. His research not only pushes the boundaries of object detection and robotic manipulation but also offers scalable, efficient solutions for environmental sustainability and smart waste management.