Jingwei Xue

Papers

Total Citations

H-Index

About

Dr. Jingwei Xue is a researcher at the forefront of applying deep learning to real-world robotic perception and environmental monitoring. Her primary research areas include computer vision, object detection, and autonomous systems, with a specific focus on deploying lightweight, efficient models for practical challenges. Dr. Xue’s most notable contribution is her work on garbage detection using the YOLOv3 architecture, presented in her highly cited 2020 paper, "Garbage Detection Using YOLOv3 in Nakanoshima Challenge." This study tackled the critical problem of automating waste collection in public spaces, demonstrating how deep learning object detectors can be adapted for robotic demonstration experiments. Her paper, which has garnered 7 citations, highlights a key bottleneck in the field: the labor-intensive nature of creating annotated training data. By addressing this issue, Dr. Xue’s work has helped pave the way for more scalable and autonomous environmental cleanup systems. Her research not only advances the practical application of AI in robotics but also underscores the importance of efficient data creation, making her a valuable contributor to the intersection of machine learning and sustainable technology.