Papers
1
Total Citations
7
H-Index
1
About
Xing Hong is a researcher advancing the frontiers of autonomous perception, with a focus on 3D object detection for mobile robotics and self-driving systems. Their most-cited work, "Leveraging Self-Paced Semi-Supervised Learning with Prior Knowledge for 3D Object Detection on a LiDAR-Camera System" (2023, 7 citations), tackles a critical bottleneck in the field: the data-hungry nature of deep learning models. Hong introduced a novel semi-supervised framework that integrates prior knowledge with self-paced learning, enabling effective 3D detection using limited labeled data from LiDAR-camera systems. This approach not only reduces reliance on costly annotations but also enhances robustness in real-world scenarios. By addressing the challenge of fusing multimodal sensor data, Hong’s contributions support safer, more scalable autonomous navigation. Their work is particularly notable for bridging the gap between theoretical semi-supervised methods and practical deployment constraints, offering a pathway to more efficient perception pipelines. As the demand for reliable autonomous systems grows, Hong’s innovations in leveraging prior knowledge and self-paced learning stand out as a promising direction for reducing data dependencies while maintaining high detection accuracy.
Research Focus
Key Achievements
Top Papers
- 1