Papers
2
Total Citations
9
H-Index
2
About
Junxiong Liang is a researcher advancing the frontiers of 3D perception and efficient deep learning for autonomous systems. His primary research areas include 3D object detection, multi-modal sensor fusion (LiDAR-camera systems), and model optimization for real-world deployment. Liang’s most notable contribution is his work on "Leveraging Self-Paced Semi-Supervised Learning with Prior Knowledge for 3D Object Detection on a LiDAR-Camera System" (2023, 7 citations), where he tackles the critical challenge of data scarcity in deep learning-based 3D detection. By integrating prior knowledge with self-paced semi-supervised learning, his method reduces reliance on expensive labeled data while maintaining high detection accuracy—a breakthrough for mobile robotics and autonomous driving. Additionally, Liang has applied object detection models to pressing environmental issues, as seen in his study on YOLOv3-SPP model pruning for municipal solid waste classification (2022, 2 citations), demonstrating how efficient AI can aid sustainable resource management. His work bridges the gap between cutting-edge perception algorithms and practical, resource-constrained applications, making him a promising voice in the drive toward safer, smarter, and more sustainable autonomous technologies.
Research Focus
Key Achievements
Top Papers
- 1
- 2