Jeng-Lun Shieh
Papers
1
Total Citations
10
H-Index
1
About
Jeng-Lun Shieh is a researcher at the forefront of autonomous driving perception, specializing in monocular 3D object detection and deep learning for computer vision. His most cited work, “Monocular 3D Object Detection Utilizing Auxiliary Learning With Deformable Convolution” (2023, 10 citations), introduces a novel algorithm that enhances detection robustness and efficiency—critical for autonomous vehicle safety. By integrating deformable convolution with auxiliary learning, Shieh’s approach improves the model’s ability to handle geometric variations in 3D space, addressing a key challenge in single-camera depth estimation. This contribution is particularly notable for its practical impact on real-world driving systems, where reliable 3D detection is essential. Shieh’s research bridges the gap between algorithmic innovation and deployment, making him a promising voice in the field. His work has already garnered attention from both academic and industry communities, reflecting its relevance to advancing autonomous navigation. For students and researchers exploring efficient 3D perception, Shieh’s methods offer a compelling pathway toward safer, more capable self-driving technologies.
Research Focus
Key Achievements
Top Papers
- 1