Jiun-Han Chen

National Taiwan University of Science and Technology

Papers

Total Citations

H-Index

About

Jiun-Han Chen is a rising researcher in computer vision and autonomous driving, whose work centers on advancing monocular 3D object detection—a critical technology for safe self-driving vehicles. His most cited paper, "Monocular 3D Object Detection Utilizing Auxiliary Learning With Deformable Convolution" (2023), introduces a novel framework that enhances detection robustness by integrating auxiliary learning tasks with deformable convolution layers. This approach addresses the inherent challenge of depth estimation from a single camera, improving both accuracy and efficiency in real-world driving scenarios. With 10 citations already in a short time, Chen’s work is gaining traction among peers focused on perception systems. His contribution lies in bridging the gap between theoretical model design and practical deployment, offering a solution that balances computational cost with detection performance. By tackling the safety-critical demands of autonomous driving, Chen’s research not only advances algorithmic capability but also supports the broader goal of reliable, real-time perception. His innovative use of deformable convolutions marks a meaningful step forward in monocular 3D detection, positioning him as a promising voice in the field.