Shih-Fu Chang

Papers

Total Citations

H-Index

About

Shih-Fu Chang is a pioneering researcher at the intersection of computer vision, robotics, and medical diagnostics. His work centers on real-time 3D pose estimation and automated interpretation of rapid diagnostic tests, addressing critical challenges in both robotics and healthcare. Chang’s major contribution includes developing a volumetric approach for pose estimation of deformable objects using low-cost depth sensors like Kinect, enabling robots to interact with flexible materials—a fundamental problem in robotics with applications in manufacturing and assistive technology. This work has garnered 69 citations, reflecting its foundational impact. More recently, Chang has advanced point-of-care diagnostics through few-shot learning, creating adaptable systems that automatically interpret lateral-flow assays (LFAs) for diseases like COVID-19. Despite its novelty, this 2021 paper has already earned 4 citations, signaling growing interest. His notable achievements include bridging computer vision and clinical practice, making diagnostic tools more scalable and accessible. Chang’s research empowers robots to perceive deformable objects and enables non-experts to reliably use rapid tests, demonstrating a commitment to practical, real-world impact. His interdisciplinary approach continues to inspire students and researchers in robotics, AI, and global health.