Sungjun Cho

Pohang University of Science and Technology

Papers

Total Citations

H-Index

About

Sungjun Cho is a leading researcher in real-time computer vision and embedded deep learning, best known for advancing the speed and efficiency of neural network-based object detection. His most-cited work, "Real-Time Object Detection System with Multi-Path Neural Networks" (2020, 58 citations), tackles the critical challenge of balancing high accuracy with the strict latency constraints required for autonomous vehicles, drones, and security robots. By introducing a multi-path architecture that dynamically routes data through specialized network branches, Cho demonstrated how to maintain detection precision while meeting real-time deadlines on resource-constrained hardware. This contribution has been instrumental in making DNN-based systems viable for safety-critical, edge-computing environments. Beyond this flagship paper, his research consistently explores the intersection of model optimization, hardware-aware design, and practical deployment—work that has earned him recognition as a key figure in bridging the gap between cutting-edge AI theory and real-world application. Cho’s output is essential reading for students and engineers seeking to understand how to build vision systems that are not only accurate, but also fast enough to save lives on the road or in the air.