Seonyeong Heo

Pohang University of Science and Technology

Papers

Total Citations

H-Index

About

Seonyeong Heo is a leading researcher in real-time computer vision and embedded AI systems, with a primary focus on enabling high-accuracy object detection under strict latency constraints. His most-cited work, "Real-Time Object Detection System with Multi-Path Neural Networks" (2020, 58 citations), addresses a critical challenge in deploying deep neural networks for time-sensitive applications like autonomous vehicles, drones, and security robots. Heo’s key contribution lies in designing multi-path neural architectures that balance detection accuracy with computational efficiency, ensuring systems can process visual data within milliseconds without sacrificing reliability. This work has been instrumental in bridging the gap between state-of-the-art DNN performance and real-world deployment requirements. Beyond this flagship paper, Heo’s research continues to push the boundaries of efficient deep learning, exploring lightweight network designs and hardware-aware optimization. His impact is evident in the growing adoption of his methodologies in both academic benchmarks and industrial prototypes. For students and researchers, Heo’s work offers a compelling model of how to tackle the practical constraints of real-time AI—a vital skill as autonomous systems become increasingly pervasive.