Hanjun Kim

Papers

Total Citations

H-Index

About

Hanjun Kim is a leading researcher at the intersection of computer vision, embedded AI, and industrial automation. His work focuses on enabling high-performance deep neural networks (DNNs) to operate reliably in real-time, resource-constrained environments—a critical challenge for autonomous vehicles, drones, and security robotics. Kim’s most influential contribution is his pioneering work on multi-path neural network architectures for real-time object detection, which has garnered 58 citations and established a foundational framework for balancing accuracy with stringent latency requirements. This research directly addresses the “speed-accuracy trade-off” that has long hindered the deployment of DNNs in safety-critical systems. Beyond vision, Kim has explored innovative approaches to predictive maintenance, applying neural networks to sound spectrogram images for machine anomaly detection. This cross-disciplinary work demonstrates his versatility in translating advanced AI techniques into practical industrial solutions. By bridging the gap between cutting-edge deep learning theory and real-world deployment, Hanjun Kim’s research continues to shape the future of intelligent, responsive autonomous systems.