Papers
2
Total Citations
8
H-Index
2
About
Seokjun Lee is a researcher at the forefront of enabling intelligent, real-time perception on resource-constrained platforms. His primary research areas span efficient deep learning, edge computing, and collective robotics. Lee’s most significant contribution is a domain-based transfer learning method for object detection, published in 2023, which allows deep learning models to achieve real-time performance on edge devices like drones and autonomous vehicles—a critical step for practical, low-latency AI deployment. This work has already garnered 6 citations, reflecting its immediate relevance to the growing field of edge AI. Earlier, Lee contributed to the development of a HARMS-based software system for collective robotics (2015), addressing the fundamental challenge of scalable, human-robot communication. This foundational work, while less cited, demonstrates his long-standing commitment to making robotic systems more ubiquitous and interactive. By bridging the gap between advanced computer vision and hardware limitations, Lee’s research is paving the way for smarter, more autonomous systems that can operate independently in the real world, making him a notable voice in the intersection of embedded systems and artificial intelligence.
Research Focus
Key Achievements
Top Papers
- 1
- 2