Youngwook Paul Kwon
Papers
1
Total Citations
2
H-Index
1
About
Youngwook Paul Kwon is a computer vision researcher specializing in efficient deep learning architectures for real-time semantic segmentation, with a focus on model deployability across heterogeneous hardware—from edge devices to high-performance GPUs. His most-cited work, “A lightweight real-time semantic segmentation model deployable from Edge to GPU” (2025), introduces a novel architecture that balances accuracy and computational efficiency, enabling practical deployment in resource-constrained environments such as autonomous systems and mobile robotics. This contribution addresses a critical bottleneck in edge AI, where real-time scene understanding must operate under strict latency and memory limits. With 2 citations in its early publication stage, the paper signals growing interest in Kwon’s approach to bridging the gap between model performance and hardware adaptability. His research advances the field by prioritizing scalability and real-world applicability, making deep learning more accessible for embedded vision tasks. Kwon’s work is particularly relevant for students and engineers developing efficient AI solutions for autonomous navigation, augmented reality, and smart surveillance systems.
Research Focus
Key Achievements
Top Papers
- 1