Sung Wook Baik
Papers
4
Total Citations
57
H-Index
3
About
Sung Wook Baik is a leading researcher at the intersection of computer vision, robotics, and industrial automation, with a particular focus on enabling intelligent systems to operate reliably in challenging, low-visibility environments. His most impactful work centers on action recognition in darkness, where he has pioneered novel deep learning architectures that fuse contextual visual and motion-salient features. His 2024 paper on the "Darkness-Adaptive Action Recognition" framework, which leverages an efficient Tubelet Slow-Fast Network, has already garnered 28 citations, demonstrating its immediate relevance to fields like nighttime security, autonomous driving, and robotics. Complementing this, his "Contextual visual and motion salient fusion framework" (20 citations) further advances robust activity detection under poor illumination. Beyond darkness-adaptive vision, Baik has made foundational contributions to mobile robot localization, notably developing a robust method using ceiling landmarks (2007, 6 citations), and to scalable 3D perception for robot navigation via cloud computing and GPU acceleration (2012, 3 citations). His work bridges the gap between theoretical computer vision and practical, real-time industrial applications, establishing him as a key innovator in creating perceptually intelligent systems for the most demanding operational conditions.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4