Daekeun Kim
Papers
1
Total Citations
10
H-Index
1
About
Daekeun Kim is a researcher whose work lies at the intersection of computer vision, machine learning, and robotics, with a particular focus on enabling machines to perceive and interpret complex, real-world sensory data. His most cited paper, "Background subtraction using the factored 3-way restricted Boltzmann machines" (2018, 10 citations), introduces a novel approach for reconstructing 3D models from continuous, noisy, and high-dimensional sensory input. This work addresses a critical challenge in robotics: how to leverage vast real-world sensor data while overcoming the inherent noise and dimensionality that make traditional processing slow and unreliable. By employing factored 3-way restricted Boltzmann machines, Kim’s method improves the efficiency and accuracy of background subtraction—a fundamental task for dynamic scene understanding. His contributions are particularly valuable for autonomous systems that must operate in unstructured environments, where robust perception is key. Though his citation count is still growing, Kim’s research demonstrates a clear commitment to bridging the gap between raw sensor streams and actionable 3D representations, marking him as a promising voice in the fields of robotic perception and deep learning.
Research Focus
Key Achievements
Top Papers
- 1