Hye‐Jung Yoon
Papers
1
Total Citations
2
H-Index
1
About
Hye-Jung Yoon is a leading researcher in computer vision and robotics, specializing in perception systems for logistics automation. Her work centers on developing advanced deep learning models for unseen object instance segmentation, a critical capability for robotic manipulation in cluttered environments like bin-picking and shelf-picking. Her most notable contribution, "DA-Fusion: Deformable Attention-Based RGB-D Fusion Transformer," introduces a novel transformer architecture that fuses RGB and depth data using deformable attention mechanisms. This approach significantly improves segmentation accuracy by robustly handling occlusions, varying object shapes, and complex spatial arrangements. Although recently published in 2025, this work has already garnered 2 citations, signaling its immediate impact on the field. Yoon's research addresses a key bottleneck in industrial automation—enabling robots to perceive and manipulate novel objects without prior training. Her innovative fusion of deformable attention with transformer models represents a major step forward in creating more adaptable and reliable robotic vision systems for real-world logistics applications.
Research Focus
Key Achievements
Top Papers
- 1