Seongju Lee
Papers
1
Total Citations
3
H-Index
1
About
Seongju Lee’s research lies at the intersection of computer vision and robotics, with a particular focus on enabling machines to interpret visual instructions for autonomous task planning. His most-cited work, “Object Detection for Understanding Assembly Instruction Using Context-aware Data Augmentation and Cascade Mask R-CNN” (2021), tackles the challenge of segmenting speech bubbles from 2D assembly diagrams—a critical step for robots to extract actionable information from human-readable guides. By combining context-aware data augmentation with the Cascade Mask R-CNN architecture, Lee’s approach improves the detection of key components in complex visual scenes, directly enhancing robotic comprehension of step-by-step assembly tasks. Though his citation count (3) is modest, this work addresses a niche yet vital gap in human-robot interaction: bridging the semantic divide between instructional imagery and robotic execution. Lee’s contributions underscore his commitment to practical, application-driven AI, where robust object detection serves as the foundation for more intuitive and autonomous robotic systems. His research holds promise for advancing smart manufacturing and assistive robotics, where understanding visual context is paramount.
Research Focus
Key Achievements
Top Papers
- 1