Anyang, South Korea

Geon Woo Baek

This inventor holds 1 USPTO granted patent. Top assignee: Ajou University Industry-Academic Cooperation Foundation. Active years: 2026.

IDiyas Innovation Intelligence. (2026). Inventor Profile: Geon Woo Baek. Retrieved from https://idiyas.com/inventor/geon-woo-baek

Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile

Calculating rank

Average Co-Inventor Count = 1.0

ph-index = 1


Company Filing History:


Years Active: 2026

Loading Chart...
1 patent (USPTO):Explore Patents

Title: Geon Woo Baek: Inventor in 3D Object Detection

Introduction

Geon Woo Baek is an inventor based in Anyang, South Korea. His patent work concerns reducing the computational weight of 3D object detection models through knowledge distillation.

Latest Patents

Baek is associated with 1 patent: “Electronic Apparatus for Weight Reduction of 3D Object Detection Model Based on Knowledge Distillation and Weight Reduction Method Thereof.” The invention describes an electronic apparatus that trains a student network to align its feature map with a teacher network’s feature map using input point-cloud data. It also applies relation-aware self-attention to information from multiple detection heads, using knowledge distillation to support a lighter 3D object detection model.

Career Highlights

Baek is associated with the Ajou University Industry-Academic Cooperation Foundation. His patent highlights an approach to making 3D object detection models more efficient while retaining useful detection information.

Collaborations

The provided information lists Hyeon Cho and Won Jun Hwang as Baek’s coworkers.

Conclusion

Geon Woo Baek’s patent focuses on knowledge distillation and relation-aware self-attention as methods for reducing the weight of 3D object detection models.

Profile summary based on public USPTO records.
Data Sources: USPTO Patent Grant XML, Patent Center, EPO & CIPO • Normalized by IDiyas Innovation Graph. Methodology & provenance architecturePlease report any incorrect information to [email protected]
Loading…