Jaehyeong Park

Papers

Total Citations

H-Index

About

Jaehyeong Park is a researcher advancing the frontiers of multi-modal perception and object detection, with a particular focus on cross-modal attention mechanisms. His most cited work, "CrossFormer: Cross-guided attention for multi-modal object detection" (2024), has garnered 58 citations, establishing him as a rising voice in the integration of diverse sensor data. Park’s core contribution lies in designing architectures that enable different data modalities—such as vision and depth—to guide each other’s attention, significantly improving detection accuracy in complex environments. This work addresses a critical challenge in autonomous systems and robotics, where robust perception requires seamless fusion of heterogeneous inputs. Beyond his technical innovations, Park’s research demonstrates high impact relative to its recent publication, signaling strong community interest and practical relevance. His achievements reflect a commitment to bridging gaps between modalities, making his work essential reading for students and researchers exploring multi-modal learning, attention-based models, and real-world perception systems. Park continues to push boundaries in how machines interpret and interact with their surroundings.