About Me

I am currently an M.S. student at Jeonbuk National University, advised by Prof. Sang Jun Lee. My research interests include medical image analysis and remote photoplethysmography (rPPG), with a focus on deep learning-based analysis of biomedical and physiological data.

Recently, I have been working on non-contact stress estimation using rPPG, aiming to robustly extract physiological signals from camera-based videos and explore their practical and clinical applications. Previously, I conducted research on medical image analysis for dental and maxillofacial applications using panoramic X-ray images.

In the long term, I aim to expand my research toward rPPG estimation in egocentric-view settings, contributing to the development of non-contact physiological signal analysis technologies for wearable cameras and real-world daily environments.

PulsePath: Two-Stage Generative Waveform Refinement for Robust Remote Photoplethysmography Estimation

Sensors, 2026 (Under Review)

Juha Park, Seungmin Oh, Sang Jun Lee*

BEAT: Bottleneck-Enhanced Adaptive Temporal Learning for Heart Rate Estimation from Egocentric NIR Eye Videos

IEEE/CVF European Conference on Computer Vision Workshop on Wearable AI (ECCVW), 2026

Juha Park, Sang Jun Lee*

PRISSM: PRV-Guided SSM for Non-contact Stress Estimation

The 37th British Machine Vision Conference (BMVC), 2026

Juha Park, Jiho Choi, Sang Jun Lee*

[Code]

Weighted Knowledge Distillation for Semi-Supervised Segmentation of Maxillary Sinus in Panoramic X-ray Images

Scientific Reports, 2026

Juha Park, Jiho Choi, Jong Pil Yun, Yong Chan Park, Han-Gyeol Yeom, Byung-Do Lee*, Sang Jun Lee*

[Paper]

파노라마 X-ray 영상에서의 상악동 영역 세그멘테이션을 위한 어텐션 기반의 U-Net 트랜스포머

대한임베디드공학회논문지, 2025

박주하, 최지호, 윤종필, 염한결, 이병도*, 이상준*

[Paper]

골프장 주행환경 세그멘테이션을 위한 채널 어텐션 기반의 지식 증류 기법

제어로봇시스템학회논문지, 2025

양윤석, 최지호, 박주하, 이상준*

[Paper]