JEONBUK NATIONAL UNIVERSITY · MACS LAB

Medical AI & Computational Science

Medical AI & Computational Science Laboratory at Jeonbuk National University

Medical AI · Multimodal Learning · Applied Research

Research areas →Our team →

JEONBUK NATIONAL UNIVERSITY · MACS LAB

Medical AI

We study diagnostic support and trustworthy AI using medical data and deep learning.

Diagnosis Support · Clinical Workflow · Trustworthy AI

Publications →

JEONBUK NATIONAL UNIVERSITY · MACS LAB

Vision-Language Intelligence

We develop multimodal AI that connects medical images, text, and clinical information.

Vision-Language · Multimodal Learning · Reasoning

Research topics →

LAB NEWS · 2026.10.15

Undergraduate First-Author Paper by Jun Ho Lee Accepted to WACV 2027

Research first-authored by undergraduate researcher Jun Ho Lee has been accepted to the WACV 2027 Main Conference (Application Track).

Read news →

LAB NEWS · 2026.09.22

Two Papers Accepted to ACCV 2026

We are pleased to announce that two papers from our laboratory have been accepted to the Asian Conference on Computer Vision 2026 (ACCV 2026), a Top BK/CS conference.

Read news →

LAB NEWS · 2026.06.18

ECCV2026 Accepted: Semantic Line Diffusion

We are pleased to announce that our paper, “Semantic Line Diffusion: Character-Consistent Line Art from Text-Annotated Storyboards,” has been accepted to the European …

Read news →

LAB NEWS · 2026.06.11

Two MICCAI 2026 Papers Accepted as Early Accepts

We are pleased to announce that two papers from MACS Lab have been accepted to Medical Image Computing and Computer Assisted Intervention 2026 (MICCAI 2026) as early …

Read news →

PUBLICATION · 2027

Learning When to Correct: Selective Calibration for Monocular Kinematics

This work learns when to retain a joint-angle estimate and when to apply a correction. It was first-authored by undergraduate researcher Jun Ho Lee.

WACV2027

View paper →

Overview figure for Learning When to Correct: Selective Calibration for Monocular Kinematics

PUBLICATION · 2026

Uncertainty-Aware Bayesian Prompt Adaptation of SAM2 for Few-Shot Cross-Modal Segmentation

Medical image segmentation is essential for clinical image analysis, supporting diagnosis, quantitative assessment, treatment planning, and follow-up evaluation. In …

ESWA

View paper →

Overview figure for Uncertainty-Aware Bayesian Prompt Adaptation of SAM2 for Few-Shot Cross-Modal Segmentation

PUBLICATION · 2026

Modality-Aware Spectral Alignment for Personalized Federated EEG–Gaze Learning

This work combines EEG and gaze for surgical performance prediction. Personalized federated learning handles individual differences while retaining raw signals at each …

IEEE SPL

View paper →

PUBLICATIONIEEE SPLIEEE Signal Processing Letters

PUBLICATION · 2026

SFXGraph: Causal-Compositional Graph Learning for Stylized Sound Effects in Webtoons

Lettering in webtoons mixes with artwork and varies in shape. This work represents content, deformation, style, and context as a graph for sound-effect recognition.

ACCV2026

View paper →