Publications

Our Research Achievements
  • All
  • International
  • Domestic
ECCV 2026
International Conference ECCV 2026

Different Changes Require Different Reasoning: Change-Type-Specialized Experts for Robust Change Captioning

Jiyoung Park, InJae Oh, Jung Uk Kim

European Conference on Computer Vision (ECCV), 2026

ECCV 2026
International Conference ECCV 2026

PersonaDrive: Controllable Trajectory Prediction with Multi-Dimensional Driving Personas

Chan Lee, Kimin Yun, Yuseok Bae, Seong Tae Kim, Jung Uk Kim

European Conference on Computer Vision (ECCV), 2026

ECCV 2026
International Conference ECCV 2026

Online Versatile Incremental Learning: Towards Class and Domain-Agnostic Adaptation at Any Time

Jae-Ho Lee, Jun-Yeong Moon, Min-Yeong Park, Jung Uk Kim, Gyeong-Moon Park

European Conference on Computer Vision (ECCV), 2026

TIP 2026
International Journal IEEE TIP 2026

Adverse Weather Removal via Dynamic Enhancement Diffusion with Weather-Adaptive Prompting

Youngmin Oh, Sungyoung Lee, MyeongAh Cho, Jung Uk Kim

IEEE Transactions on Image Processing (TIP, IF: 13.7), 2026

Generate, Analyze, and Refine: Training-Free Sound Source Localization via MLLM Meta-Reasoning
International Conference CVPR 2026

Generate, Analyze, and Refine: Training-Free Sound Source Localization via MLLM Meta-Reasoning

Subin Park, Jung Uk Kim

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

MonoSAOD: Monocular 3D Object Detection with Sparsely Annotated Label
International Conference CVPR 2026

MonoSAOD: Monocular 3D Object Detection with Sparsely Annotated Label

Junyoung Jung, Seokwon Kim, Jung Uk Kim

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

Highlight
Learning from Oblivion: Predicting Knowledge-Overflowed Weights via Retrodiction of Forgetting
International Conference CVPR 2026

Learning from Oblivion: Predicting Knowledge-Overflowed Weights via Retrodiction of Forgetting

Jinhyeok Jang, Jaehong Kim, Jung Uk Kim

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

From Adaptation to Generalization: Adaptive Visual Prompting for Medical Image Segmentation
International Conference CVPR Findings 2026

From Adaptation to Generalization: Adaptive Visual Prompting for Medical Image Segmentation

Evren Çetinkaya, Sangmin Lee, Jung Uk Kim, Hong Joo Lee, Nassir Navab

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Findings, 2026

Rationale-Guided Learning for Multimodal Emotion Recognition
International Conference ICASSP 2026

Rationale-Guided Learning for Multimodal Emotion Recognition

Sujung Oh, Jung Uk Kim, Sangmin Lee

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2026

Oral
See, Rank, and Filter: Important Word-Aware Clip Filtering via Scene Understanding for Moment Retrieval and Highlight Detection
International Conference AAAI 2026

See, Rank, and Filter: Important Word-Aware Clip Filtering via Scene Understanding for Moment Retrieval and Highlight Detection

YuEun Lee, Jung Uk Kim

AAAI Conference on Artificial Intelligence (AAAI), 2026

Leveraging Textual Compositional Reasoning for Robust Change Captioning
International Conference AAAI 2026

Leveraging Textual Compositional Reasoning for Robust Change Captioning

Kyu Ri Park, Jiyoung Park, Seong Tae Kim, Hong Joo Lee, Jung Uk Kim

AAAI Conference on Artificial Intelligence (AAAI), 2026

Task Prototype-Based Knowledge Retrieval for Multi-Task Learning from Partially Annotated Data
International Conference AAAI 2026

Task Prototype-Based Knowledge Retrieval for Multi-Task Learning from Partially Annotated Data

Youngmin Oh, Hyung-Il Kim, Jung Uk Kim

AAAI Conference on Artificial Intelligence (AAAI), 2026

Do We Need Perfect Data? Leveraging Noise for Domain Generalized Segmentation
International Conference AAAI 2026

Do We Need Perfect Data? Leveraging Noise for Domain Generalized Segmentation

Taeyeong Kim, SeungJoon Lee, Jung Uk Kim, MyeongAh Cho

AAAI Conference on Artificial Intelligence (AAAI), 2026

MedIA 2026
International Journal Medical Image Analysis 2026

Unsupervised Domain Adaptation for Medical Image Segmentation Using Adaptogen-Perturbation

Hong Joo Lee, Yuan Bi, Sangmin Lee, Gyeong-Moon Park, Jung Uk Kim, Seong Tae Kim, Zhongliang Jiang, Nassir Navab

Medical Image Analysis (IF: 11.8), 2026

Object-aware Sound Source Localization via Audio-Visual Scene Understanding
International Conference CVPR 2025

Object-aware Sound Source Localization via Audio-Visual Scene Understanding

Sung Jin Um, Dongjin Kim, Sangmin Lee, Jung Uk Kim

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025

Multispectral Pedestrian Detection with Sparsely Annotated Label
International Conference AAAI 2025

Multispectral Pedestrian Detection with Sparsely Annotated Label

Chan Lee, Seungho Shin, Gyeong-Moon Park, Jung Uk Kim

AAAI Conference on Artificial Intelligence (AAAI), 2025

Watch Video, Catch Keyword: Context-aware Keyword Attention for Moment Retrieval and Highlight Detection
International Conference AAAI 2025

Watch Video, Catch Keyword: Context-aware Keyword Attention for Moment Retrieval and Highlight Detection

Sung Jin Um, Dongjin Kim, Sangmin Lee, Jung Uk Kim

AAAI Conference on Artificial Intelligence (AAAI), 2025

SSMPD: Semi-Supervised Learning for Multispectral Pedestrian Detection
International Journal IEEE TMM 2025

SSMPD: Semi-Supervised Learning for Multispectral Pedestrian Detection

Seungho Shin, Chan Lee, Gyeong-Moon Park, Jung Uk Kim

IEEE Transactions on Multimedia (TMM, IF: 9.7), 2025

Enabling Visual Object Detection with Object Sounds via Visual Modality Recalling Memory
International Journal IEEE TNNLS 2025

Enabling Visual Object Detection with Object Sounds via Visual Modality Recalling Memory

Jung Uk Kim, Yong Man Ro

IEEE Transactions on Neural Networks and Learning Systems (TNNLS, IF: 8.9), 2025

Spatial Mask-based Adaptive Robust Training for Video Object Segmentation with Noisy Labels
International Journal IEEE TCSVT 2025

Spatial Mask-based Adaptive Robust Training for Video Object Segmentation with Noisy Labels

Enki Cho, Jung Uk Kim, Seong Tae Kim

IEEE Transactions on Circuits and Systems for Video Technology (TCSVT, IF: 11.1), 2025

ESA 2025
International Journal Expert Systems 2025

Unified Link Prediction Modeling for Enhanced Knowledge Graph Completion Task

Tri D.T. Nguyen, et al., Sung-Ho Bae, Jung Uk Kim, Seong Tae Kim, Sungyoung Lee

Expert Systems With Applications (IF: 7.5), 2025

Moment Retrieval and Highlight Detection Framework via Semantic Alignment of Phrases
Domestic Conference 2025

Moment Retrieval and Highlight Detection Framework via Semantic Alignment of Phrases

YuEun Lee, Suyong Choi, Jung Uk Kim

Korean Institute of Broadcast and Media Engineers (KIBME), 2025

Grounded VideoQA via Optimal Transport-based Fine-Grained
Domestic Conference 2025

Grounded VideoQA via Optimal Transport-based Fine-Grained

Soyeon Lee, YuEun Lee, Suyong Choi, Jung Uk Kim

Korean Institute of Broadcast and Media Engineers (KIBME), 2025

Vision Language Model Based Approach for Change Captioning
Domestic Conference 2025

Vision Language Model Based Approach for Change Captioning

Jiyoung Park, Jung Uk Kim

Korea Institute of Military Science and Technology (KIMST), 2025

Mixed Sound Source Localization via Audio-Visual Information Fusion
Domestic Journal 2025

Mixed Sound Source Localization via Audio-Visual Information Fusion

YuEun Lee, Sung Jin Um, Jung Uk Kim

Journal of KIISE, 2025

Video Moment Retrieval and Highlight Detection via Effective Fusion of Captions Generated by Vision-Language Models
Domestic Journal 2025

Video Moment Retrieval and Highlight Detection via Effective Fusion of Captions Generated by Vision-Language Models

YuEun Lee, Jung Uk Kim

Journal of Broadcast Engineering / KIBME, 2025

The Necessity of Training Strategies for Monocular 3D Object Detection under Adverse Weather Conditions
Domestic Conference 2025

The Necessity of Training Strategies for Monocular 3D Object Detection under Adverse Weather Conditions

Junyoung Jung, Seokwon Kim, Jung Uk Kim

Korean Institute of Broadcast and Media Engineers (KIBME), 2025

A Semi-Supervised Learning Framework for Rain-Robust Multispectral Pedestrian Detection with Limited Labels
Domestic Conference 2025

A Semi-Supervised Learning Framework for Rain-Robust Multispectral Pedestrian Detection with Limited Labels

Chan Lee, Seungho Shin, Jung Uk Kim

Korean Institute of Broadcast and Media Engineers (KIBME), 2025

Performance Evaluation and Analysis of Visual Information Removal in Dense Video Captioning
Domestic Conference 2025

Performance Evaluation and Analysis of Visual Information Removal in Dense Video Captioning

Soyeon Lee, Jung Uk Kim

Korean Institute of Broadcast and Media Engineers (KIBME), 2025

Siamese Network-Based Knowledge Distillation Method for Domain-Robust Visual Question Answering
Domestic Conference 2025

Siamese Network-Based Knowledge Distillation Method for Domain-Robust Visual Question Answering

InJae Oh, Jung Uk Kim

Korean Institute of Broadcast and Media Engineers (KIBME), 2025

Moment Retrieval and Highlight Detection via Keyword Extraction from Natural Language
Domestic Conference 2025

Moment Retrieval and Highlight Detection via Keyword Extraction from Natural Language

Suyong Choi, YuEun Lee, Jung Uk Kim

Korean Institute of Broadcast and Media Engineers (KIBME), 2025

A Real-time Free-Viewpoint Videos Streaming Model Robust to Fast-Moving Objects
Domestic Conference 2025

A Real-time Free-Viewpoint Videos Streaming Model Robust to Fast-Moving Objects

Kanghyun Lee, Jung Uk Kim

Korean Institute of Broadcast and Media Engineers (KIBME), 2025

Hierarchical Semantic Prompt Design for Robust Open-Vocabulary Object Detection
Domestic Journal 2025

Hierarchical Semantic Prompt Design for Robust Open-Vocabulary Object Detection

Suyong Choi, Jung Uk Kim

Journal of KIISE, 2025

Learning Trimodal Relation for Audio-Visual Question Answering with Missing Modality
International Conference ECCV 2024

Learning Trimodal Relation for Audio-Visual Question Answering with Missing Modality

Kyu Ri Park, Hong Joo Lee, Jung Uk Kim

European Conference on Computer Vision (ECCV), 2024

MonoWAD: Weather-Adaptive Diffusion Model for Robust Monocular 3D Object Detection
International Conference ECCV 2024

MonoWAD: Weather-Adaptive Diffusion Model for Robust Monocular 3D Object Detection

Youngmin Oh, Hyung-Il Kim, Seong Tae Kim, Jung Uk Kim

European Conference on Computer Vision (ECCV), 2024

Oral
Towards Model-Agnostic Dataset Condensation by Heterogeneous Models
International Conference ECCV 2024

Towards Model-Agnostic Dataset Condensation by Heterogeneous Models

Jun-Yeong Moon, Jung Uk Kim, Gyeong-Moon Park

European Conference on Computer Vision (ECCV), 2024

Learning to Visually Localize Sound Sources from Mixtures without Prior Source Knowledge
International Conference CVPR 2024

Learning to Visually Localize Sound Sources from Mixtures without Prior Source Knowledge

Dongjin Kim, Sung Jin Um, Sangmin Lee, Jung Uk Kim

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024

Enhancing Audio-Visual Question Answering with Missing Modality via Trans-Modal Associative Learning
International Conference ICASSP 2024

Enhancing Audio-Visual Question Answering with Missing Modality via Trans-Modal Associative Learning

Kyu Ri Park, Youngmin Oh, Jung Uk Kim

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024

Robust Airway Generation Labeling with Airway Segmentation for Reliable Airway Assessment
International Journal IEEE Access 2024

Robust Airway Generation Labeling with Airway Segmentation for Reliable Airway Assessment

Mincheol Song, Jin An, Kyu Ri Park, Jeongmi Lee, Jinkyeong Park, Jung Uk Kim

IEEE Access, 2024

Video Moment Retrieval and Highlight Detection Using Captions Generated by Multimodal Large Language Models
Domestic Conference 2024

Video Moment Retrieval and Highlight Detection Using Captions Generated by Multimodal Large Language Models

Dongjin Kim, Jung Uk Kim

Korea Software Congress (KSC), 2024

Study For Automatic Pedestrian Data Augmented Learning Technique For Robust Multispectral Pedestrian Detection
Domestic Conference 2024

Study For Automatic Pedestrian Data Augmented Learning Technique For Robust Multispectral Pedestrian Detection

Chan Lee, Seungho Shin, Jung Uk Kim

Korea Computer Congress (KCC), 2024

Robust Video Moment Retrieval and Highlight Detection with Using Large Vision-Language Model
Domestic Conference 2024

Robust Video Moment Retrieval and Highlight Detection with Using Large Vision-Language Model

Sung Jin Um, Jung Uk Kim

Korea Computer Congress (KCC), 2024

Robust 3D Object Detection Using 2D-Based Object Detection Information and Symmetry Knowledge
Domestic Journal 2024

Robust 3D Object Detection Using 2D-Based Object Detection Information and Symmetry Knowledge

Youngmin Oh, Jung Uk Kim

Journal of Broadcast Engineering, 2024

Efficient Sampling Method for Repetitive Data for Label Data Selection In Multispectral Pedestrian Detection
Domestic Conference 2024

Efficient Sampling Method for Repetitive Data for Label Data Selection In Multispectral Pedestrian Detection

Seungho Shin, Jung Uk Kim

Korean Institute of Broadcast and Media Engineers (KIBME), 2024

Effective Change Captioning via Feature Map Restoration in Noisy Environments
Domestic Conference 2024

Effective Change Captioning via Feature Map Restoration in Noisy Environments

Jiyoung Park, Kyu Ri Park, Jung Uk Kim

Korean Institute of Broadcast and Media Engineers (KIBME), 2024

Handling Missing Modality Using Multimodal Relational Knowledge
Domestic Conference 2024

Handling Missing Modality Using Multimodal Relational Knowledge

Kyu Ri Park, Jung Uk Kim

Korea Institute of Military Science and Technology (KIMST), 2024

Audio-Visual Spatial Integration and Recursive Attention for Robust Sound Source Localization
International Conference ACM MM 2023

Audio-Visual Spatial Integration and Recursive Attention for Robust Sound Source Localization

Sung Jin Um*, Dongjin Kim*, Jung Uk Kim

ACM International Conference on Multimedia (ACM MM), 2023

Online Class Incremental Learning on Stochastic Blurry Task Boundary via Mask and Visual Prompt Tuning
International Conference ICCV 2023

Online Class Incremental Learning on Stochastic Blurry Task Boundary via Mask and Visual Prompt Tuning

Jun-Yeong Moon, KeonHee Park, Jung Uk Kim*, Gyeong-Moon Park*

IEEE/CVF International Conference on Computer Vision (ICCV), 2023

Stereoscopic Vision Recalling Memory for Monocular 3D Object Detection
International Journal IEEE TIP 2023

Stereoscopic Vision Recalling Memory for Monocular 3D Object Detection

Jung Uk Kim, Hyung-Il Kim, Yong Man Ro

IEEE Transactions on Image Processing (TIP, IF: 13.7), 2023

Robust Multispectral Pedestrian Detection Via Spectral Position-Free Feature Mapping
International Conference ICIP 2023

Robust Multispectral Pedestrian Detection Via Spectral Position-Free Feature Mapping

Sungjune Park, Jung Uk Kim, Jin Mo Song, Yong Man Ro

IEEE International Conference on Image Processing (ICIP), 2023

Towards Robust Audio-Based Vehicle Detection via Importance-Aware Audio-Visual Learning
International Conference ICASSP 2023

Towards Robust Audio-Based Vehicle Detection via Importance-Aware Audio-Visual Learning

Jung Uk Kim, Seong Tae Kim

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023

Similarity Relation Preserving Cross-Modal Learning for Multispectral Pedestrian Detection Against Adversarial Attacks
International Conference ICASSP 2023

Similarity Relation Preserving Cross-Modal Learning for Multispectral Pedestrian Detection Against Adversarial Attacks

Jung Uk Kim, Yong Man Ro

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023

Multimodal Deep Learning for Korean Fake News Detection
Domestic Conference 2023

Multimodal Deep Learning for Korean Fake News Detection

Dongjin Kim, Jung Uk Kim

Korea Software Congress (KSC), 2023

Multimodal Pedestrian Detection Using Attention and Multi Modal Guide
Domestic Conference 2023

Multimodal Pedestrian Detection Using Attention and Multi Modal Guide

Seungho Shin, Jung Uk Kim

Korea Software Congress (KSC), 2023

Single-Modal Pedestrian Detection Leveraging Multimodal Knowledge for Blackout Situations
Domestic Journal 2023

Single-Modal Pedestrian Detection Leveraging Multimodal Knowledge for Blackout Situations

Seungho Shin, Jung Uk Kim

Journal of KIISE, 2023

Best Paper
Effective 3D Object Detection using 2D Object Detection information
Domestic Conference 2023

Effective 3D Object Detection using 2D Object Detection information

Youngmin Oh, Kyu Ri Park, Jung Uk Kim

Korean Institute of Broadcast and Media Engineers (KIBME), 2023

Enhancing Multi-Modal Audio-Visual QA Model Performance via Single Modal Feature Maps with Added Noise Input
Domestic Conference 2023

Enhancing Multi-Modal Audio-Visual QA Model Performance via Single Modal Feature Maps with Added Noise Input

Kyu Ri Park, Youngmin Oh, Jung Uk Kim

Korean Institute of Broadcast and Media Engineers (KIBME), 2023

Automatic Notification of Dangerous Situations in Blind Spots via Image-based Pedestrian Detection using Deep Learning
Domestic Conference 2022

Automatic Notification of Dangerous Situations in Blind Spots via Image-based Pedestrian Detection using Deep Learning

Kyu Ri Park, Jung Uk Kim

Korea Software Congress (KSC), 2022