Kimin Yun

I am a senior researcher at Visual Intelligence Lab at the Electronics and Telecommunications Research Institute (ETRI) in South Korea.

At ETRI, I am involved in national R&D projects focusing on both foundational technologies and applied research of computer vision and machine learning. My research interest is to improve human life through smarter, more beneficial vision systems, aiming to create practical applications.

I completed an integrated Master's and Ph.D. program in Electrical and Computer Engineering at Seoul National University, under the supervision of Prof. Jin Young Choi, in 2017. I received my Bachelor's degree from the Seoul National University in 2010.

Email: kimin.yun (at) etri.re.kr  /  CV  /  Google Scholar  

profile photo
Research

A significant part of my work is dedicated to addressing real-world challenges and developing practical applications (e.g., surveillance camera applications)

arxiv24 Task-Specific Adaptation of Segmentation Foundation Model via Prompt Learning
Hyung-Il Kim*, Kimin Yun* Jun-Seok Yun, Yuseok Bae
European Conference on Computer Vision Workshop on Out Of Distribution Generalization in Computer Vision (ECCVW), 2024
arXiv

* indicates equal contribution.

etrij23 Background memory-assisted zero-shot video object segmentation for unmanned aerial and ground vehicles
Kimin Yun, Hyung-Il Kim, Kangmin Bae, Jinyoung Moon
ETRI Journal, 2023
Paper / Binary

tbiom22 Face Shape-Guided Deep Feature Alignment for Face Recognition Robust to Face Misalignment
Hyung-Il Kim, Kimin Yun, Yong Man Ro.
IEEE Transactions on Biometrics, Behavior, and Identity Science, 2022
arXiv / Bibtex

swag_22 SWAG-Net: Semantic Word-Aware Graph Network for Temporal Video Grounding
Sunoh Kim, Taegil Ha, Kimin Yun, Jin Young Choi.
ACM International Conference on Information and Knowledge Management (CIKM), 2022
Paper

uncertain_22 Localization Uncertainty Estimation for Anchor-Free Object Detection
Youngwan Lee, Joong-won Hwang, Hyung-Il Kim, Kimin Yun, Yongjin Kwon, Yuseok Bae, Sung Ju Hwang.
European Conference on Computer Vision Workshop on Uncertainty Quantification for Computer Vision (ECCVW) , 2022
arXiv

OC_PAR22 Occluded Pedestrian-Attribute Recognition for Video Sensors Using Group Sparsity
Geonu Lee, Kimin Yun, Jungchan Cho.
Sensors, 2022
arXiv

Gating21 Gating Mechanism in Deep Neural Networks for Resource-Efficient Continual Learning
Hyundong Jin, Kimin Yun, Eunwoo Kim.
IEEE Access, 2021
Paper

vov3d_21 Diverse Temporal Aggregation and Depthwise Spatiotemporal Factorization for Efficient Video Classification
Youngwan Lee, Hyung-Il Kim, Kimin Yun, Jinyoung Moon.
IEEE Access, 2021
arXiv

HOI_21 Improved Human-Object Interaction Detection through On-the-Fly Stacked Generalization
Geonu Lee, Kimin Yun, Jungchan Cho.
IEEE Access, 2021
Paper

fallen_21 The Dataset and Baseline Models to Detect Human Postural States Robustly against Irregular Postures
Kangmin Bae*, Kimin Yun*, Jungchan Cho, Yuseok Bae.
IEEE Int'l Conf on Advanced Video and Signal-based Surveillance (AVSS), 2021
Paper

* indicates equal contribution.

pa_ground_21 Position-aware Location Regression Network for Temporal Video Grounding
Sunoh Kim, Kimin Yun, Jin Young Choi.
IEEE Int'l Conf on Advanced Video and Signal-based Surveillance (AVSS), 2021
arXiv / GitHub

rotation_pose_20 Robust Human Pose Estimation for Rotation via Self-Supervised Learning
Kimin Yun, Jongyoul Park, Jungchan Cho.
IEEE Access, 2020
Paper

ptz_20 Unsupervised Moving Object Detection through Background Models for PTZ Camera
Kimin Yun, Hyung-Il Kim, Kangmin Bae, Jongyoul Park.
International Conference on Pattern Recognition (ICPR), 2020
Paper / Slide

mtl_20 Anti-Litter Surveillance based on Person Understanding via Multi-task Learning
Kangmin Bae* Kimin Yun*, Hyung-Il Kim, Youngwan Lee, Jongyoul Park.
British Machine Vision Conference (BMVC), 2020
Paper

* indicates equal contribution.

garbage_19 Vision-based Garbage Dumping Action Detection for Real-World Surveillance Platform
Kimin Yun, Yongjin Kwon, Sungchan Oh, Jinyoung Moon, Jongyoul Park.
ETRI Journal, 2019 (Best Paper Award)
Paper

GCNH_19 Skeleton-based Action Recognition of People Handling Objects
Sunoh Kim, Kimin Yun, Jongyoul Park, Jin Young Choi.
IEEE Winter Conference on Applications of Computer Vision (WACV), 2019
arXiv

RL_track_18 Action-Driven Visual Object Tracking with Deep Reinforcement Learning
Sangdoo Yun, Jongwon Choi, Youngjoon Yoo, Kimin Yun, Jin Young Choi.
IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2018
Paper

dankook18 Behavior Recognition of a Person in a Daily Video Using Joint Position Information
Jeong-Min Seo, Haanju Yoo, Kimin Yun, Hyunil Kim, Sang-Il Choi.
IEEE International Conference on Artificial Intelligence and Knowledge Engineering Workshop on AI Bigdata Cloud Technologies, 2018
Paper

SC_MCD_17 Scene Conditional Background Update for Moving Object Detection in a Moving Camera
Kimin Yun, Jongin Lim, Jin Young Choi.
Pattern Recognition Letters, 2017
Paper / Video / Binary

MIF_17 Motion Interaction Field for Detection of Abnormal Interactions
Kimin Yun, Youngjoon Yoo, Jin Young Choi.
Machine Vision and Applications, 2017
Paper / Video

rltrack_17 Action-Decision Network for Visual Tracking with Deep Reinforcement Learning
Sangdoo Yun, Jongwon Choi, Youngjoon Yoo, Kimin Yun, Jin Young Choi.
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2017
Paper

DMCD_17 Appearance and Motion based Deep Learning Architecture for Moving Object Detection in Moving Camera
Byeongho Heo, Kimin Yun, Jin Young Choi.
IEEE International Conference on Image Processing (ICIP), 2017
Paper

car_MCD_16 Attention-Inspired Moving Object Detection in Monocular Dashcam Videos
Kimin Yun, Jongin Lim, Sangdoo Yun, Soo Wan Kim, Jin Young Choi.
International Conference on Pattern Recognition (ICPR), 2016
Paper

pedestrian_16 Density-Aware Pedestrian Proposal Networks for Robust People Detection in Crowded Scenes
Sangdoo Yun, Kimin Yun, Jongwon Choi, Jin Young Choi.
International Workshop on Crowd Understanding in conjuction with ECCV, 2016
Paper

path_predict_16 Visual Path Prediction in Complex Scenes with Crowded Moving Objects
Youngjoon Yoo, Kimin Yun, Sangdoo Yun, Jonghee Hong, Hawook Jeong, Jin Young Choi.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016
Paper

fp_sampling_15 Robust and Fast Moving Object Detection in a Non-Stationary Camera via Foreground Probability based Sampling
Kimin Yun, Jin Young Choi.
IEEE International Conference on Image Processing (ICIP), 2015
Paper

rgb2gray_15 Gradient Preserving RGB-to-Gray Conversion using Random Forest
ByeongJu Lee, Jongwon Choi, Kimin Yun, Jin Young Choi.
IEEE International Conference on Image Processing (ICIP), 2015
Paper

ptztrack_15 Robust Pan-Tilt-Zoom Tracking via Optimization Combining Motion Features and Appearance Correlations
ByeongJu Lee, Kimin Yun, Jongwon Choi, Jin Young Choi.
IEEE International Conf. on Advanced Video and Signal based Surveillance (AVSS), 2015
Paper

Stab_14 Spatio-temporal weighting in local patches for direct estimation of camera motion in video stabilization
Soo Wan Kim, Shimin Yin Kimin Yun, Jin Young Choi.
Computer Vision and Image Understanding, 2014
Paper

unusual_app_14 Learning with Adaptive Rate for Online Detection of Unusual Appearance
Kimin Yun, Jiyun Kim, Soo Wan Kim, Hawook Jeong, Jin Young Choi.
International Symposium on Visual Computing, 2014
Paper

clustering_14 Proximity Clustering for Revealing a Semantically Dominant Class
Tushar Sandhan, Kimin Yun, Jin Young Choi.
International Symposium on Visual Computing, 2014
Paper

mif_14 Motion Interaction Field for Accident Detection in Traffic Surveillance Video
Kimin Yun, Hawook Jeong, Kwang Moo Yi, Soo Wan Kim, Jin Young Choi.
International Conference on Pattern Recognition (ICPR), 2014
Paper

vsb_14 Visual Surveillance Briefing System: Event-based Video Retrieval and Summarization
Sangdoo Yun, Kimin Yun, Soo Wan Kim, Youngjoon Yoo, Jiyeoup Jeong.
IEEE International Conf. on Advanced Video and Signal based Surveillance, 2014
Paper

NP_MCD_13 Detection of moving objects with a moving camera using non-panoramic background model
Soo Wan Kim, Kimin Yun, Kwang Moo Yi, Sun Jung Kim, Jin Young Choi.
Machine Vision and Applications, 2013
Paper

mcd58_13 Detection of Moving Objects with Non-Stationary Cameras in 5.8ms: Bringing Motion Detection to your Mobile Device
Kwang Moo Yi, Kimin Yun, Soo Wan Kim, Hyung Jin Chang, Hawook Jeong, Jin Young Choi.
IEEE Int. workshop on Mobile vision, in conjunction with CVPR, 2013 (Best Paper Award)
Paper / GitHub / Video

stab_11 Probabilistic Approach with Three Hierarchies of Motion Estimation for Video Stabilization
Kimin Yun, Soo Wan Kim, Jin Young Choi.
IEEE Digital Image Computing: Techniques and Applications, 2011
Paper

Award and Honors

  • National R&D Excellence Top 100, Minister of Science and ICT, South Korea, 2023
    • 2023년 국가연구개발 우수성과 100선 선정, 과학기술정보통신부
    • 성과명: 다양한 환경에 적용가능한 영상 이해 인공지능 핵심기술 개발과 시민 안전 분야 실증 및 사업화 (과제책임자: 배유석)
  • National Disaster Management R&D Award, Ministry of the Interior and Safety, South Korea, 2023
    • 2023년 대한민국 재난안전 연구개발 행정안전부 장관상
    • 성과명: 영상 이해 인공지능 핵심기술을 통한 공공 CCTV 활용 시민 안전 실증 및 사업화 (과제책임자: 배유석)
  • Best Paper Award, ETRI, 2022
  • National R&D Excellence Top 100, Minister of Science and ICT, South Korea, 2021
    • 2021년 국가연구개발 우수성과 100선 선정, 과학기술정보통신부
    • 성과명: 사람의 행동을 정밀하게 이해하는 시각지능 핵심 원천기술 확보 및 실세계 적용 응용 기술 개발 (과제책임자: 배유석)
  • Best Paper Award, ETRI Journal, 2020
  • ETRI Representative Research - Grand Prize, ETRI, 2019
    • 2019년 ETRI 대표성과
    • 성과명: 영상 내용을 사람처럼 이해하는 시각지능 원천기술 (과제책임자: 박종열)
  • National R&D Excellence Top 100 (Project leader: Jongyoul Park), Minister of Science and ICT, South Korea, 2019
    • 2019년 국가연구개발 우수성과 100선 선정, 과학기술정보통신부
    • 성과명: 대규모 시각 데이터 실시간 분석 및 내용 이해를 위한 디스커버리 플랫폼 (DeepView: 딥뷰) 개발 (과제책임자: 박종열)
  • New Employee Award, ETRI, 2019
  • Best Paper Award, CVPR worshop, 2013
  • Songwon KimYoungHwan Scholarship, 2006-2013
  • Scholarship of EECS Department, Seoul National University, 2006

Link


Template borrowed from Jon Barron and Sangdoo Yun.