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

Research

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

	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.
	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
	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-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
	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
	Occluded Pedestrian-Attribute Recognition for Video Sensors Using Group Sparsity Geonu Lee, Kimin Yun, Jungchan Cho. Sensors, 2022 arXiv
	Gating Mechanism in Deep Neural Networks for Resource-Efficient Continual Learning Hyundong Jin, Kimin Yun, Eunwoo Kim. IEEE Access, 2021 Paper
	Diverse Temporal Aggregation and Depthwise Spatiotemporal Factorization for Efficient Video Classification Youngwan Lee, Hyung-Il Kim, Kimin Yun, Jinyoung Moon. IEEE Access, 2021 arXiv
	Improved Human-Object Interaction Detection through On-the-Fly Stacked Generalization Geonu Lee, Kimin Yun, Jungchan Cho. IEEE Access, 2021 Paper
	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.
	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
	Robust Human Pose Estimation for Rotation via Self-Supervised Learning Kimin Yun, Jongyoul Park, Jungchan Cho. IEEE Access, 2020 Paper
	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
	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.
	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
	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
	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
	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
	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
	Motion Interaction Field for Detection of Abnormal Interactions Kimin Yun, Youngjoon Yoo, Jin Young Choi. Machine Vision and Applications, 2017 Paper / Video
	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
	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
	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
	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
	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
	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
	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
	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
	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
	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
	Proximity Clustering for Revealing a Semantically Dominant Class Tushar Sandhan, Kimin Yun, Jin Young Choi. International Symposium on Visual Computing, 2014 Paper
	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
	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
	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
	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
	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