Projects

AI-based Motion Analysis for National Archery Team Performance Improvement - Integrated Data Analytics Platform

Korea Sports Promotion Foundation (KSPO) (2023.02 - 2025.05)

Development of Real·Virtual Environmental Analysis Based Adaptive Interaction Technology

Electronics and Telecommunications Research Institute (ETRI) grant funded by ICT RD program of MSIT/IITP (2021.09 - 2024.12)

Digital New Software·AI Camp, Yong In University SW·AI DoDream

Korea Foundation for the Advancement of Science and Creativity (KOFAC) (2022.12 - 2023.04)

Deep Learning-Based Human-Object Interaction on Mobile Device

National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (2020.09 - 2023.02)

Method for Human-Object Interaction (HOI) Detection

Yong In University (2020.06 - 2022.05)

Introduction of AI Education and Establishment Plan of AI Research Institute

Yong In University (2020)

Before 2020 (Representative)

On-Device AI; Bixby Vision, AI Camera @ Visual S/W R&D Group, Samsung Electronics (2018 - 2020)

Deep Learning-Based Smart-Car Multi-Sensor Fusion for AR/VR Contents @ MVPL

Institute for Information & communications Technology Promotion (IITP) (2016 - 2018)

Scene Understanding for the Visually Impaired @ MVPL

Electronics and Telecommunications Research Institute (ETRI) (2014 - 2017)

Stereo Vision for an Autonomous Vehicle @ MVPL

Hyundai Motor Company (2012 - 2016)

Depth Image-Based Rendering @ MVPL

LG Electronics (2011 - 2013)

Publications

D2FP: Learning Implicit Prior for Human Parsing [code]

Junyoung Hong, Hyeri Yang, Ye ju Kim, Haerim Kim, Shinwoong Kim, Euna Shim, and Kyungjae Lee

IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) (Mar 2025)

Local Context Aggregation for Semantic Segmentation: A Novel PSPNet Approach [link]

Haerim Kim, Ye Ju Kim, Junyoung Hong, Hyeri Yang, Shim Euna, and Kyungjae Lee

International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC) (Jul 2024)

Selective Style Gaussian: Enabling Localized Style Transfer in 3D Scenes [link]

Hyeri Yang, Hyeonbeom Heo, Junyoung Hong, Ye Ju Kim, and Kyungjae Lee

International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC) (Jul 2024)

Patch Regularization in Visual State Space Model [link]

Junyoung Hong, Hyeri Yang, Ye Ju Kim, Shinwoong Kim, and Kyungjae Lee

International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC) (Jul 2024)

Dual-Modality Cross-Interaction-Based Hybrid Full-frame Video Stabilization [link]

by Jaeyoung Jang, Yuseok Ban, and Kyungjae Lee

Applied Sciences (May 2024)

Vehicle and Method for Detecting Obstacle [link]

Hyundai Motor Company, Kia Motors Corporation, and Yonsei University

Patent Registered: Korea (2024)

Method for Processing Image Based on Scene Recognition of Image and Electronic Device Therefor [link]

Samsung Electronics

Patent Registered: Korea (2024); United States (2021)

Cascade Fusion-Based Multi-Scale Enhancement of Thermal Image [link]

Kyungjae Lee

The Journal of the Korea institute of electronic communication sciences (Feb 2024)

LH-FAS v2: Head Pose Estimation-Based Lightweight Face Anti-Spoofing [link]

Hyeonbeom Heo, Hyeri Yang, Sunguk Jung, and Kyungjae Lee

The Journal of the Korea institute of electronic communication sciences (Feb. 2024)

Light Awareness Network for Shadow Detection

Ye Ju Kim, Junyoung Hong, Hyeonbeom Heo, Hyeri Yang, Soyeon Kim, and Kyungjae Lee

International Conference of Next Generation Convergence Technology (ICNGCT) (Aug 2023)

LH-FAS: Lightweight Head Pose-based Face Anti-Spoofing

Hyeonbeom Heo, Hyeri Yang, Junyoung Hong, Soyeon Kim, Ye Ju Kim, Haerim Kim, and Kyungjae Lee

International Conference of Next Generation Convergence Technology (ICNGCT) (Aug 2023)

Exploring the Potential of UPerNet-Based Multi-task Learning

Soyeon Kim, Hyeonbeom Heo, Junyoung Hong, Hyeri Yang, Ye Ju Kim, and Kyungjae Lee

International Conference of Next Generation Convergence Technology (ICNGCT) (Aug 2023)

Look Around for Anomalies: Weakly-supervised Anomaly Detection via Context-Motion Relational Learning [link]

MyeongAh Cho, Minjung Kim, Sangwon Hwang, Chaewon Park, Kyungjae Lee, and Sangyoun Lee

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (Jun 2023)

Frame-to-Frame Visual Odometry Estimation Network With Error Relaxation Method [link]

Sangwon Hwang, Myeongah Cho, Yuseok Ban, and Kyungjae Lee

IEEE Access (Oct 2022)

Benchmarking Deep Learning Models for Instance Segmentation [link]

Sunguk Jung, Hyeonbeom Heo, Sangheon Park, Sung-Uk Jung, and Kyungjae Lee

Applied Sciences (Sep 2022)

LiDAR Depth Completion Using Color-Embedded Information via Knowledge Distillation [link]

Sangwon Hwang, Junhyeop Lee, Woo Jin Kim, Sungmin Woo, Kyungjae Lee, and Sangyoun Lee

IEEE Transactions on Intelligent Transportation Systems (T-ITS) (Sep 2022)

Vehicle Detecting Method and System [link]

Hyundai Motor Company, Kia Motors Corporation, and Yonsei University

Patent Registered: Germany (2022); China (2019); United States (2016); Korea (2015)

A Screen of Slide Detection Method Using Deep Learning-Based Segmentation and Hough Transform [link]

Junyoung Hong*, Sunguk Jung*, Ye Ju Lee, Hyeonbeom Heo, Hyeri Yang, Hayeon Kim, and Kyungjae Lee (* equally contributed)

International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC) (Jul 2022)

A Method for Converting an Image of a GO Game Record to Training Data [link]

Hyeri Yang*, Hyeonbeom Heo*, Sunguk Jung, Yongwoo Lee, Junyoung Hong, Ye Ju Kim, and Kyungjae Lee (* equally contributed)

International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC) (Jul 2022)

Electronic Device, User Terminal, and Method for Running Scalable Deep Learning Network [link]

Samsung Electronics

Patent Application: United States (2022); Korea (2019)

컨텐츠에 관한 추천 정보를 생성하기 위한 장치 및 방법 [link]

Yong In University and Chungbuk National University

Patent Application: Korea (2021)

Multi-Scale Ensemble Learning for Thermal Image Enhancement [link]

Yuseok Ban and Kyungjae Lee

Applied Sciences (Mar 2021)

How the Multiplicity of Suggested Information Affects the Behavior of a User in a Recommender System [link]

Yuseok Ban and Kyungjae Lee

Electronics (Mar 2021)

Re-Enrichment Learning: Metadata Saliency for the Evolutive Personalization of a Recommender System [link]

Yuseok Ban and Kyungjae Lee

Applied Sciences (Fed 2021)

Relational Deep Feature Learning for Heterogeneous Face Recognition [link] [arxiv]

MyeongAh Cho, Taeoh Kim, Ig-Jae Kim, Kyungjae Lee, and Sangyoun Lee

IEEE Transactions on Information Forensics and Security (T-IFS) (Jan 2021)

AD-VO: Scale-resilient visual odometry using attentive disparity map [link]

Joosung Lee, Sangwon Hwang, Kyungjae Lee, Woo Jin Kim, Junhyeop Lee, Tae-young Chung, and Sangyoun Lee

arXiv (2020)

Electronic Device and Method for Providing Service Corresponding to Selection of Object in Image [link]

Samsung Electronics

Patent Application: United States (2019); Korea (2019)

Brightness-Based Convolutional Neural Network for Thermal Image Enhancement [link] [page]

Kyungjae Lee, Junhyeop Lee, Joosung Lee, Sangwon Hwang, and Sangyoun Lee

IEEE Access (2017)

Apparatus And Method for Detecting Moving Object [link]

Yonsei University

Patent Registered: Korea (2019)

Efficient Depth Enhancement Using a Combination of Color and Depth Information [link] [page]

Kyungjae Lee, Yuseok Ban, and Sangyoun Lee

Sensors (2017)

Road Surface Estimation Using a Piecewise Linear Function in v-Disparity

Kyungjae Lee, Jaesung Kim, and Sangyoun Lee

International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC) (2016)

Compressed Video Noise Sensitivity Analysis for Blocking Artifact Reduction

C Park, T Kim, H Son, K Lee, and S Lee

International Conference on Electronics, Information and Communication (ICEIC), 2018


A Study on The Lane Detection Robust to Road Markers Systems

박성주, 이경재, 이준협, 정태영, 이상윤

한국통신학회 학술대회논문집, 2017


Robust Face Recognition via Sparse Representation through Overlapping-Patch and Sparsity Concentration Index

S Hwang, H Bae, K Lee, and S Lee

International Conference on Electronics, Information and Communication (ICEIC), 2017


Side Obstacle Detection using Dynamic Programming based on Stereo Vision

T Chung, K Lee, J Kim and S Lee

International Conference on Electronics, Information and Communication (ICEIC), 2017


Hierarchical Feature Augmentation for Detecting Keypoints in a Range Image

Y Ban, K Lee, and S Lee

International Conference on Electronics, Information and Communication (ICEIC), 2017


Inversion of Spread-Direction and Alternate Neighborhood System for Cellular Automata-Based Image Segmentation Framework

K Lee, J Lee, S Hwang, and S Lee

Journal of International Society for Simulation Surgery, 2017


Method For Real-Time Odometry Estimation Using Mono Camera and IMU Sensor

Yonsei University

Patent Application, Korea, 2017


Precise Ego-Motion Estimating Deep Network Through Rearrangement of Image Sequences Which Can Also Allow the Prediction of an Automobile Driving in Reverse

Yonsei University

Patent Application, Korea, 2017


Method of Generating 3d-Background Map Except Dynamic Obstacles Using Deep Learning

Yonsei University

Patent Application, Korea, 2016


Cascade Feature Selection and Projection for Rapid Human Face Recognition

M Lee, Y Ban, K Lee, J Choi, C Park, and S Lee

International Conference on Electronics, Information and Communication (ICEIC), 2016


Body Pose Estimation Using Context-Based Bag-Of-Features

Y Ban, M Lee, J Choi, K Lee, and S Lee

International Conference on Electronics, Information and Communication (ICEIC), 2016


Photometric Stereo with Relit Images from a Single Frontal Face Image

J Lee, K Lee, and S Lee

International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC), 2016


3D Alignment of Face in a Single Image

E Song, K Lee, and S Lee

International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC), 2016


Generation of Neighborhood Euclidean Distance Maps for Rapid GrowCut

K Lee, E Song, T Jeon, and S Lee

International Conference on Electronics, Information and Communication (ICEIC), 2015


Human Height Estimation Algorithm Using the Single RGB Camera

전태재, 김재성, 이경재, 배한별, 이상윤

대한전자공학회 학술대회, 2014


Pedestrian Distance Estimation Using a Single Camera Image

전태재, 황진규, 임경민, 송응열, 김재성, 이경재, 이상윤

대한전자공학회 학술대회, 2014


Enhancement of Depth Image Using Color Segmentation Method

K Lee, J Hwang, J Kim, E Song, J Oh, and S Lee

International Conference on Electronics, Information and Communication (ICEIC), 2014


Head Pose Estimation Using Depth Information

최인영, 황진규, 김재성, 이경재, 이상윤

대한전자공학회 학술대회, 2013


A Novel Hole Filling Method Using Image Segmentation-Based Image In-Painting

J Hwang, K Lee, J Kim, and S Lee

IEEE International Conference on Consumer Electronics (ICCE), 2013


Non-linear Rate-Distortion Optimization Model for HEVC

S Kim, K Lee, and S Lee

International Conference on Electronics, Information and Communication (ICEIC), 2013


Apparatus For Redeeming Noise of Depth Image and Method Thereof

Yonsei University

Patent Application, Korea, 2013


Automatic Human Object Segmentation and Depth Map Estimation Using Depth Map

이경재, 황진규, 반유석, 오지훈, 이상윤

대한전자공학회 학술대회, 2012