Kwang In Kim
Head of research group
Machine Learning and Vision
Associate professor in
Department of Electrical Engineering
Graduate School of Artificial Intelligence
at POSTECH
Address: E2-327, POSTECH
77 Cheongam-ro, Nam-gu, Pohang, 37673 Korea
E-mail: kimkin (at) postech.ac.kr
My main research interest is improving the way we explore, analyze, and interact with complex data. To achieve this goal, I work on developing new techniques and methodologies in machine learning and computer vision.
My current research projects focus on algorithmic aspects of machine learning, particularly in the context of distributed learning, semi-supervised learning, active learning, multi-task learning, and transfer learning. I also investigate novel approaches for capturing, processing, mining, and visualizing image and video data.
Vita
Since 2023: Associate Professor, POSTECH, Department of Electrical Engineering and Graduate School of Artificial Intelligence
2019-2023: Associate Professor & Professor, UNIST, Artificial Intelligence Graduate School and Department of Computer Science and Engineering
2016-2019: Senior Lecturer, University of Bath, Department of Computer Science
2013-2016: Lecturer, Lancaster University, School of Computing and Communications
2010-2013: Post-doc, Max Planck Institue for Informatics, GVV Group and Computer Graphics Department
2008-2009: Post-doc, Saarland University, Machine Learning Group
2002-2004, 2005-2008: Post-doc, Max Planck Institute for Biological Cybernetics, Empirical Inference Department
2000-2002, 2004-2005: Post-doc, KAIST, A. I. Lab
2000: PhD, Kyungpook National University, Computer Engineering
Open positions
I am seeking highly motivated candidates to apply for our PhD and Masters programs in Machine Learning or Computer Vision. These programs are offered by either the Department of Electronic Engineering or the Graduate School of Artificial Intelligence at POSTECH.
To learn more, please visit our group website and read the note provided.
Publications
Uyoung Jeong, Jonathan Freer, Seungryul Baek, Hyung Jin Chang, and Kwang In Kim
PoseBH: Prototypical multi-dataset training beyond human pose estimation
CVPR 2025
Paper
Kwang In Kim
Diffusion-based active learning for distributed client manifolds
AAAI 2025
Paper
Kwang In Kim
Distributed active client selection with noisy clients using model association scores
ECCV 2024
Paper
Yunpyo An, Suyeong Park, and Kwang In Kim
Active learning guided by efficient surrogate learners
AAAI 2024
Paper
Kwang In Kim
Robust distributed gradient aggregation using projections onto gradient manifolds
AAAI 2024
Paper
Jake Deane, Sinéad Kearney, Kwang In Kim, and Darren Cosker
RGBT-dog: a parametric model and pose prior for canine body analysis data creation
WACV 2024
Paper | Supplemental
Uyoung Jeong, Seungryul Baek, Hyung Jin Chang, and Kwang In Kim
BoIR: box-supervised instance representation for multi-person pose estimation
BMVC 2023
Paper | Supplemental | Code
Kwang In Kim
Active label correction using robust parameter update and entropy propagation
ECCV 2022
Paper | Supplemental
Tze Ho Elden Tse, Kwang In Kim, Ales Leonardis, and Hyung Jin Chang
Collaborative learning for hand and object reconstruction with attention-guided graph convolution
CVPR 2022
Paper | Supplemental
Kwang In Kim
Robust combination of distributed gradients under adversarial perturbations
CVPR 2022
Paper | Supplemental
Youssef A. Mejjati, Isa Milefchik, Aaron Gokaslan, Oliver Wang, Kwang In Kim, and James Tompkin
GaussiGAN: controllable image synthesis with 3D Gaussians from unposed silhouettes
BMVC 2021
Paper | Supplemental | Web page
Kwang In Kim and James Tompkin
Testing using privileged information by adapting features with statistical dependence
ICCV 2021
Paper | Supplemental | Web page
Dong Uk Kim, Kwang In Kim, and Seungryul Baek
End-to-end detection and pose estimation of two interacting hands
ICCV 2021
Paper | Supplemental
Kwang In Kim
Improving predictors via combination across diverse task categories
ICML 2021
Paper | Supplemental
Kwanyoung Kim, Dongwon Park, Kwang In Kim, and Se Young Chun
Task-aware variational adversarial active learning
CVPR 2021
Paper | Supplemental
Kwang In Kim, Christian Richardt, and Hyung Jin Chang
Combining task predictors via enhancing joint predictability
ECCV 2020
Paper | Supplemental
Youssef A. Mejjati, Celso F. Gomez, Kwang In Kim, Eli Shechtman, and Zoya Bylinskii
Look here! A parametric learning based approach to redirect visual attention
ECCV 2020
Paper | Supplemental | Web page
Seungryul Baek, Kwang In Kim, and Tae-Kyun Kim
Weakly-supervised domain adaptation via GAN and mesh model for estimating 3D hand poses interacting objects
CVPR 2020
Paper | Supplemental
Sinéad Kearney, Wenbin Li, Martin Parsons, Kwang In Kim, and Darren Cosker
RGBD-Dog: Predicting canine pose from RGBD sensors
CVPR 2020
Paper | Supplemental | Web page
Youssef A. Mejjati, Zejiang Shen, Michael Snower, Aaron Gokaslan, Oliver Wang, James Tompkin, and Kwang In Kim
Generating object stamps
AI for Content Creation Workshop, CVPR 2020
Paper | arXiv (long version) | Web page
Dushyant Mehta, Kwang In Kim, and Christian Theobalt
On implicit filter level sparsity in convolutional neural networks
CVPR 2019
Paper | Supplemental
Seungryul Baek, Kwang In Kim, and Tae-Kyun Kim
Pushing the envelope for RGB-based dense 3D hand pose estimation via neural rendering
CVPR 2019
Paper | Supplemental
Kwang In Kim and Hyung Jin Chang
Joint manifold diffusion for combining predictions on decoupled observations
CVPR 2019
Paper
Yassir Saquil, Kwang In Kim, and Peter Hall
Ranking CGANs: subjective control over semantic image attributes
BMVC 2018
Paper
Juil Sock, Kwang In Kim, Caner Sahin, and Tae-Kyun Kim
Multi-task deep networks for depth-based 6D object pose and joint registration in crowd scenarios
BMVC 2018
Paper
Kwang In Kim, Juhyun Park, and James Tompkin
High-order tensor regularization with application to attribute ranking
CVPR 2018
Paper
Youssef A. Mejjati, Darren Cosker, and Kwang In Kim
Multi-task learning by maximizing statistical dependence
CVPR 2018
Paper
Seungryul Baek, Kwang In Kim, and Tae-Kyun Kim
Augmented skeleton space transfer for depth-based hand pose estimation
CVPR 2018
Paper
Kwang In Kim, James Tompkin, and Christian Richardt
Predictor combination at test time
ICCV 2017
Paper | Supplemental
Seungryul Baek, Kwang In Kim, and Tae-Kyun Kim
Real-time online action detection forests using spatiotemporal contexts
WACV 2017
Paper
Kwang In Kim
Semi-supervised learning based on joint diffusion of graph functions and Laplacians
ECCV 2016
Web page
Yanxia Zhang, Thomas Wilcockson, Kwang In Kim, Trevor Crawford, Hans Gellersen, and Pete Sawyer
Monitoring dementia with automatic eye movements analysis
Intelligent Decision Technologies 2016
Paper
Kwang In Kim, James Tompkin, Hanspeter Pfister, and Christian Theobalt
Context-guided diffusion for label propagation on graphs
ICCV 2015
Web page
Helge Rhodin, James Tompkin, Kwang In Kim, Edilson de Aguiar, Hanspeter Pfister, Hans-Peter Seidel, and Christian Theobalt
Generalizing wave gestures from sparse examples for real-time character control
ACM Trans. Graphics (SIGGRAPH Asia) 2015
Web page
Ahmed Elhayek, Carsten Stoll, Kwang In Kim, and Christian Theobalt
Outdoor human motion capture by simultaneous optimization of pose and camera parameters
Computer Graphics Forum 2015
Web page
Kwang In Kim, James Tompkin, Hanspeter Pfister, and Christian Theobalt
Local high-order regularization on data manifolds
CVPR 2015
Web page
Kwang In Kim, James Tompkin, Hanspeter Pfister, and Christian Theobalt
Semi-supervised learning with explicit relationship regularization
CVPR 2015
Web page
Younghee Kwon, Kwang In Kim, James Tompkin, Jin Hyung Kim, and Christian Theobalt
Efficient learning of image super-resolution and compression artifact removal with semi-local Gaussian processes
IEEE Trans. PAMI 2015
Web page
Helge Rhodin, James Tompkin, Kwang In Kim, Kiran Varanasi, Hans-Peter Seidel, and Christian Theobalt
Interactive motion mapping for real-time character control
Computer Graphics Forum (Eurographics) 2014
Web page
Kwang In Kim, James Tompkin, and Christian Theobalt
Curvature-aware regularization on Riemannian submanifolds
ICCV 2013
Web page
Miguel Granados, Kwang In Kim, James Tompkin, and Christian Theobalt
Automatic noise modeling for ghost-free HDR reconstruction
ACM Trans. Graphics (SIGGRAPH Asia) 2013
Web page
James Tompkin, Min H. Kim, Kwang In Kim, Jan Kautz, and Christian Theobalt
Preference and artifact analysis for video transitions of places
ACM Trans. Applied Perception 2013
Web page
Frank Lenzen, Kwang In Kim, Henrik Schäfer, Rahul Nair, Stephan Meister, Florian Becker, Christoph S. Garbe, and Christian Theobalt
Denoising strategies for time-of-flight data
Time-of-Flight Imaging: Algorithms, Sensors and Applications 2013
Paper
Kwang In Kim, James Tompkin, Martin Theobald, Jan Kautz, and Christian Theobalt
Match graph construction for large image databases
ECCV 2012
Paper | Supplemental | Link prediction code MATLAB
Miguel Granados, Kwang In Kim, James Tompkin, Jan Kautz, and Christian Theobalt
Background inpainting for videos with dynamic objects and a free-moving camera
ECCV 2012
Web page
Younghee Kwon, Kwang In Kim, Jin Hyung Kim, and Christian Theobalt
Efficient learning-based image enhancement: application to super-resolution and compression artifact removal
BMVC 2012
Web page
James Tompkin, Kwang In Kim, Jan Kautz, and Christian Theobalt
Videoscapes: exploring sparse, unstructured video collections
ACM Trans. Graphics (SIGGRAPH) 2012
Web page
Ahmed Elhayek, Carsten Stoll, Kwang In Kim, Hans-Peter Seidel, and Christian Theobalt
Feature-based multi-video synchronization with subframe accuracy
DAGM-OAGM 2012
Paper | Supplemental
Miguel Granados, James Tompkin, Kwang In Kim, Oliver Grau, Jan Kautz, and Christian Theobalt
How not to be seen – object removal from videos of crowded scenes
Computer Graphics Forum (Eurographics) 2012
Web page
Robert Herzog, Martin Čadík, Tunç O. Aydčin, Kwang In Kim, Karol Myszkowski, and Hans-P. Seidel
NoRM: no-reference image quality metric for realistic image synthesis
Computer Graphics Forum (Eurographics) 2012
Web page
Kwang In Kim and Younghee Kwon
Single-image super-resolution using sparse regression and natural image prior
IEEE Trans. PAMI 2010
Web page
Kwang In Kim, Florian Steinke, and Matthias Hein
Semi-supervised regression using Hessian energy with an application to semi-supervised dimensionality reduction
NIPS 2009
Web page
Pia Breuer, Kwang In Kim, Wolf Kienzle, Bernhard Schölkopf, and Volker Blanz
Automatic 3D face reconstruction from single images or video
Proc. FG 2008
Paper
Kwang In Kim and Younghee Kwon
Example-based learning for single-image super-resolution and JPEG artifact removal
Max Planck Institute for Biological Cybernetics Technical Report No. 173 2008
Paper
Christian Walder, Kwang In Kim, and Bernhard Schölkopf
Sparse multiscale Gaussian process regression
ICML 2008
Paper | Technical report (long version)
Kwang In Kim, Keechul Jung, and Jin Hyung Kim
Fast color texture-based object detection in images: application to license plate localization
Workshop on Support Vector Machines: Theory and Applications 2005
Kwang In Kim, Matthias O. Franz, and Bernhard Schölkopf
Iterative kernel principal component analysis for image modeling
IEEE Trans. PAMI 2005
Kwang In Kim, Younghee Kwon, Dongho Kim, and Jin Hyung Kim
Learning to remove JPEG artifacts
Proc. Korea Information Science Society Conference 2005
Kwang In Kim, Dongho Kim, and Jin Hyung Kim
Example-based learning for image superresolution
Proc. Tsinghua-KAIST Joint Workshop on Pattern Recognition 2004
Kwang In Kim, Matthias O. Franz, and Bernhard Schölkopf
Kernel Hebbian algorithm for single-frame super-resolution
Proc. Statistical Learning in Computer Vision 2004
Keechul Jung, Kwang In Kim, and Anil K. Jain
Text information extraction in images and video: a survey
Pattern Recognition 2004
Kwang In Kim, Keechul Jung, and Jin Hyung Kim
Texture-based approach for text detection in images using support vector machines and continuously adaptive mean shift algorithm
IEEE Trans. PAMI 2003
Kwang In Kim, Matthias O. Franz, and Bernhard Schölkopf
Kernel Hebbian algorithm for iterative kernel principal component analysis
Technical Report 109, Max Planck Institute for Biological Cybernetics 2003
Kwang In Kim, Dongho Kim, and Jin Hyung Kim
Example-based learning for image superresolution
Proc. Tsinghua-KAIST Joint Workshop on Pattern Recognition 2004
Kwang In Kim, Dongho Kim, and Jin Hyung Kim
Example-based learning for image superresolution
Proc. Tsinghua-KAIST Joint Workshop on Pattern Recognition 2004
Kwang In Kim, Dongho Kim, and Jin Hyung Kim
Example-based learning for image superresolution
Proc. Tsinghua-KAIST Joint Workshop on Pattern Recognition 2004
