Home

kwang_in_kimSmall

Associate Professor
School of Electrical & Computer Engineering
UNIST

Address:
E106 501-9, School of Electrical and Computer Engineering, UNIST
50 UNIST-gil, Eonyang-eup, Ulsan, 44919 Korea
email: kimki (at) unist.ac.kr

I am interested in advancing the understanding of how we can explore, make sense of, and interact with data. I contribute to this endeavor by exploiting and developing new techniques in machine learning, computer vision, computer graphics, and human-computer interaction.
My current research projects focus on algorithmic aspects of machine learning, especially in the context of semi-supervised learning, active learning, multi-task learning, and transfer learning and on capturing, processing, mining, and visualizing image and video data.

Informal Lectures: Basic Mathematical Objects in Machine Learning

We will discuss basic mathematical objects that are frequently used in machine learning.
When: 4pm-5pm, Wednesdays 3 July — 14 August 2019 except 10 July:

3 July 2019
17 July 2019
24 July 2019
31 July 2019
7 August 2019
14 August 2019

Where: E204
Lecture slides

Vita

Since 2019: Associate Professor, UNIST, School of Electrical & Computer 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 Institue for Biological Cybernetics, Empirical Inference Deptartment
2000-2002, 2004-2005: Post-doc, KAIST, A. I. Lab
2000: PhD, Kyungpook National University, Computer Engineering

Open positions

Postdoc in Machine Learning or Computer Vision
A postdoc position in machine learning or computer vision is available. Possible topics include (but are not limited to)

  • active learning in deep neural networks,
  • transfer learning,
  • semi-supervised learning,
  • machine learning for human-computer interaction.
  • human body pose or hand pose estimation.

Applicants should hold a PhD in machine learning, computer vision, or a related area. A strong publication record (in CVPR / ICCV / ECCV / NeurIPS / ICML) is expected.
If you are interested, please send me an email including your CV.
Please include `[postdoc]’ in the subject line.

PhD/Masters in Machine Learning or Computer Vision
Multiple PhD and Masters positions are available. Applicants should have first-class Bachelor’s degree in Mathematics, Computer Science, Physics, or a related subject field, and they must have a solid background in Mathematics including Linear Algebra, Vector Calculus, and Probability Theory, and have experience in programming, e.g., Python and Matlab.
If you are interested, please send me an email including your academic transcripts.
Please include `[PhD]’ or `[Masters]’ in the subject line.

Publications

  • D. Mehta, K. I. Kim, and C. Theobalt
    On implicit filter level sparsity in convolutional neural networks
    Proc. CVPR 2019
    Paper | Supplemental

     

  • S. Baek, K. I. Kim, and T.-K. Kim
    Pushing the envelope for RGB-based dense 3D hand pose estimation via neural rendering
    Proc. CVPR 2019
    Paper | Supplemental

     

  • K. I. Kim and H. J. Chang
    Joint manifold diffusion for combining predictions on decoupled observations
    Proc. CVPR 2019
    Paper

     

  • Y. A. Mejjati, C. Richardt, J. Tompkin, D. Cosker, and K. I. Kim
    Unsupervised attention-guided image-to-image translation
    Proc. NeurIPS 2018
    Paper | Webpage

     

  • A. Gokaslan, V. Ramanujan, D. Ritchie, K. I. Kim, and J. Tompkin
    Improving shape deformation in unsupervised image-to-image translation
    Proc. ECCV 2018
    Paper

     

  • Y. Saquil, K. I. Kim, and P. Hall
    Ranking CGANs: subjective control over semantic image attributes
    Proc. BMVC 2018
    Paper

     

  • J. Sock, K. I. Kim, C. Sahin, and T.-K. Kim
    Multi-task deep networks for depth-based 6D object pose and joint registration in crowd scenarios
    Proc. BMVC 2018
    Paper

     

  • K. I. Kim, J. Park, and J. Tompkin
    High-order tensor regularization with application to attribute ranking
    Proc. CVPR 2018
    Paper

     

  • Y. A. Mejjati, D. Cosker, and K. I. Kim
    Multi-task learning by maximizing statistical dependence
    Proc. CVPR 2018
    Paper

     

  • S. Baek, K. I. Kim, and T.-K. Kim
    Augmented skeleton space transfer for depth-based hand pose estimation
    Proc. CVPR 2018
    Paper

     

  • K. I. Kim, J. Tompkin, and C. Richardt
    Predictor combination at test time
    Proc. ICCV 2017
    Paper | Supplemental

     

  • J. Tompkin, K. I. Kim, H. Pfister, and C. Theobalt
    Criteria sliders: learning continuous database criteria via interactive ranking
    Proc. BMVC 2017
    PDF | Video

     

  • S. Baek, K. I. Kim, and T.-K. Kim
    Real-time online action detection forests using spatiotemporal contexts
    Proc. WACV 2017
    Paper

     

  • K. I. Kim
    Semi-supervised learning based on joint diffusion of graph functions and Laplacians
    Proc. ECCV 2016
    Webpage

     

  • Y. Zhang, T. Wilcockson, K. I. Kim, T. J. Crawford, H. G. Gellersen, and P. H. Sawyer
    Monitoring dementia with automatic eye movements analysis
    Proc. Intelligent Decision Technologies 2016
    Paper

     

  • K. I. Kim, J. Tompkin, H. Pfister, and C. Theobalt
    Context-guided diffusion for label propagation on graphs
    Proc. ICCV 2015
    Webpage

     

  • H. Rhodin, J. Tompkin, K. I. Kim, E. de Aguiar, H.-P. Seidel, and C. Theobalt
    Generalizing wave gestures from sparse examples for real-time character control
    ACM Trans. Graphics (Proc. SIGGRAPH Asia) 2015
    Webpage

     

  • A. Elhayek, C. Stoll, K. I. Kim, and C. Theobalt
    Outdoor human motion capture by simultaneous optimization of pose and camera parameters
    Computer Graphics Forum 2015
    Webpage

     

  • K. I. Kim, J. Tompkin, H. Pfister, and C. Theobalt
    Local high-order regularization on data manifolds
    Proc. CVPR 2015
    Webpage

     

  • K. I. Kim, J. Tompkin, H. Pfister, and C. Theobalt
    Semi-supervised learning with explicit relationship regularization
    Proc. CVPR 2015
    Webpage

     

  • Y. Kwon, K. I. Kim, J. Tompkin, J.-H. Kim, and C. Theobalt
    Efficient learning of image super-resolution and compression artifact removal with semi-local Gaussian processes
    IEEE Trans. PAMI 2015
    Webpage

     

  • H. Rhodin, J. Tompkin, K. I. Kim, K. Varanasi, H.-P. Seidel, and C. Theobalt
    Interactive motion mapping for real-time character control
    Computer Graphics Forum (Proc. Eurographics) 2014
    Webpage

     

  • K. I. Kim, J. Tompkin, and C. Theobalt
    Curvature-aware regularization on Riemannian submanifolds
    Proc. ICCV 2013
    Webpage

     

  • M. Granados, K. I. Kim, J. Tompkin, and C. Theobalt
    Automatic noise modeling for ghost-free HDR reconstruction
    ACM Trans. Graphics (Proc. SIGGRAPH Asia) 2013
    Webpage

     

  • J. Tompkin, M. H. Kim, K. I. Kim, J. Kautz, and C. Theobalt
    Preference and artifact analysis for video transitions of places
    ACM Trans. Applied Perception 2013
    Webpage

     

  • F. Lenzen, K. I. Kim, R. Nair, S. Meister, H. Schäfer, F. Becker, C. Garbe, and C. Theobalt
    Denoising strategies for time-of-flight data
    Time-of-Flight Imaging: Algorithms, Sensors and Applications 2013
    Paper

     

  • K. I. Kim, J. Tompkin, M. Theobald, J. Kautz, and C. Theobalt
    Match graph construction for large image databases
    Proc. ECCV 2012
    Paper | Supplemental | Link prediction code MATLAB

     

  • M. Granados, K. I. Kim, J. Tompkin, J. Kautz, and C. Theobalt
    Background inpainting for videos with dynamic objects and a free-moving camera
    Proc. ECCV 2012
    Webpage

     

  • Y. Kwon, K. I. Kim, J. H. Kim, and C. Theobalt
    Efficient learning-based image enhancement: application to super-resolution and compression artifact removal
    Proc. BMVC 2012
    Webpage

     

  • J. Tompkin, K. I. Kim, J. Kautz, and C. Theobalt
    Videoscapes: exploring sparse, unstructured video collections
    ACM Trans. Graphics (Proc. SIGGRAPH) 2012
    Webpage

     

  • A. Elhayek, C. Stoll, N. Hasler, K. I. Kim, H.-P. Seidel, and C. Theobalt
    Spatio-temporal motion tracking with unsynchronized cameras
    Proc. CVPR 2012
    Paper | Video

     

  • A. Elhayek, C. Stoll, K. I. Kim, H.-P. Seidel, and C. Theobalt
    Feature-based multi-video synchronization with subframe accuracy
    Proc. DAGM-OAGM 2012
    Paper | Supplemental

     

  • M. Granados, J. Tompkin, K. I. Kim, O. Grau, J. Kautz, and and C. Theobalt
    How not to be seen – object removal from videos of crowded scenes
    Computer Graphics Forum (Proc. Eurographics) 2012
    Webpage

     

  • R. Herzog, M. Cadik, T. O. Aydin, K. I. Kim, K. Myszkowski, and H.-P. Seidel
    NoRM: no-reference image quality metric for realistic image synthesis
    Computer Graphics Forum (Proc. Eurographics) 2012
    Webpage

     

  • K. I. Kim and Y. Kwon
    Single-image super-resolution using sparse regression and natural image prior
    IEEE Trans. PAMI 2010
    Webpage

     

  • K. I. Kim, F. Steinke, and M. Hein
    Semi-supervised regression using Hessian energy with an application to semi-supervised dimensionality reduction
    Proc. NIPS 2009
    Webpage

     

  • P. Breuer, K. I. Kim, W. Kienzle, B. Schölkopf, and V. Blanz
    Automatic 3D face reconstruction from single images or video
    Proc. FG 2008
    Paper

     

  • K. I. Kim and Y. 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

     

  • C. Walder, K. I. Kim, and B. Schölkopf
    Sparse multiscale Gaussian process regression
    Proc. ICML 2008
    Paper (long version)

     

  • K. I. Kim, K. Jung, and J. H. Kim
    Fast color texture-based object detection in images: application to license plate localization
    Proc. Workshop on Support Vector Machines: Theory and Applications 2005

     

  • K. I. Kim, M. O. Franz, and B. Schölkopf
    Iterative kernel principal component analysis for image modeling
    IEEE Trans. PAMI 2005

     

  • K. I. Kim, Y. Kwon, D. Kim, and J. H. Kim
    Learning to remove JPEG artifacts
    Proc. Korea Information Science Society Conference 2005

     

  •