|
|
*We publish in the top journals of computer science and electrical engineering studies, such as TPAMI (impact factor: 5.96) and IJCV (impact factor: 5.35), and in the most prestigious conferences including CVPR, ECCV, ICCV, NIPS and BMVC. See selected papers.
*See Google Scholar for citations.
|
|
|
2013
|
|
|
T.H. Yu, T-K. Kim, and R. Cipolla, Unconstrained Monocular 3D Human Pose Estimation by Action Detection and Cross-modality Regression Forest,
Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Portland, Oregon, USA, 2013.
Download: pdf [12,522 KB] [Demo on YouTube video]
|
|
|
|
2012
|
|
|
D. Tang, Y. Liu and T-K. Kim, Fast Pedestrian Detection by Cascaded Random Forest with Dominant Orientation Templates,
Proc. of British Machine Vision Conference (BMVC), Surrey, UK, 2012.
Download: pdf [2,492 KB] [Demo on YouTube video]
|
|
|
K. Lee, T-K. Kim and Y. Demiris, Learning Reusable Task Components using Hierarchical Activity Grammars with Uncertainties,
Proc. of IEEE International Conference on Robotics and Automation (ICRA), Saint Paul, Minnesota, USA, May 2012.
Download: pdf [700 KB] [Project webpage]
|
|
|
K. Lee, T-K. Kim and Y. Demiris, Learning Action Symbols for Hierarchical Grammar Induction,
Proc. of International Conference on Pattern Recognition (ICPR), Tsukuba Science City, Japan, Nov 2012 (oral).
Download: pdf [1,325 KB]
|
|
|
C. Xiong and T-K. Kim, Set-Based Label Propagation of Face Images,
Proc. of IEEE International Conference on Image Processing (ICIP), Orlando, Florida, USA, Oct 2012.
Download: pdf [575 KB]
|
|
|
|
2011
|
|
|
Y. Chen, T-K. Kim and R. Cipolla, Silhouette-based Object Phenotype Recognition Using 3D Shape Priors,
Proc. IEEE 13th Int. Conf. on Computer Vision (ICCV), Barcelona, Spain, November 2011.
Download: pdf [1,946 KB] [Longer version] [Slides]
|
|
|
T-K. Kim, I. Budvytis, R. Cipolla, Making a Shallow Network Deep: Conversion of a Boosting Classifier into a Decision Tree by Boolean Optimisation,
International Journal of Computer Vision (IJCV), 100(2):203-215, 2012 (BMVC10 special issue, online first published, June 2011).
Download: pdf [1,643 KB]
|
|
|
T-K. Kim and R. Cipolla, Multiple Classifier Boosting and Tree-Structured Classifiers,
a bookchapter in Machine Learning for Computer Vision, Springer, 2012 (ISBN 978-3-642-28660-5).
Download: pdf [1,161 KB]
|
|
|
|
2010
|
|
|
T-K. Kim, B. Stenger, J. Kittler and R. Cipolla, Incremental Linear Discriminant Analysis Using Sufficient Spanning Sets and Its Applications,
International Journal of Computer Vision (IJCV), 91(2):216-232, Jan 2011.
Download: pdf [2,101 KB] [Code and dataset]
|
|
|
U. Bonde, T-K. Kim, K.R. Ramakrishnan, Randomised Manifold Forests for Principal Angle based Face Recognition, Proc. of Asian Conf. on Computer Vision (ACCV), Queenstown, New Zealand, 2010.
Download: pdf [431 KB]
|
|
|
Y. Chen, T-K. Kim, R. Cipolla, Inferring 3D Shapes and Deformations from Single Views, Proc. of European Conference on Computer Vision (ECCV), Crete, Greece, 2010.
Download: pdf
[2,336 KB] [Technical Report] [Slides] [Demo on YouTube] |
|
|
T.H. Yu, T-K. Kim, R. Cipolla, Real-time Action Recognition by Spatiotemporal Semantic and Structural Forest, Proc. of British Machine Vision Conference (BMVC), Aberystwyth, UK, 2010 (oral, accept rate=30/345).
Download: pdf
[5,245 KB] [Slides] [Demo on YouTube video] |
|
|
T-K. Kim*, I. Budvytis*, R. Cipolla, Making a Shallow Network Deep: Growing a Tree from Decision Regions of a Boosting Classifier, Proc. of British Machine Vision Conference (BMVC), Aberystwyth, UK, 2010 (oral, accept rate=30/345). *indicates equal contribution.
Download: pdf [3,283 KB] [Technical Report] [Slides] [Demo on YouTube] |
|
|
T-K. Kim, T. Woodley, B. Stenger, R. Cipolla, Online Multiple Classifier Boosting for Object Tracking, Proc. of IEEE CVPR workshop on Online Learning for Computer Vision, San Francisco, USA, Jun 2010 (oral).
Download: pdf [932 KB] [Technical Report] [Slides] [Demo on YouTube] |
|
|
|
2009
|
|
|
T-K. Kim, J. Kittler, R. Cipolla, On-line Learning of Mutually Orthogonal Subspaces for Face Recognition by Image Sets,
IEEE Trans. on Image Processing (TIP),
19(4):1067-1074, April 2010.
Download: pdf [827 KB] |
|
|
K.
Chaiyasarn, T-K. Kim, R. Cipolla, K. Soga, Image
Mosaicing via Quadric Surface Estimation with Priors
for Tunnel Inspection, Proc. of IEEE
International Conference on Image Processing (ICIP),
Cairo, Egypt, Nov 2009.
Download: pdf
[3,990 KB] |
|
|
B.
Stenger, T. Woodley, T-K. Kim, R. Cipolla, A
Vision-based Interface for Display Interaction, HCI
2009 - 23rd BCS Conference on Human-Computer
Interaction, Cambridge, UK, Sep 2009.
Download: pdf [1,008 KB] |
|
|
Navid
Mavaddat, Tae-Kyun Kim and Roberto Cipolla, Design
and evaluation of features that best define text in
complex scene images, Proc. of IAPR
Conf. on Machine Vision Applications (MVA),
Japan, May 2009.
Download: pdf
[1,260 KB] |
|
|
|
2008
|
 |
|
Tae-Kyun
Kim and Roberto Cipolla, MCBoost: Multiple
Classifier Boosting for Perceptual Co-clustering of
Images and Visual Features, In Advances in
Neural Information Processing Systems (NIPS),
Vancouver, Canada, Dec. 2008.
Download: pdf
[477 KB] [slide] |
|
|
Tae-Kyun
Kim and Roberto Cipolla, Canonical Correlation
Analysis of Video Volume Tensors for Action
Categorization and Detection, IEEE Transactions
on Pattern Analysis and Machine Intelligence (TPAMI),
31(8):1415-1428, 2009. (Regular paper).
Download: pdf
[780 KB] |
 |
|
B.
Stenger, T. Woodley, T-K. Kim, C. Hernandez, R.
Cipolla, AIDIA - Adaptive Interface for Display
InterAction, Proc. of British Machine Vision
Conference (BMVC), Leeds, UK, 2008.
Download: pdf
[1,009 KB] [Demo at IFA 2008 on YouTube video] |
|
|
|
2007
|
|
|
Tae-Kyun
Kim and Roberto Cipolla, Gesture Recognition
Under Small Sample Size, In Proc. 8th Asian
Conf. on Computer Vision (ACCV) (Lecture
Notes in Computer Science),
Tokyo, Japan, November 2007. (Oral,
8.4% acceptance ratio).
Download: pdf
[4,348 KB] |
 |
|
Shu-Fai
Wong, Tae-Kyun Kim and Roberto Cipolla, Learning
Motion Categories Using Both Semantic and Structural
Information, In Proc. of IEEE Conference on
Computer Vision and Pattern Recognition (CVPR),
Minneapolis, MN, 2007.
Download: pdf
[593
KB] |
 |
|
Tae-Kyun
Kim, Shu-Fai
Wong and Roberto Cipolla, Tensor Canonical
Correlation Analysis for Action Classification, In
Proc. of IEEE Conference on Computer Vision and
Pattern Recognition (CVPR), Minneapolis,
MN, 2007.
Download: pdf
[639 KB] |
 |
|
Tae-Kyun
Kim, Shu-Fai
Wong, Bjorn Stenger, Josef Kittler and Roberto
Cipolla, Incremental Linear Discriminant Analysis
Using Sufficient Spanning Set Approximations, In
Proc. of IEEE Conference on Computer Vision and
Pattern Recognition (CVPR), Minneapolis,
MN, 2007.
Download: pdf
[468 KB] |
 |
|
Tae-Kyun
Kim, Josef
Kittler and Roberto Cipolla, Discriminative
Learning and Recognition of Image Set Classes Using
Canonical Correlations, IEEE Transactions on
Pattern Analysis and Machine Intelligence (TPAMI),
Vol.29, No.6, 2007 (Regular paper).
Download: pdf
[5,977 KB] |
|
|
Tae-Kyun
Kim, Ognjen
Arandjelovic and Roberto Cipolla, Boosted Manifold
Principal Angles for Image Set-Based Recognition, Pattern
Recognition, Vol.40, No.9, pp.2475-2484, 2007.
Download: pdf
[992 KB] |
|
|
|
2006
|
|
|
Tae-Kyun
Kim, Josef Kittler and Roberto Cipolla, Learning
Discriminative Canonical Correlations for Object
Recognition with Image Sets, In Proc. of European
Conference on Computer Vision (ECCV) (Lecture Notes
in Computer Science), pages 251-262, Graz, Austria,
2006. (about 20% acceptance ratio).
Download: pdf
[460 KB]
|
|
|
Tae-Kyun
Kim, Josef
Kittler, and Roberto Cipolla, Incremental Learning of
Locally Orthogonal Subspaces for Set-based Object
Recognition, Proc. IAPR British Machine Vision
Conference (BMVC), pages 559-568, Edinburgh,
UK, Sept 2006. (25% acceptance rate).
Download: pdf
[478 KB]
|
|
|
Tae-Kyun Kim and Josef Kittler, Design and
Fusion of Pose Invariant Face Identification Experts, IEEE
Transactions on Circuit and System for Video Technology, Vol.16,
No.9, pp.1096-1106, 2006.
Download: pdf
[2,342 KB] |
|
|
|
2005
|
 |
|
Tae-Kyun
Kim, Ognjen
Arandjelovic and Roberto Cipolla, Learning
over Sets using Boosted Manifold Principal Angles (BoMPA),
IAPR British Machine Vision Conference (BMVC),
pp.779-788, Oxford, U.K., Sept 2005.
Download: pdf
[283 KB] |
 |
|
Tae-Kyun
Kim and
Josef Kittler, Locally Linear Discriminant
Analysis for Multi-modally Distributed Classes for
Face Recognition with a Single Model Image, IEEE
Transactions on Pattern Analysis and Machine
Intelligence (TPAMI), Vol.27, No.3,
pp.318-327, 2005 (Regular paper).
Download: pdf
[3,947
KB] (See
Technical Report) |
 |
|
Tae-Kyun
Kim, Hyunwoo
Kim, Wonjun Hwang and Josef Kittler, Component-based
LDA Face Description for Image Retrieval and MPEG-7
Standardisation, Image and Vision Computing,
Vol.23, No.7, pp.631-642, 2005.
Download: pdf
[475 KB] |
 |
|
Tae-Kyun
Kim and Josef
Kittler, Composite Support Vector Machines with the
Extended Discriminative Features For Accurate Face
Detection, IEICE Transactions on Information
& Systems, Vol.E88-D, No.10, Oct 2005.
Download: pdf
[666 KB] |
|
|
|
2004
|
|
Tae-Kyun
Kim,
Hyunwoo Kim, Wonjun Hwang and Josef Kittler, Independent
Component Analysis in a Local Facial Residue Space for
Face Recognition , Pattern Recognition, Vol.37,
No.9, pp.1873-1885, 2004.
Download: pdf
[618 KB]
Tae-Kyun
Kim and
Josef Kittler, Combining Classifier for Face
Identification at Unknown Views with a Single Model Image,
Joint IAPR International Workshops on Syntactical and
Structural Pattern Recognition and Statistical Pattern
Recognition (SSPR+SPR) (Lecture
Notes in Computer Science),
Lisbon, Portugal, August, 2004.
Download: pdf
[628 KB]
Wonjun
Hwang, Tae-Kyun Kim, and Seok-Cheol Kee,
LDA with Subgroup PCA Method for Facial Image Retrieval,
5th International Workshop on Image Analysis for
Multimedia Interactive Services(WIAMIS), Portugal,
April 2004.
Download:
pdf
[387 KB]
Hyunwoo
Kim, Tae-Kyun Kim, et.al., A
Recursive Matching Method for Content-based Image
Retrieval, 5th International Workshop on Image
Analysis for Multimedia Interactive Services(WIAMIS), Portugal,
April 2004.
Download: pdf
[238 KB]
|
|
|
2003
|
|
Tae-Kyun
Kim,
Hyunwoo Kim, Wonjun Hwang, Seok-Cheol Kee and Josef
Kittler, Independent Component Analysis in a
Facial Local Residue Space, Proc. IEEE
Computer Vision and Pattern Recognition (CVPR),
Madison, Wisconsin, 2003. (Oral presentation, 6%
acceptance ratio).
Download: pdf
[879 KB]
Tae-Kyun
Kim,
Josef Kittler, Hyun-Chul Kim and Seok-Cheol Kee, Discriminant
Analysis by Multiple Locally Linear Transformations,
Proc. IAPR British Machine Vision Conference (BMVC),
East Anglia, Norwich, UK, 2003.
Download:
pdf
[368 KB]
Tae-Kyun
Kim,
Hyunwoo Kim, Wonjun Hwang, Seok-Cheol Kee and Josef
Kittler, Face Description based on Decomposition
and Combining of a Facial Space with LDA, Proc.
IEEE International Conference on Image Processing (ICIP),
Spain, 2003.
Download:
pdf
[221 KB]
Hyunwoo
Kim, Tae-Kyun Kim, Wonjun Hwang, Seok-Cheol Kee,
and Sang-Ryong Kim, A Recursive Matching Method for
Content-based Image Retrieval, WSEAS Transactions
on Computers, Vol.2, No.4, pp.1035-1039, 2003.
Download: pdf [0 KB]
|
|
|
2002
|
|
Young
Hoon Sung, Tae-Kyun Kim, Seok Cheol Kee, Hierarchical
Combination of Face/Non-face Classifiers based on Gabor
Wavelet and Support Vector Machines , Proc.
IAPR Workshop on Machine Vision Applications (MVA),
Japan, 2002.
Download: pdf
[2,275 KB]
Tae-Kyun
Kim,
Hyunwoo Kim, Wonjun Hwang, Seok Cheol Kee, Jong Ha Lee, Component-based
LDA Face Descriptor for Image Retrieval , Proc.
IAPR British Machine Vision Conference (BMVC),
Cardiff, UK, Sept. 2-5, 2002.
Download: pdf
[220 KB]
Tae-Kyun
Kim,
Donggeon Kong and Sang-Ryong Kim, Learning a
Dicision Boundary for Face Detection , Proc.
IEEE International Conference on Image Processing (ICIP),
Rochester, New York, Sept. 22-25, 2002.
Download: pdf
[218 KB]
Peter
Bazanov, Tae-Kyun Kim, Seok Cheol Kee and
Sang Uk Lee, Hybrid and Parallel Face Classifier
based on Artificial Neural Networks and Principal
Component Analysis , Proc. IEEE International
Conference on Image Processing (ICIP),
Rochester, New York, Sept. 22-25, 2002.
Download: pdf
[755 KB]
Tae-Kyun
Kim,
Sung-Uk Lee, Jong-Ha Lee, Seok-Cheol Kee and Sang-Ryong
Kim, Integrated Approach of Multiple Face
Detection for Video Surveillance , Proc. IAPR/IEEE
International Conference on Pattern Recognition (ICPR),
Quebec, Canada, August 11-15, 2002.
Download: pdf
[223 KB]
|
|
|
Etc
|
|
Tae
Kyun Kim,
Seok Cheol Kee and Sang Ryong Kim, Real-Time
Normalization and Feature Extraction of 3D Face Data Using
Curvature Characteristics , The 10th IEEE
International Workshop on Robot-Human Interactive
Communication (ROMAN), Paris, France, 2001.
Download: pdf
[1,203 KB]
Tae
Kyun Kim,
Chang Kyu Choi and Sang Ryong Kim, Face Detection
Using Consecutive Bootstrapping ICA , The 6th
Biennial International Symposium on Communications (ISCOM),
Tainan, Taiwan, 2001.
Download: pdf
[0 KB]
Tae
Kyun Kim,
Young Jin Lee, Myung Jin Chung, Self localization
of a mobile robot by recognizing color objects in an
omnidirectional image, The 5th International
Symposium on Artificial Life and Robotics (AROB),
Japan, 2000.
Download:
pdf [0 KB]
Tae-Kyun
Kim,
YoungJin Lee and MyungJin Chung, Global
Positioning of a Mobile Robot based on Color
Omnidirectional Image Understanding, KIEE
(Korean Institute of Electrical Engineers) Transactions, Vol.
49D, No. 6, Jun. 2000.
|
|
|
International
Patents & Standardization
|
|
|
*
I have co-authored 6 MPEG-7 (ISO/IEC JTC1/SC29/WG11)
standard documents and more than 12 international patents.
The joint proposal of Samsung and NEC corporation for the
face image descriptor, for which I have developed main
algorithms, is the international
standard of ISO/IEC
JTC1/SC29.
|
|
|
Selected
MPEG-7 proposals (including the winning proposal):
|
|
- Hyunwoo
Kim, Tae-Kyun Kim, Jong Ha Lee, Wonjun Hwang,
Seok Cheol Kee, Component-based 2nd-order ICA Face
Descriptor, ISO/IEC JTC1/SC21/WG11 MPEG2002/M7953,
Jeju Island, March 2002.
- Tae-Kyun
Kim,
Hyunwoo Kim, Wonjun Hwang, Seok Cheol Kee, Component-based
LDA Face Descriptor, ISO/IEC JTC1/SC29/WG11
MPEG2002/M8243, Fairfax, USA, May 2002.
- Toshio
Kamei, Akio Yamada, Tae-Kyun Kim, Hyunwoo Kim,
Wonjun Hwang, Seok Cheol Kee, Advanced Face
Descriptor Using Fourier and Intensity LDA Features,
ISO/IEC JTC1/SC21/WG11 MPEG2002/M8998, Shanghai,
Oct 2002.
- Toshio
Kamei, Akio Yamada, Tae-Kyun Kim, Hyunwoo Kim,
Wonjun Hwang, and Seok-Cheol Kee, CE report on Advanced
Face Recognition Descriptor, ISO/IEC JTC1/SC29 WG11
MPEG-9178, Awaji, Japan, Dec., 2002.
- Wonjun
Hwang, Hyunwoo Kim, Tae-Kyun Kim, Seok-Cheol Kee,
and Jongha Lee, Result of Component-based 2nd-order ICA
Face Descriptor, ISO/IEC JTC1/SC29 WG11 MPEG-8270,
Fairfax, USA, May, 2002.
- Hyunwoo
Kim, Wonjun Hwang, Tae-Kyun Kim, and Seok-Cheol
Kee, Component-Based LDA Face Descriptor using Pose
Estimation, ISO/IEC JTC1/SC29 WG11 MPEG-8572,
Klagenfurt, Austria, Jul., 2002.
|
|
|
Selected International (USA/Europe/Japan) Patents (*from
http://www.patentstorm.us/, U.S. patents only):
|
|
- Hyunwoo
Kim, Tae-Kyun Kim, Seok-Cheol Kee, Jongha Lee,
Wonjun Hwang, Changkyu Choi, Method and apparatus of
recognizing face using 2nd-order independent component
analysis (ICA)/principal component analysis (PCA), US
Patent 7164781.
- Hyunwoo
Kim, Tae-Kyun Kim, Seok-Cheol Kee, Jongha Lee,
Wonjun Hwang, Method and apparatus of recognizing face
using component-based 2nd-order principal component
analysis (PCA)/independent component analysis (ICA), US
Patent 7254257.
- Hyunwoo
Kim, Tae-Kyun Kim, Wonjun Hwang, Seok-Cheol Kee,
Face recognition method and apparatus using
component-based face descriptor, US Patent 7203346.
- Hyunwoo
Kim, Tae-Kyun Kim, Wonjun Hwang, Seok-Cheol Kee,
Image retrieval method and apparatus using iterative
matching, US Patent 7298931.
- Inmyung
Cho, Tae-Kyun Kim, Apparatus and method for
providing security in a base or mobile station by using
detection of face information, US Patent 7146025.
- Seok-Cheol
Kee, Tae-Kyun Kim, Face recognition method using
artificial neural network and apparatus thereof, US
Patent 7295687.
- Tae-Kyun
Kim, Jongha Lee, System and method for detecting and
tracking a plurality of faces in real time by
integrating visual ques, US Patent 7352880.
- Tae-Kyun
Kim, Inmyung Cho, Jong Ha Lee,
Illumination-invariant object tracking method and image
editing system using the same, US
Patent 7171023.
- T.
Kamei, Hyunwoo Kim, Tae-Kyun Kim, Wonjun Hwang,
Seok-Cheol Kee, Method
and apparatus for extracting feature vector used for
face recognition and retrieval, US
Patent 7391889.
- Tae-Kyun
Kim, Hyunwoo Kim, Seok Cheol Kee, Wonjun Hwang,
Component-based LDA (Linear Discriminant Analysis) Face
Descriptor, P20020023255.
- Tae-Kyun
Kim, Method
and system for face detection using pattern classifier,
US Patent 7447338.
- Young
Hoon Sung, Tae-Kyun Kim, Human Detection Method
and Apparatus, US
Patent 7409091.
- Tae-Kyun Kim,
Face identification apparatus, medium, and method, US
Patent Application 20070086627.
- Tae-Kyun
Kim, Method for feature
extraction using local linear transformation functions,
and method and apparatus for image recognition employing
the same, US
Patent Application 20050078869.
|
|
|
Technical
Reports & Theses
|
|
Yu Chen, Tae-Kyun Kim, Roberto Cipolla, Inferring 3D Shapes and Deformations from Single Views, Technical report, CUED/F-INFENG/TR654, Dept. of Engineering, Univ. of Cambridge, July 2010.
Download:
pdf [8,298 KB]
Vijay Badrinarayanan, Tae-Kyun Kim, Roberto Cipolla, Semantic Label Propagation in Video Sequences, Cambridge-Toyota project progress report,
23 Oct 2009.
Download:
pdf
[KB]
Tae-Kyun Kim, Ignas Budvytis, Roberto Cipolla, Making a Shallow Network Deep: Growing a Tree from Decision Regions of a Boosting Classifier, Technical report, CUED/F-INFENG/TR633, Dept. of Engineering, Univ. of Cambridge, June 2009.
Download:
pdf [1,877 KB]
Tae-Kyun Kim, Tom Woodley, Bjorn Stenger, Roberto Cipolla, Online Multiple Classifier Boosting for Object Tracking, Technical report, CUED/F-INFENG/TR631, Dept. of Engineering, Univ. of Cambridge, June 2009.
Download:
pdf [1,114 KB]
Tae-Kyun
Kim, PhD
Thesis, Dept. of Engineering, Univ. of Cambridge, 2007.
Download: pdf
[5,348
KB]
Tae-Kyun Kim, Locally
Linear Discriminant Analysis for Multi-modally Distributed
Classes for Face Recognition with a Single Model Image,
Technical Report, Dept. of Engineering, Univ. of
Cambridge, Apr 2007.
Download: pdf
[1,249 KB]
Tae-Kyun
Kim, First
Year PhD Report, Dept. of Engineering, Univ. of Cambridge,
Jan 2006.
Download:
pdf
[0 KB]
|
|
|
