Jiri MATAS
My old home page at U. of Surrey
Professor
The Center for Machine Perception
Department of Cybernetics
Faculty of Electrical Engineering
Czech Technical University, Prague
Karlovo namesti 13, 121 35 Praha 2, Czech Republic
Office: G1 (building G, room 1), see map
Tel.: +420-603-140180, Fax:+420-2-24357385
E-mail: surname@cmp.felk.cvut.cz
ORCID: 0000-0003-0863-4844
CV:       Publications. Demos:
(mostly outdated)
Awards Students

Teaching: Pattern Recognition, Digital Image Processing, Computer Vision Methods, Vision and Sports Summer School
Service: Editor-in-Chief of IJCV, Associate Editor-in-Chief of IEEE PAMI (2009-2013), Programme Chair ECCV'04, ECCV'16, CVPR'07, General Chair CVPR'22, ECCV'22.

Research: Visual recognition, Tracking, Image Retrieval, Sequential decision-making, Pattern recognition, Wide-baseline Matching, RANSAC, Face detection and recognition, Biometric authentication, Colour-based recognition, Hough Transform.

Awards:
2022  Best paper award, @ BMVC, 33rd British Machine Vision Conference,
A. Lukezic, Z. Trojer , J. Matas, M. Kristan Trans2k: Unlocking the Power of Deep Models for Transparent Object Tracking
2019  Honorable Mention for Outstanding Contribution Award, @ GCPR, 41st German Conf. on Pattern Recognition,
R. Rozumnyi, J. Kotera, F. Sroubek J. Matas: Non-Causal Tracking by Deblatting
2017  Best paper award , 3rd International Workshop on Robust Reading @ Asian Conf. on Comp. Vision, M. Busta, Y. Patel, J. Matas: E2E-MLT: an Unconstrained End-to-End Method form Multi-Language Scene Text
2017  First place in the ICDAR Robust Reading Multi-language Task 2 - Script identification. Yash Patel, Michal Busta, Lukas Neumann and Jiri Matas
2017  Attila Kuba Prize:
D. Barath, J. Matas, and L. Hajder: Multi-H: Efficient Recovery of Tangent Planes in Stereo Images
2015  Best Paper Prize at ICDAR, the 13th International Conference on Document Analysis and Recognition (Nancy, France):
L. Neumann and Matas J.: Efficient Scene Text Localization and Recognition with Local Character Refinement
2013  Best Paper Prize at IVCNZ 2013:
J. Pritts, O. Chum, J. Matas, Approximate Models for Fast and Accurate Epipolar Geometry Estimation
2013  Best Student Paper Prize at ICDAR, the 12th International Conference on Document Analysis and Recognition (Washington, USA): L. Neumann and Matas J.: On Combining Multiple Segmentations in Scene Text Recognition , presentation.
2013  Best Paper Prize at the Scandianavian Conference on Image Analysis SCIA : T. Vojir, J. Noskova and J. Matas.Robust Scale-Adaptive Mean-Shift for Tracking , presentation.
2011  Zdenek Kalal, a PhD student co-supervised by me and K. Mikolajczyk at the U. of Surrey, was awarded the ICT Pioneers Prize in the "Technology Everywhere" category for the TLD tracker developed during the PhD.
2010  My student Lukas Neumann won the Czech Master Thesis of Year 2010 in Informatics award. The work is summarized in our ACCV'10 paper A method for text localization and recognition in real-world images
2010  Outstanding Reviewer, CVPR 2010.
2009  My student (co-supervised with T. Svoboda) Karel Zimmermann was awarded the CSKI prize for the best PhD work in 2008 for his PhD thesis Fast Learnable Methods for Object Tracking. See the related PAMI paper .
2007  Best Paper Prize at Asian Conference on Computer Vision (ACCV). J. Sochman and J. Matas: Learning A Fast Emulator of a Binary Decision Process.
2006  My student S. Obdrzalek won the Doctorandus prize for the most innovative PhD work in the Czech Rep.
2005  Best paper prize at BMVC: J. Matas, S. Obdrzalek: Sub-linear Indexing for Large Scale Object Recognition.
2005  The CMP Team I advised of finished second in the ICCV 2005 Contest.
2004  Best scientific result prize of the Czech Technical University Prague.
2002  Best paper prize at BMVC: J. Matas et al.: Robust wide baseline stereo from maximally stable extremal regions.
1987  MSc thesis awarded the Chancellor's prize.

Students:
current: Radim Spetlik, Michal Neoral, Jonas Serych, Filip Naiser, Yash Patel [Google Scholar],
former: Dmytro Mishkin (PhD'21, thesis awarded the Rector's Prize and the Dean's Prize), Tomas Hodan (PhD'21, thesis awarded the Rector's Prize), Milan Sulc (PhD'21), Maksym Ivashechkin (MSc'21), Denys Rozumnyi (MSc'19), Tomas Vojir (PhD'18), Lukas Neumann (MSc'10, PhD'17), Andrej Mikulik (MSc'09, PhD'15), Michal Perdoch (MSc'04, PhD'11), Zdenek Kalal (MSc'05, PhD'11), Lukas Zich (MSc), Jura Trefny (MSc), Jan Sochman (Phd'09), Karel Zimmermann(PhD'08,MSc'04), Stepan Obdrzalek (PhD'07), Ondra Chum (PhD'05), Mirek Hamouz (PhD'05), Kenneth Jonsonn (PhD'02), Ulises Ramos Sanchez (PhD'01), Yongping Li (PhD'01)

Publications:
@ DBLP
Google Scholar
@ Arnetminer
@ MS Academic

Bibliometrics:
H-index: 64
(WoS)
H-index: 92
(Google Scholar)
Citations: ~26000
(WoS)
Citations: ~62000
(Google Scholar)
2018
2017
2016
till 2015
Selected: (recent work is best found on arXiv)

Serych, J. and Matas, J.
Visual Coin-Tracking: Tracking of Planar Double-Sided Objects
In GCPR 2019
Kart U, Lukezic A, Kristan M, Kamarainen JK, Matas J.
Object Tracking by Reconstruction with View-Specific Discriminative Correlation Filters.
In CVPR 2019
Barath D, Matas J, Noskova J.
MAGSAC: marginalizing sample consensus.
In CVPR 2019
Qian Y, Kamarainen JK, Nikkanen J, Matas J.
On Finding Gray Pixels.
In CVPR 2019
D. Mishkin, F. Radenovic and J.Matas.
Repeatability is not enough: Learning affine regions via discriminability.
In ECCV 2018
Hodan T, et al.
BOP: Benchmark for 6D object pose estimation
In ECCV 2018
Barath D, Matas J.
Multi-class model fitting by energy minimization and mode-seeking
In ECCV 2018
Barath D, Matas J.
Graph-cut RANSAC
In CVPR 2018
Neoral M, Sochman J, Matas J
Continual Occlusion and Optical Flow Estimation
In ACCV 2018,
(ArXiv:1811.01602v1 version)
Busta M, Patel Y, Matas J.
E2E-MLT-an unconstrained end-to-end method for multi-language scene text
In ACCV 2018,
(arXiv:1801.09919 version)
Lukezic A, Cehovin-Zajc L, Vojir T, Matas J, Kristan M
FuCoLoT -- A Fully-Correlational Long-Term Tracker
In ACCV 2018,
(arXiv:1711.09594v2 version)
Mishchuk A, Mishkin D, Radenovic F, Matas J
Working hard to know your neighbor's margins: Local descriptor learning loss
In NIPS 2017,
Sulc M, Matas J.
Fine-grained recognition of plants from images.
Plant methods. 2017 Dec;13(1):115
open access
Smid, M and Matas, J
Rolling Shutter Camera Synchronization with Sub-millisecond Accuracy.
In VISIGRAPP (4: VISAPP) 2017,
(arXiv:1902.11084 version)
Hodan T, Haluza P, Obdrzalek S, Matas J, Lourakis M, Zabulis X.
T-LESS: An RGB-D dataset for 6D pose estimation of texture-less objects
In WACV 2017
(arXiv:1701.05498v1 version)
Rozumnyi D, Kotera J, Sroubek F, Novotny L, Matas J.
The world of fast moving objects
In CVPR 2017
Lukezic A, Vojir T, Cehovin Zajc L, Matas J, Kristan M
Discriminative correlation filter with channel and spatial reliability
In CVPR 2017
Radenovic F, Schonberger JL , Ji D , Frahm JM , Chum O, Matas J
From dusk till dawn: Modeling in the dark
In CVPR 2016
D. Mishkin, M. Perdoch and J.Matas.
MODS: Fast and Robust Method for Two-View Matching.
Computer Vision and Image Understanding. 2015 Dec 1;141:81-93.
L. Neumann and J. Matas
Efficient Scene Text Localization and Recognition with Local Character Refinement
In ICDAR
, 2015, . * Awarded the Best Paper Prize
D. Mishkin, M. Perdoch, J.Matas and K. Lenc.
WxBS: Wide Baseline Stereo Generalizations.
Proc. of the British Machine Vision Conference 2015
L. Neumann and J. Matas
On Combining Multiple Segmentations in Scene Text Recognition
Proc. of 12th Intl. Conf. on Doc. Anal. and Recog. (ICDAR), 2013. ,
* Awarded the Best Student Paper Prize
H. Cai, T. Werner and J. Matas.
Fast Detection of Multiple Textureless 3-D Objects.
Proc. of the 9th Intl. Conf. on Computer Vision Systems (ICVS), 2013.
T. Vojir, J. Noskova and J. Matas.
Robust Scale-Adaptive Mean-Shift for Tracking
Proc. Scandinavian Conf. on Image Analysis (SCIA), 2013. *Awarded the Best Paper Prize
Z. Kalal, K. Mikolajczyk and J. Matas.
Tracking-Learning-Detection
IEEE T. PAMI. 34(7): 1409-1422, July 2012
L. Neumann and Matas J.
Real-time scene text localization and recognition
In CVPR , 2012. .
L. Ellis, N. Dowson, J. Matas, and R. Bowden.
Linear regression and adaptive appearance models for fast simultaneous modelling and tracking.
International Journal of Computer Vision (2011) 95:154-179
L. Neumann, J. Matas.
A method for text localization and recognition in real-world images.
In ACCV 2010.
O. Chum, J. Matas.
Planar Affine Rectification from Change of Scale.
In ACCV 2010.
A. Mikulik, M. Perdoch, O. Chum, J. Matas.
Learning a Fine Vocabulary.
In ECCV (3) 2010: 1-14
J. Cech, J. Matas, M. Perdoch.
Efficient Sequential Correspondence Selection by Cosegmentation.
IEEE T. PAMI. 32(9): 1568-1581, September 2010 [data and code]
O. Chum and J. Matas.
Unsupervised discovery of co-occurrence in sparse high dimensional data. In CVPR 2010

H. Grabner, J. Matas, L. van Gool, and P. Cattin.
Tracking the invisible: Learning where the object might be. In CVPR 2010

Zdenek Kalal, Jiri Matas, and Krystian Mikolajczyk.
P-n learning: Bootstrapping binary classifiers by structural constraints.
In CVPR 2010

O. Chum, J. Matas.
Large-Scale Discovery of Spatially Related Images.
IEEE Trans. Pattern Analalysis and Mach. Intell. 32(2): 371-377, February 2010

J. Sochman, J. Matas.
Learning Fast Emulators of Binary Decision Processes.
International Journal of Computer Vision 83(2): 149-163, June 2009

K. Zimmermann, J. Matas, and T. Svoboda.
Tracking by an optimal sequence of linear predictors.
IEEE Transactions on Pattern Analysis and Machine Intelligence, 31(4):677-692, April 2009.

O. Chum, M. Perdoch, J. Matas.
Geometric min-Hashing: Finding a (thick) needle in a haystack.
CVPR 2009: 17-24

O. Chum and J. Matas.
Optimal randomized RANSAC.
IEEE Transactions on Pattern Analysis and Machine Intelligence, 30(8):1472-1482, August 2008.

J. Sochman and J. Matas.
Learning a fast emulator of a binary decision process.
In ACCV 2007: Proc. 8th Asian Conference on Computer Vision, volume II of LNSC, pages 236-245, November 2007. Springer.
* Sang Uk Lee Outstanding Paper Award. * [ppt, 4 MB]

K. Mikolajczyk and J. Matas.
Improving sift for fast tree matching by optimal linear projection.
In ICCV 2007: Proc. of Eleventh IEEE International Conference on Computer Vision, October 2007.

S. Obdrzalek and J. Matas. Toward Category-Level Object Recognition,
Chapter 2, pages 85-108., Springer, 2006.

O. Chum and J. Matas. Geometric hashing with local affine frames.
In CVPR 2006: Proc. of Conference on Computer Vision and Pattern Recognition (CVPR), volume 1, pages 879-884, Los Alamitos, USA, June 2006. IEEE Computer Society.

K Mikolajczyk, T Tuytelaars, C Schmid, A Zisserman, J Matas, F Schaffalitzky, T Kadir, and L van Gool.
A comparison of affine region detectors.
International Journal of Computer Vision, 65(7):43 - 72, November 2005.

Jiri Matas and Ondrej Chum.
Randomized ransac with sequential probability ratio test.
In ICCV 2005: Proc. IEEE International Conference on Computer Vision (ICCV), volume II, pages 1727-1732, New York, USA, October 2005. IEEE Computer Society Press.

S. Obdrzálek and J. Matas.
Sub-linear indexing for large scale object recognition.
Proc. of the British Machine Vision Conference, volume 1, pages 1-10, 2005.
*Awarded the Best Paper Prize *,

M. Hamouz, J. Kittler, JK Kamarainen, P Paalanen, H. Kalviainen, and J. Matas.
Feature-based affine-invariant localization of faces.
IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(9):1490-1495, September 2005.

O. Chum and J. Matas.
Matching with PROSAC - progressive sample consensus.
Proc. of Conference on Computer Vision and Pattern Recognition (CVPR), volume 1, pages 220-226, Los Alamitos, California, USA, June 2005.

O. Chum, T. Werner, and J. Matas.
Two-view geometry estimation unaffected by a dominant plane. Proc. of Conference on Computer Vision and Pattern Recognition (CVPR), volume 1, pages 772-780, Los Alamitos, California, USA, June 2005.

J. Šochman and J. Matas.
Waldboost - learning for time constrained sequential detection. Proc. of Conference on Computer Vision and Pattern Recognition (CVPR), volume 2, pages 150-157, Los Alamitos, California, USA, June 2005.

J. Matas and O. Chum.
Randomized RANSAC with T_d,d test.
Image and Vision Computing, 22(10):837-842, September 2004.

J. Kittler, R. Ghaderi, T. Wideatt, and J. Matas.
Face verification via error correcting output codes.
Image and Vision Computing, 21(13-14):1163-1169, Dec 2003.

J. Matas, O. Chum, U. Martin, and T Pajdla.
Robust wide baseline stereo from maximally stable extremal regions.
Proc. of the British Machine Vision Conference, volume 1, pages 384-393, 2002.
*Awarded the Best Paper Prize*

J. Matas, D. Koubaroulis, and J. Kittler.
The multimodal neighborhood signature for modeling object color appearance and applications in object recognition and image retrieval.
Computer Vision and Image Understanding, 88(1):1-23, October 2002.

K. Jonsson, J. Kittler, Y. P. Li, and J. Matas.
Support vector machines for face authentication.
Image and Vision Computing, 20(5-6):369-375, March 2002.

J. Matas, C. Galambos, and J. Kittler.
Robust detection of lines using progressive probabilistic Hough Transform.
Computer Vision and Image Understanding, 2000.

J. Matas, K. Jonsson, and J. Kittler.
Fast face localisation and verification.
Image and Vision Computing , 17(8):578-581, June 1999.

J. Kittler, M. Hatef, R.P.W Duin, and J. Matas.
On combining classifiers.
IEEE Trans. Pattern Analysis and Machine Intellige nce, 20(3):226 - 239, March 1998.
*More than 1000 citations in SCI! *


Demos:
Sequential Correspondence Verification Wide-baseline matching TLD tracking
Frontal face detector Face tracking Face verification
Colour-based image retrieval Lip tracking (on M2VTS),