Professor
I am leading a team within the Visual Recognition Group at the Department of Cybernetics, Faculty of Electrical Engineering, Czech Technical University in Prague. I received the MSc degree in computer science from Charles University, Prague, in 2001 and the PhD degree from the Czech Technical University in Prague, in 2005. From 2006 to 2007, I was a postdoctoral researcher at the Visual Geometry Group, University of Oxford, United Kingdom. My research interests include large-scale image and particular object retrieval, object recognition, and robust estimation of geometric models. I am a member of Image and Vision Computing editorial board, and I have served as an area chair at major international conferences (e.g., ICCV, ECCV, CVPR, WACV and BMVC). I co-organize Computer Vision and Sports Summers School in Prague. I was the recipient of the Best Paper Prize at the BMVC 2002, Best Science Paper Honorable mention at BMVC 2017, and Saburo Tsuji Best Paper Award at ACCV 2018. I was awarded the 2012 Outstanding Young Researcher in Image & Vision Computing runner up for researchers within seven years of their PhD. Complete list of awards below. [. . .]
News
- PhD and PostDoc positions open in the group. Apply by sending me an e-mail. For PostDocs, include links to your CVPR, ICCV, ECCV, NIPS papers.
Our paper Pritts, Kukelova, Larsson, and Chum : Rectification from Radially-Distorted Scales, ACCV 2018 has received the Saburo Tsuji Best Paper Award.
Ph.D. Students
- Tomas Jenicek
- Nikos Efthymiadis, (co-advised with Giorgos Tolias)
- Nikolaos-Antonios Ypsilantis
Close collaborators
- Giorgos Tolias assistant professor
Graduated
- Arun Mukundan (co-advised with Giorgos Tolias) Ph.D. 2020
Thesis: Local Descriptors for Image Matching and Retrieval - James Pritts (co-advised with Zuzana Kukelova) Ph.D. 2020, moved on to Oculus
Thesis: Methods for the Rectification of Imaged Coplanar Repeated Patterns - Javier Aldana (co-advised with Jiri Matas) Ph.D. 2020, moved on to Avast
Thesis: Relevant Shot Detection with Local Features for Video Re-ranking - Filip Radenovic Ph.D. 2019, moved on to Facebook
Thesis: Visual Retrieval with Compact Image Representations - Andrej Mikulik (co-advised with Jiri Matas) Ph.D. 2015, moved to Google
Thesis: Large-Scale Content-Based Sub-Image Search
Alumni
- Ahmet Iscen moved on to Google
- Pierre Jacob
- Assia Benbihi
Contact
Karlovo namesti 13, 121 35 Praha 2, Czech Republic
Office: G3 (building G, room 3), directions
Tel: +420 2 2435 7282
Awards
Rector's award for prestigeous publication (one per year per CTU in Prague) for paper
Radenovic, Tolias, Chum:
Fine-tuning CNN Image Retrieval with No Human Annotation,
TPAMI'19
Saburo Tsuji Best Paper Award at ACCV 2018
Pritts, Kukelova, Larsson, Chum:
Rectification from Radially-Distorted Scales,
ACCV'18
Best Science Paper Honorable Mention at BMVC 2017
Mukundan, Tolias, Chum:
Multiple-Kernel Local-Patch Descriptor,
BMVC'17
Longuet-Higgins Prize at CVPR 2017
Philbin,Chum,Isard,Sivic,Zisserman:
Object Retrieval with Large Vocabularies and Fast Spatial Matching,
CVPR'07
The 2012 Outstanding Young Researcher in Image & Vision Computing runner up for researchers within seven years of their PhD.
Best Science Paper at BMVC 2002
Matas, Chum, Urban, Pajdla:
RobustWide Baseline Stereo from Maximally Stable Extremal Regions,
BMVC'02
Projects and code
Training data, fine-tuned deep neural networks and matlab evaluation code to reproduce the results of our ECCV 2016 paper. See the project page.
Feature maps construction for kernels with low-dimensional compact interval input cast as a convex optimization problem. See our ICCV 2015 paper for details, Matlab code is available.
Fast and reliable two-view geometry estimation from our BMVC 12 paper , software page, and data. Results any RANSAC paper should compare to.
A modular framework implementing a number of RANSAC extensions. Our PAMI 2013 paper and code and data zip archive are available.
Homography estimation from a correspondence of at least two elliptical featires: ICPR 2012 paper and Matlab code .
Alps100K dataset contains 98,136 annotated (GPS coordinates, elevation, EXIF if available) outdoor images from mountain environments, from our BMVC 2015 paper. See the project page.