J
Jiri Matas
Researcher at Czech Technical University in Prague
Publications - 359
Citations - 50878
Jiri Matas is an academic researcher from Czech Technical University in Prague. The author has contributed to research in topics: RANSAC & Video tracking. The author has an hindex of 78, co-authored 345 publications receiving 44739 citations. Previous affiliations of Jiri Matas include University of Surrey & IEEE Computer Society.
Papers
More filters
Journal ArticleDOI
Systematic evaluation of convolution neural network advances on the Imagenet
TL;DR: It is shown that the use of 128 × 128 pixel images is sufficient to make qualitative conclusions about optimal network structure that hold for the full size Caffe and VGG nets, and an order of magnitude faster than with the standard 224 pixel images.
Proceedings ArticleDOI
WaldBoost - learning for time constrained sequential detection
Jan Sochman,Jiri Matas +1 more
TL;DR: An algorithm with near optimal time and error rate trade-off is proposed, called WaldBoost, which integrates the AdaBoost algorithm for measurement selection and ordering and the joint probability density estimation with the optimal SPRT decision strategy.
Proceedings ArticleDOI
Tracking the invisible: Learning where the object might be
TL;DR: This work proposes a method to learn supporters which are, be it only temporally, useful for determining the position of the object of interest and exploits the General Hough Transform strategy.
Proceedings ArticleDOI
Deep TextSpotter: An End-to-End Trainable Scene Text Localization and Recognition Framework
TL;DR: The proposed method achieves state-of-the-art accuracy in the end-to-end text recognition on two standard datasets – ICDar 2013 and ICDAR 2015, whilst being an order of magnitude faster than competing methods.
Proceedings ArticleDOI
The Visual Object Tracking VOT2013 Challenge Results
Matej Kristan,Roman Pflugfelder,Ale Leonardis,Jiri Matas,Fatih Porikli,Luka Cehovin,Georg Nebehay,Gustavo Fernandez,Toma Vojir,Adam Gatt,Ahmad Khajenezhad,Ahmed Salahledin,Ali Soltani-Farani,Ali Zarezade,Alfredo Petrosino,Anthony Milton,Behzad Bozorgtabar,Bo Li,Chee Seng Chan,Cherkeng Heng,Dale A. Ward,David Kearney,Dorothy Monekosso,Hakki Can Karaimer,Hamid R. Rabiee,Jianke Zhu,Jin Gao,Jingjing Xiao,Junge Zhang,Junliang Xing,Kaiqi Huang,Karel Lebeda,Lijun Cao,Mario Edoardo Maresca,Mei Kuan Lim,Mohamed El Helw,Michael Felsberg,Paolo Remagnino,Richard Bowden,Roland Goecke,Rustam Stolkin,Samantha Yueying Lim,Sara Maher,Sebastien Poullot,Sebastien Wong,Shin'Ichi Satoh,Weihua Chen,Weiming Hu,Xiaoqin Zhang,Yang Li,ZhiHeng Niu +50 more
TL;DR: The evaluation protocol of the VOT2013 challenge and the results of a comparison of 27 trackers on the benchmark dataset are presented, offering a more systematic comparison of the trackers.