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
Proceedings ArticleDOI
Unconstrained licence plate and text localization and recognition
Jiri Matas,Karel Zimmermann +1 more
TL;DR: A new class of locally threshold separable detectors based on extremal regions, which can be adapted by machine learning techniques to arbitrary shapes, is proposed, which is very robust to illumination change and partial occlusions.
Book ChapterDOI
Repeatability Is Not Enough: Learning Affine Regions via Discriminability
TL;DR: It is shown that maximizing geometric repeatability does not lead to local regions, a.k.a features, that are reliably matched and this necessitates descriptor-based learning, and a novel hard negative-constant loss function is proposed for learning of affine regions.
Journal ArticleDOI
Tracking by an Optimal Sequence of Linear Predictors
TL;DR: A learning approach to tracking explicitly minimizing the computational complexity of the tracking process subject to user-defined probability of failure (loss-of-lock) and precision, verified on publicly-available sequences with approximately 12000 frames with ground-truth.
Proceedings ArticleDOI
Sub-linear Indexing for Large Scale Object Recognition.
Stepan Obdrzalek,Jiri Matas +1 more
TL;DR: A method capable of recognising one of N objects in log(N) time, which preserves all the strengths of local affine region methods – robustness to background clutter, occlusion, and large changes of viewpoints.
Journal ArticleDOI
Efficient sequential correspondence selection by cosegmentation
TL;DR: It is shown experimentally that the proposed sequential correspondence verification (SCV) algorithm significantly outperforms the standard correspondence selection method based on SIFT distance ratios on challenging matching problems.