Matej Kristan received a Ph.D from the Faculty of Electrical Engineering, University of Ljubljana in 2008. He is an full professor and a vice chair of the department of artificial intelligence at the Faculty of Computer and Information Science, University of Ljubljana. He leads the Visual object tracking VOT initiative, he is president of the IAPR Slovenian pattern recognition society and Associate Editor of IJCV. He has co-organized over thirteen workshops and conferences, he recieved fourteen research excellence awards, four teaching excellence awards and was the finalist of Mentor of the year in 2020 and 2023. His students regularly receive research excellence awards as well. His research interests include visual object tracking, anomaly detection and segmentation,perception methods for autonomous boats and machine-learning-based physics prediction models. According to Google scholar, his works have been cited over 11.000 times, his h-index is 42. His Erdos number is 3.

Teaching

• Machine perception(Umetno zaznavanje)
• Multimedia systems (Multimedijski sistemi)
• Advanced computer vision methods: (Napredne metode računalniškega vida)
• In-depth computer vision research: Doctoral study, FRI, UL

Past courses

• Komunikacije v Avtomatiki, (computer networks) 2009-2012: vaje, dodiplomski študij, FE, UL
• Sistemi Daljinjskega vodenje (wireless sensor networks) 2009-2012: vaje, dodiplomski študij, FE, UL
• Strojni Vid (machine vision) 2010-2018: podiplomski študij, FE, UL
• Večpredstavitveni sistemi (computer vision for multimedia sistems): vaje z letom 2010/2011, dodiplomski študij, FRI, UL
• Računalniško zaznavanje (computer vision): vaje z letom 2010/2011, dodiplomski študij, FRI, UL
• Multimedijski sistemi (computer vision for multimedia systems): vaje z letom 2011/2012, dodiplomski študij, FRI, UL
• Umetno zaznavanje (computer vision): vaje z letom 2011/2012, dodiplomski študij, FRI, UL
• Robotics and machine perception 2012/2013: predavanja(Robotika in računalniško zaznavanje)

Research

My primary research interests include visual object tracking, anomaly detection and segmentation, perception methods for autonomous boats and machine-learning-based geophysics prediction models.

Visual object tracking

Contains 7 subtopics

We have a long tradition in visual object tracking research. The primary goal is developing method for object localization, where the single training image is provided in the first frame. In addition to designing new algorithms for object tracking, we have invested significant effort also in development of performance evaluation measures and protocols for objective tracker evaluation.

Autonomous boats perception methods

Unmnanned surface vehicles (USV) are robotic boats that can be used for coastal patrolling in a numerous applications ranging from surveillance to water cleanness control. We are developing computer vision algorithms that enable autonomous operation in the highly dynamic environments in which the USVs are applied.

Physics informed deep learning prediction models

This research is dedicated to geophyiscs prediction problems such as sea surface height dynamics modelling for predicting coastal floods. We are developing new physics-informed machine learning models that rival gephysics numerical models, while performing orders of magnitude faster.

Object counting

Contains 2 subtopics

We are designing novel deep architectures for object counting based on trainable category-specific detectors and low-shot counters.

Visual anomaly detection

This research focuses on the development of unsupervised visual anomaly detection methods. Trained on anomaly-free samples only, these methods attempt to remove the need for a difficult acquisition of a diverse set of anomalous objects while aiming to match the performance of supervised methods.

Surface defect detection

Contains 2 subtopics

We are designing novel deep architectures for visual surface inspection. The developed methods allow specialization for large defect detection such as cracks, as well as smooth deformations on reflective surfaces like dents. The methods are learning-based and are thus robust, run realtime and are applicable to a wide range of real problems. Several of the methods are part of most advances surface inspection commercial systems.

Deep structured models

Contains 4 subtopics

This research is dedicated to deep models which utilize compositional structure of object parts. The methodologies span from modern deep learning frameworks to more classical hierarchies of parts.

Online learning with mixture models

Contains 3 subtopics

Online learning from data streams is a challenging problem in which datapoints arrive in continual fashion and cannot be stored, but rather compressed into a model. We have explored this problem in the context of learning by mixture models. We developed several algorithms that build mixture models in under generative or discriminative constraints and introduced a concept of unlearning into the mixure models.

Selected projects

Sabuvis II - Swarm of biomimetic underwater vehicles for underwater intelligence, surveillance and reconnaissance

June 2023 - December 2025

This project is a continuation of the successful collaboration enjoyed between Poland, Germany and Portugal in the first SABUVIS project. In this first iteration, three different Biomimetic Underwater Vehicles (BUVs) were constructed with the resulting conclusion that BUVs can be designed with varying degrees of similarity with living organisms. Some of the identified benefits are that undulating propulsion consumes less electrical energy than conventional propulsion systems utilising screw based propellers, and different hydroacoustic signatures are produced with a corresponding lower noise level.

SMASH - Machine learning for science and humanities postdoctoral program

July 2023 - June 2028

SMASH is an innovative, intersectoral, career-development training program for outstanding postdoctoral researchers, co-funded by the Marie Skłodowska-Curie Actions COFUND program. SMASH is open to researchers around the world who are interested in developing cutting-edge machine learning applications for science and humanities.

DAViMaR - Adaptive deep perception methods for autonomous surface vehicles

April 2020 - August 2023

The project primary goal is to develop the next-generation maritime environment perception methods, which will harvest the power of end-to-end trainable deep models for essential challenges of safe operation like: general obstacle detection with re-identification, implicit detection of hazardous areas and sensor fusion for improved detection.

ViAMaRo - Robust computer vision methods for autonomous water surface vehicles

May 2017 - April 2020

The project primary goal is to develop functionalities required for robust autonomous navigation of USVs in uncontrolled environments, primarily relying on the captured visual information. The project focuses on obstacle detection using monocular and stereo systems, development of efficient visual tracking algorithms for marine environments and environment representation through sensor fusion.

DIVID - Detection of inconsistencies in complex visual data using deep learning

July 2018 - December 2021

The objective of the project is to develop novel deep learning methods for modelling complex consistency and detecting inconsistencies in visual data using training images annotated with different levels of accuracy. The main project goal is to go beyond the traditional supervised learning, where all anomalies on all training images have to be adequately labelled.

Events & Service to Community

Service to community:

• President of IAPR Slovenian Pattern Recognition Society
• Associate Editor of IJCV (2021 - )
• Area chair at IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022, 2023, 2024
• Vice chair of Department of artificial intelligence FRI-UNILJ

Conferences:

• Organization committe of the 2nd Visual Object Tracking Segmentation Challenge Workshop VOTS2024 in conjunction with the ECCV2024
• Organization committe of the first Visual Object Tracking Segmentation Challenge Workshop VOTS2023 in conjunction with the ICCV2023
• Organization committe of the 2nd Workshop on Maritime Computer Vision MaCVi in conjunction with the WACV2024
• Organization committe of the tenth Visual Object Tracking Challenge Workshop VOT2022 in conjunction with the ECCV2022
• Organization committe of the 1st Workshop on Maritime Computer Vision MaCVi in conjunction with the WACV2023
• Organization committe of the ninth Visual Object Tracking Challenge Workshop VOT2021 in conjunction with the ICCV2021
• Organization committe of the eighth Visual Object Tracking Challenge Workshop VOT2020 in conjunction with the ECCV2020
• Organization committe of the seventh Visual Object Tracking Challenge Workshop VOT2019 in conjunction with the ICCV2019
• Organization committe of the sixth Visual Object Tracking Challenge Workshop VOT2018 in conjunction with the ECCV2018
• Organization committe of the fifth Visual Object Tracking Challenge Workshop VOT2017 in conjunction with the ICCV2017
• Program chair of the 10th Int’l Symposium on Image and Signal Processing and Analysis, ISPA2017
• Organization committe of the fourth Visual Object Tracking Challenge Workshop VOT2016 in conjunction with the ECCV2016
• Organization committe of the third Visual Object Tracking Challenge Workshop VOT2015 in conjunction with the ICCV2015
• Competition chair at the 11th IEEE International Conference on Automatic Face and Gesture Recognition, FG2015
• Organization committe of the second Visual Object Tracking Challenge Workshop VOT2014 in conjunction with the ECCV2014
• Organization committe of the first Visual Object Tracking Challenge Workshop VOT2013 in conjunction with the ICCV2013
• Organization committe of the Pattern Recognition section at the 22nd International Electrotechnical and Computer Science Conference ERK2013
• Organization committe of the 17th Computer Vision Winter Workshop (CVWW2012)

Awards

• 2023 Professor of the year (masters program) voted by students of FRI-UL.
• 2023 Excellent research achievements in 2022 award by the Slovenian Research Agency for our work on anomaly detection.
• 2023 Best paper award at ERK 2023 Pattern recognition section
• 2023 Runner-up for supervisor of the year award organized by Mlada Akademija (Slovenia Universities and Institutes).
• 2022 BMVC2022 best paper award for our work on transparent object tracking
• 2022 Excellent research achievements in 2021 award by the Slovenian Research Agency for our work on segmentation tracking.
• 2022 Research excellence award by University of Ljubljana for our work on segmentation tracking.
• 2021 Professor of the year (masters program) voted by students of FRI-UL.
• 2021 Excellent research achievements in 2020 award by the Slovenian Research Agency (Hidra).
• 2021 Research excellence award by University of Ljubljana for surface defect detection methods (coauthor).
• 2020 Our work on RGB/RGBD long-term tracking and evaluation was selected as one of the Excellent Slovenian research achievements in 2020 by the Slovenian Research Agency.
• 2020 Golden plaque award for outstanding scientific achievements of a research group awarded by University of Ljubljana.
• 2020 Runner-up for supervisor of the year award organized by Mlada Akademija (Slovenia Universities and Institutes).
• 2019 Excellent research achievements in 2019 award for our work on tracking by the Slovenian Research Agency.
• 2018 Golden plaque award for outstanding scientific and pedagogic contributions awarded by University of Ljubljana.
• 2018 Award for excellent pedagogical work, awarded by the Faculty of computer and information science, University of Ljubljana
• 2017 Our work on VOT initiative that was selected as one of 10 exceptional research achievements in 2017 by University of Ljubljana.
• 2015 Best paper award at pattern recognition section at ERK2015 for the paper coauthored with my student Domen Rački.
• 2013 Young University teachers and researchers award for excellent teaching and research achievements, by University of Ljubljana.
• 2013 Exceptional scientific achievements in 2012 award for a coauthored paper, awarded by the Slovenian research agency.
• 2012 Contributed on the research project “A system for interactive learning in dialogue with the tutor”, for which an award for exceptional research achievements in 2011 was attributed by the Slovenian research agency.
• 2010 Award for contributions in popularization of Computer and information science, awarded by the FRI, University of Ljubljana
• 2009 Vodovnik Award for excellent research achievements relating to doctoral thesis, FE, University of Ljubljana.
• 2009 Award for excellent research achievements in the last years, FRI, University of Ljubljana.
• 2009 Innovation award for applied research project (part of project team), by Innovation forum, sponsored by Slovenian business and foreign investment agency.
• 2005 Best paper award at the International Symposium on Image and Signal Processing and Analysis ISPA2005

Awards of students under my supervision:

• 2024 Jer Pelhan received [Uroš Seljak award]{{}} for best student research paper at UL ([DAVE paper]{{https://openaccess.thecvf.com/content/CVPR2024/html/Pelhan_DAVE_-_A_Detect-and-Verify_Paradigm_for_Low-Shot_Counting_CVPR_2024_paper.html}}).
• 2024 Alan Lukežič received the University [dr. Ana Mayer Kansky]{{https://fri.uni-lj.si/sl/novice/novica/dr-alan-lukezic-prejel-nagrado-dr-ane-mayer-kansky}} award for his Phd thesis.
• 2023 Outstanding research achievement of PhD students in 2023 award (Lojze Žust) by FRI-UNI-LJ.
• 2023 Three Prešern awards! Nikola Djukic, Žiga Trojer and Matija Teršek each received a Prešeren award from FRI for their master theses.
• 2023 Uroš Seljak commendation (pohvala) for research work (Žiga Trojer) by UNI-LJ
• 2022 Outstanding research achievement of PhD students in 2022 award (Borja Bovcon) by FRI-UNI-LJ.
• 2022 Honorable mention of the research achievements of PhD students in 2022 (Lojze Žust) by the FRI UNI-LJ.
• 2021 Lojze Žust received (University Prešeren award) from UNI-LJ, for his masters thesis.
• 2021 Two outstanding research achievements of PhD students in 2021 award (Lojze Žust and Borja Bovcon) by FRI-UNI-LJ.
• 2021 Vitjan Zavrtanik (co-supervised his research) received an honorable mention of the research achievements of PhD students in 2020, awarded by FRI UNI-LJ (four awards given).
• 2020 Two PhD students, Borja Bovcon (my PhD student), and Vitjan Zavrtanik (co-supervised his research) received an award for outstanding research achievements of PhD students in 2020 (three awards given), awarded by The Faculty of computer and information science (FRI) UNI-LJ.
• 2020 Two PhD students Domen Tabernik (my PhD student)) and Jon Muhovič (co-supervised his research) received an honorable mention of the research achievements of PhD students in 2020, awarded by FRI UNI-LJ (five awards given).
• 2019 Two of my PhD students (Alan Lukežič and Borja Bovcon) received an (award for outstanding research achievements) of PhD students in 2019 (four awards given), awarded by FRI UNI-LJ.
• 2018 Two of my PhD students (Alan Lukežič and Domen Tabernik) received an (award for outstanding research achievements) of PhD students in 2018 (five awards given), by FRI UNI-LJ .
• 2018 Borja Bovcon received an (honorable mention of the research achievements) of PhD students in 2018, by the FRI UNI-LJ.
• 2018 Lojze Žust received (Prešeren award) from FRI UNI-LJ, for his bachelor thesis.
• 2017 Borja Bovcon received Prešeren award from the FRI UNI-LJ, for his masters thesis.
• 2015 Alan Lukežič received Prešeren award from the FRI UNI-LJ, for his masters thesis.

Selected publications

Selected journals:

Selected conferences:

Complete list of my publications is available here .

PhD Students

Here’s a list of PhD students under my supervision:

• Jer Pelhan=, Area of research: Few-shot detection and counting, (active)
• Marko Rus=, Area of research: Physics-informed deep climate prediction models, (active)
• Lojze Žust, Area of research: Vision for unmanned surface vehicles, (active)
• Borja Bovcon, Area of research: Vision for unmanned surface vehicles, (finished 2022)
• Alan Lukežič, Area of research: Visual object tracking, (finished suma cum laude 2021)
• Domen Tabernik, Area of research: Deep compositional models, (finished 2021)
• Peter Uršič, A Compositional Hierarchical Architecture for Spatial Modelling, (finished 2016)
• Luka Čehovin, A hierarchical adaptive model for robust short-term visual tracking, (finished 2015)