Bill Psomas has been awarded the prestigious MSCA Postdoctoral Fellowship 2024 for his project RAVIOLI (Retrieval-Augmented VIsion-Language Models for Open-vocabulary LocalizatIon). Hosted at the Visual Recognition Group (VRG) at Czech Technical University in Prague (CTU) under the supervision of associate Prof. Giorgos Tolias, RAVIOLI aims to advance open-vocabulary segmentation by integrating retrieval-based predictions with vision-language models. The project seeks to enhance segmentation accuracy and adaptability across diverse environments and applications. As part of this research, Bill will also undertake a secondment at AImageLab, University of Modena and Reggio Emilia (UNIMORE), collaborating with Prof. Rita Cucchiara.

The Czech Science Foundation (GA ČR), the largest Czech grant funding provider for basic research, announced the results of the Standard grant projects for year 2025. The standard grand project are intended for applicants in all phases of their scientific career without age restrictions.The topic of a project is chosen by the applicant and the project is carried out by a single investigator or by research team from one or more institutions.

Researcher Tomáš Vojíř from Visual Recognition Group succeeded with his 3 year project  “Detection of anomalous or out-of-distribution inputs in deep neural network models”.

The "LUSt: Learning a Universal Similarity Function" project has been funded under Horizon Europe and will run for two years (2025-2026). This grant is supporting a postdoctoral fellowship at CTU in Prague with Giorgos Tolias as advisor and a collaboration with the University of Amsterdam and assistant professor Pascal Mettes. The project's objective is to perform research on similarity learning based on the similarities of the constituent parts of multimedia items. The ultimate goal is creating a foundational model capable of accommodating all modalities -- visual, audio, text -- and supporting a broad range of similarity types, including uni-modal, cross-modal, and multi-modal scenarios.

Yash Patel was announced as a winner of the Antonín Svoboda Award for the Best Ph.D. for Thesis defended in 2023. The Czech Society for Cybernetics and Informatics selects the best Ph.D. Thesis every year. The PhD thesis topic falls within the scope of ČSKI’s scientific activities (cybernetics, informatics, and related fields). Any Thesis defended in a particular year at a faculty located in the Czech Republic can be submitted.

The thesis title Neural Network Training and Non-Differentiable Objective Functions. Congratulations to Yash and his supervisor prof. Jiří Matas! More detailed article is available on the Faculty website here

The Dean’s Awards for prestigious dissertations were awarded on March 13th at the Scientific Council meeting. Researcher Yash Patel was awarded for his work Neural Network Training and Non-Differentiable Objective Functions under the supervision of Prof. Jiří Matas. 

On April 4th the Department of Cybernetics hosts the 47th Colloquium in Pattern Recognition and Computer Vision. It is a biannual event with a rich tradition dating back to 1998. This esteemed gathering is jointly organized by the Visual Recognition Group and enjoys the generous support of the Czech Pattern Recognition Society (CPRS). The technical program is curated by Jiri Matas. The list of lecturers and other information about the Colloquium is available here.

Congratulations to Ing. Jekatěrina Jaroslavceva and her supervisor prof. Ondřej Chum for their extraordinary achievement in this year’s Werner von Siemens Awards!

Jekatěrina received two awards. She was awarded for excellence in women’s scientific work and she was a runner-up in the category Best Master Thesis for her thesis entitled New Algorithm for Coupling 3D Energy Deposits Based on Graph Neural Networks for the CMS Experiment at the Large Hadron Collider at CERN. Jekatěrina is a member of the Visual Recognition Group.

More information about the awards is available either on the Faculty web site , and also photos, winners’ medallions, and other documents are available for download at: www.siemenspress.cz

Ph.D. students Radim Špetlík from the Department of Cybernetics and Michal Kučera from the Department of Computer Graphics and Interaction and Open Computer Science student David Kunz won the Chaos Neurathon 2023, their team named “All You Need Is All You Need”.

This competition, the first of its kind, focused on using artificial intelligence in 3D rendering, was held in Prague from 25 to 29 November 2023 under the auspices of Chaos, a leading player in the world of visualization technologies.

more info here

On December 7th the Department of Cybernetics hosts the 46th Colloquium in Pattern Recognition and Computer Vision. It is a biannual event with a rich tradition dating back to 1998. This esteemed gathering is jointly organized by the Visual Recognition Group and enjoys the generous support of the Czech Pattern Recognition Society (CPRS). The technical program is curated by Jiri Matas. The list of lecturers and other information about the Colloquium is available here.

The Czech Science Foundation (GA ČR)  announced the results of the JUNIOR STAR 2024 projects. The highly selective tender is aimed at excellent early-career scientists coming to the Czech Republic from abroad or with significant international experience. With an exceptional funding amount of CZK 25 million for 5 years, the scientists will be able to build new scientific teams and focus on new research areas.

Researcher Lukáš Neumann from Visual Recognition Group succeeded with his project “Inductive Biases of Deep Neural Networks in Computer Vision”.

Congratulations to Zuzana Kúkelová for her achievement! She is the laureate of the Neuron 2023 prize for promising scientists in the field of computer science. The prizes are awarded to Czech scientists for their scientific results and should be perceived as encouraging to their further work. An independent local Scientific Council selects the laureates in seven fields – mathematics, physics, chemistry, biology, medicine, computer science, and social sciences.

You can find an article about the news on the Faculty website here.

According to Research.com’s international ranking, which evaluates the success of computer scientists based on their H-index, citations, and the number of papers collected by 21 December 2022, the top-ranked Czech computer scientist is prof. Jiří Matas. The success of CTU is underlined by the fact that it has three representatives among the first four Czech scientists – dr. Josef Šivic (CIIRC CTU) is the second and doc. Tomáš Pajdla (CIIRC CTU and FEL CTU) is fourth. Dr. Tomáš Mikolov (CIIRC CTU) is seventh and Dr. Torsten Sattler (CIIRC CTU and FEL CTU) is tenth. Prof. Ondřej Chum (FEL CTU) and Dr. Josef Urban (CIIRC CTU) are in the second ten, in fourteenth and seventeenth place, respectively. More info is available here.

The team of authors, including prof. Jiří Matas received an award for the Best Paper at the 33rd British Machine Vision Conference this week.

The Best Paper Prize was awarded for the Trans2k: Unlocking the Power of Deep Models for Transparent Object Tracking to Alan Lukezic (University of Ljubljana), Žiga Trojer (University of Ljubljana), Jiří Matas (Czech Technical University, Prague) and Matej Kristan (University of Ljubljana).