2014

2015

2016

2017

2018

2019

2020

2022

2023

2024

The thirty-fifth meeting of the Prague computer science seminar

Josef Šivic

Automatic Visual Recognition: from Internet Images towards Machines that See

Building machines that can automatically understand complex visual inputs is one of the central problems in artificial intelligence with applications in autonomous robotics, automatic manufacturing or healthcare. The problem is difficult due to the large variability of the visual world.

Annotation Lecturer

2024
2023
2022
2020
2019
2018
2017
2016
2015
2014

Play record

April 26, 2018

4:00pm

Auditorium S5, MFF UK
Malostranské nám. 25, Praha 1
Show on the map

Building machines that can automatically understand complex visual inputs is one of the central problems in artificial intelligence with applications in autonomous robotics, automatic manufacturing or healthcare. The problem is difficult due to the large variability of the visual world. I will present our contributions to the recent progress in automatic visual understanding and discuss some of the key open challenges.

First I will discuss the recent successes that are, in large part, due to a combination of learnable visual representations based on convolutional neural networks, supervised machine learning techniques and large-scale Internet image collections. Then I will argue that in order to build machines that understand the changing visual world the challenges lie in developing visual representations that generalize to yet unseen conditions and are learnable from noisy and only partially annotated data.

Josef Šivic

Josef Sivic holds a senior researcher position at INRIA in Paris and a distinguished senior researcher position at the Czech Institute of Informatics, Robotics and Cybernetics at the Czech Technical University in Prague where he leads a newly created intelligent machine perception team. He received his habilitation from École Normale Supérieure in Paris in 2014, the PhD degree from the University of Oxford in 2006 and the MSc degree from the Czech Technical University in Prague in 2002. Before joining INRIA he was a post-doctoral associate at the Computer Science and Artificial Intelligence Lab at the Massachusetts Institute of Technology. He received the Sullivan Thesis Prize from the British Machine Vision Association and his papers have been awarded the Longuet-Higgins prize (CVPR’07) and the Helmholtz prize (ICCV’03, ICCV’05) for fundamental contributions to computer vision that withstood the test of time. He is a senior fellow of the Learning in Machines & Brains program at the Canadian Institute of Advanced Research. He was awarded an ERC Starting Grant in 2013.

Its program consists of a one-hour lecture followed by a discussion. The lecture is based on an (internationally) exceptional or remarkable achievement of the lecturer, presented in a way which is comprehensible and interesting to a broad computer science community. The lectures are in English.

The seminar is organized by the organizational committee consisting of Roman Barták (Charles University, Faculty of Mathematics and Physics), Jaroslav Hlinka (Czech Academy of Sciences, Computer Science Institute), Michal Chytil, Pavel Kordík (CTU in Prague, Faculty of Information Technologies), Michal Koucký (Charles University, Faculty of Mathematics and Physics), Jan Kybic (CTU in Prague, Faculty of Electrical Engineering), Michal Pěchouček (CTU in Prague, Faculty of Electrical Engineering), Jiří Sgall (Charles University, Faculty of Mathematics and Physics), Vojtěch Svátek (University of Economics, Faculty of Informatics and Statistics), Michal Šorel (Czech Academy of Sciences, Institute of Information Theory and Automation), Tomáš Werner (CTU in Prague, Faculty of Electrical Engineering), and Filip Železný (CTU in Prague, Faculty of Electrical Engineering)

The idea to organize this seminar emerged in discussions of the representatives of several research institutes on how to avoid the undesired fragmentation of the Czech computer science community.