Josef Šivic presents Automatic Visual Recognition: from Internet Images towards Machines that See

35. Prague Computer Science Seminar

LECTURE ANNOTATION

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.

LECTURER

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 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.