no code implementations • 12 Jan 2023 • Ivan Sosnovik, Artem Moskalev, Cees Kaandorp, Arnold Smeulders
Video summarization aims at choosing parts of a video that narrate a story as close as possible to the original one.
1 code implementation • 9 Oct 2022 • Artem Moskalev, Anna Sepliarskaia, Ivan Sosnovik, Arnold Smeulders
Symmetries built into a neural network have appeared to be very beneficial for a wide range of tasks as it saves the data to learn them.
1 code implementation • 31 May 2022 • Artem Moskalev, Ivan Sosnovik, Volker Fischer, Arnold Smeulders
The views are ordered in pairs, such that they are either positive, encoding different views of the same object, or negative, corresponding to views of different objects.
1 code implementation • 18 Nov 2021 • Sadaf Gulshad, Ivan Sosnovik, Arnold Smeulders
To demonstrate that wiggling the weights consistently improves classification, we choose a standard network and modify it to a transform-augmented network.
no code implementations • ICLR 2019 • Jan Jetze Beitler, Ivan Sosnovik, Arnold Smeulders
We consider the problem of information compression from high dimensional data.
no code implementations • 11 Aug 2021 • Artem Moskalev, Ivan Sosnovik, Arnold Smeulders
Tracking multiple objects individually differs from tracking groups of related objects.
no code implementations • ICCVW 2021 • Ivan Sosnovik, Artem Moskalev, Arnold Smeulders
We aim for accurate scale-equivariant convolutional neural networks (SE-CNNs) applicable for problems where high granularity of scale and small kernel sizes are required.
no code implementations • 20 Jul 2021 • Sadaf Gulshad, Ivan Sosnovik, Arnold Smeulders
We focus on building robustness in the convolutions of neural visual classifiers, especially against natural perturbations like elastic deformations, occlusions and Gaussian noise.
1 code implementation • 4 Jun 2021 • Ivan Sosnovik, Artem Moskalev, Arnold Smeulders
In recent work scale equivariance was added to convolutional neural networks.
1 code implementation • 17 Jul 2020 • Ivan Sosnovik, Artem Moskalev, Arnold Smeulders
We develop the theory for scale-equivariant Siamese trackers, and provide a simple recipe for how to make a wide range of existing trackers scale-equivariant.
Ranked #1 on Visual Object Tracking on OTB-2013
1 code implementation • ICLR 2020 • Ivan Sosnovik, Michał Szmaja, Arnold Smeulders
The effectiveness of Convolutional Neural Networks (CNNs) has been substantially attributed to their built-in property of translation equivariance.
Ranked #33 on Image Classification on STL-10
3 code implementations • 1 May 2019 • Andrei Atanov, Alexandra Volokhova, Arsenii Ashukha, Ivan Sosnovik, Dmitry Vetrov
This paper proposes a semi-conditional normalizing flow model for semi-supervised learning.
2 code implementations • 27 Sep 2017 • Ivan Sosnovik, Ivan Oseledets
The main novelty of this work is to state the problem as an image segmentation task.