1 code implementation • 7 Aug 2023 • Artem Moskalev, Anna Sepliarskaia, Erik J. Bekkers, Arnold Smeulders
We demonstrate that even when a network learns to correctly classify samples on a group orbit, the underlying decision-making in such a model does not attain genuine invariance.
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.
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.
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