loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Artjoms Gorpincenko and Michal Mackiewicz

Affiliation: School of Computing Sciences, University of East Anglia, Norwich, U.K.

Keyword(s): Dataset, Deep Learning, Domain Adaptation, Video.

Abstract: Unsupervised video domain adaptation (DA) has recently seen a lot of success, achieving almost if not perfect results on the majority of various benchmark datasets. Therefore, the next natural step for the field is to come up with new, more challenging problems that call for creative solutions. By combining two well known sets of data - SVW and UCF, we propose a large-scale video domain adaptation dataset that is not only larger in terms of samples and average video length, but also presents additional obstacles, such as orientation and intra-class variations, differences in resolution, and greater domain discrepancy, both in terms of content and capturing conditions. We perform an accuracy gap comparison which shows that both SVW→UCF and UCF→SVW are empirically more difficult to solve than existing adaptation paths. Finally, we evaluate two state of the art video DA algorithms on the dataset to present the benchmark results and provide a discussion on the properties which create th e most confusion for modern video domain adaptation methods (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 13.59.92.247

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Gorpincenko, A. and Mackiewicz, M. (2021). SVW-UCF Dataset for Video Domain Adaptation. In Proceedings of the International Conference on Image Processing and Vision Engineering - IMPROVE; ISBN 978-989-758-511-1, SciTePress, pages 107-111. DOI: 10.5220/0010460901070111

@conference{improve21,
author={Artjoms Gorpincenko. and Michal Mackiewicz.},
title={SVW-UCF Dataset for Video Domain Adaptation},
booktitle={Proceedings of the International Conference on Image Processing and Vision Engineering - IMPROVE},
year={2021},
pages={107-111},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010460901070111},
isbn={978-989-758-511-1},
}

TY - CONF

JO - Proceedings of the International Conference on Image Processing and Vision Engineering - IMPROVE
TI - SVW-UCF Dataset for Video Domain Adaptation
SN - 978-989-758-511-1
AU - Gorpincenko, A.
AU - Mackiewicz, M.
PY - 2021
SP - 107
EP - 111
DO - 10.5220/0010460901070111
PB - SciTePress