SVW-UCF Dataset for Video Domain Adaptation

Gorpincenko, Artjoms and Mackiewicz, Michal ORCID: https://orcid.org/0000-0002-8777-8880 (2021) SVW-UCF Dataset for Video Domain Adaptation. In: Proceedings of the International Conference on Image Processing and Vision Engineering (IMPROVE 2021). Proceedings of the International Conference on Image Processing and Vision Engineering, IMPROVE 2021 . UNSPECIFIED, pp. 107-111. ISBN 9789897585111

Preview

PDF (svw-ucf) - Published Version Available under License Creative Commons Attribution Non-commercial No Derivatives. Download (9MB) | Preview

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 the most confusion for modern video domain adaptation methods.

Item Type:	Book Section
Additional Information:	Funding Information: The project was jointly funded by Innovate UK (grant #102072), Cefas, Cefas Technology Limited and EDF Energy, and has also been supported by by the Natural Environment Research Council; and Engineering and Physical Sciences Research Council through the NEXUSS Centre for Doctoral Training (grant #NE/RO12156/1). Publisher Copyright: Copyright © 2021 by SCITEPRESS – Science and Technology Publications, Lda. All rights reserved
Uncontrolled Keywords:	dataset,deep learning,domain adaptation,video,artificial intelligence,computer vision and pattern recognition,signal processing,software ,/dk/atira/pure/subjectarea/asjc/1700/1702
Faculty \ School:	Faculty of Science > School of Computing Sciences
UEA Research Groups:	Faculty of Science > Research Groups > Colour and Imaging Lab Faculty of Science > Research Groups > Collaborative Centre for Sustainable Use of the Seas
Related URLs:	http://www.scopus.com/inward/record.url?...
Depositing User:	LivePure Connector
Date Deposited:	15 May 2023 08:31
Last Modified:	30 Jan 2024 04:02
URI:	https://ueaeprints.uea.ac.uk/id/eprint/92054
DOI:	10.5220/0010460901070111

Downloads

Actions (login required)

View Item