Extending Temporal Data Augmentation for Video Action Recognition

Gorpincenko, Artjoms and Mackiewicz, Michal ORCID: https://orcid.org/0000-0002-8777-8880 (2023) Extending Temporal Data Augmentation for Video Action Recognition. In: Image and Vision Computing. Lecture Notes in Computer Science . Springer, pp. 104-118. ISBN 978-3-031-25824-4

[thumbnail of 2211.04888]
Preview
PDF (2211.04888) - Accepted Version
Download (11MB) | Preview

Abstract

Pixel space augmentation has grown in popularity in many Deep Learning areas, due to its effectiveness, simplicity, and low computational cost. Data augmentation for videos, however, still remains an under-explored research topic, as most works have been treating inputs as stacks of static images rather than temporally linked series of data. Recently, it has been shown that involving the time dimension when designing augmentations can be superior to its spatial-only variants for video action recognition . In this paper, we propose several novel enhancements to these techniques to strengthen the relationship between the spatial and temporal domains and achieve a deeper level of perturbations. The video action recognition results of our techniques outperform their respective variants in Top-1 and Top-5 settings on the UCF-101 and the HMDB-51 datasets.

Item Type: Book Section
Additional Information: Funding information: The authors are grateful for the support from the Natural Environment Research Council and Engineering and Physical Sciences Research Council through the NEXUSS Centre for Doctoral Training (grant #NE/RO12156/1).
Uncontrolled Keywords: action recognition,data augmentation,temporal domain,theoretical computer science,computer science(all) ,/dk/atira/pure/subjectarea/asjc/2600/2614
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:
Depositing User: LivePure Connector
Date Deposited: 18 May 2023 10:30
Last Modified: 03 Feb 2024 01:38
URI: https://ueaeprints.uea.ac.uk/id/eprint/92093
DOI: 10.48550/arXiv.2211.04888

Downloads

Downloads per month over past year

Actions (login required)

View Item View Item