Fuzzy Fusion for Two-stream Action Recognition

Anderson Carlos Sousa e Santos, Helena de Almeida Maia, Marcos Roberto e Souza, Marcelo Bernardes Vieira, Helio Pedrini

2020

Abstract

There are several aspects that may help in the characterization of an action being performed in a video, such as scene appearance and estimated movement of the involved objects. Many works in the literature combine different aspects to recognize the actions, which has shown to be superior than individual results. Just as important as the definition of representative and complementary aspects is the choice of good combination methods that exploit the strengths of each aspect. In this work, we propose a novel fusion strategy based on two fuzzy integral methods. This strategy is capable of generalizing other common operators, besides it allows more combinations to be evaluated by having a distinct impact in sets linearly dependent. Our experiments show that the fuzzy fusion outperforms the most commonly-used weighted average on the challenging UCF101 and HMDB51 datasets.

Paper Citation

in Harvard Style

Santos A., Maia H., Souza M., Vieira M. and Pedrini H. (2020). Fuzzy Fusion for Two-stream Action Recognition. In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP; ISBN 978-989-758-402-2, SciTePress, pages 117-123. DOI: 10.5220/0008973901170123

in Bibtex Style

@conference{visapp20,
author={Anderson Carlos Sousa e Santos and Helena de Almeida Maia and Marcos Roberto e Souza and Marcelo Bernardes Vieira and Helio Pedrini},
title={Fuzzy Fusion for Two-stream Action Recognition},
booktitle={Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP},
year={2020},
pages={117-123},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008973901170123},
isbn={978-989-758-402-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 5: VISAPP
TI - Fuzzy Fusion for Two-stream Action Recognition
SN - 978-989-758-402-2
AU - Santos A.
AU - Maia H.
AU - Souza M.
AU - Vieira M.
AU - Pedrini H.
PY - 2020
SP - 117
EP - 123
DO - 10.5220/0008973901170123
PB - SciTePress