TVNet: Temporal Voting Network for Action Localization

Hanyuan Wang, Dima Damen, Majid Mirmehdi, Toby Perrett

2022

Abstract

We propose a Temporal Voting Network (TVNet) for action localization in untrimmed videos. This incorporates a novel Voting Evidence Module to locate temporal boundaries, more accurately, where temporal contextual evidence is accumulated to predict frame-level probabilities of start and end action boundaries. Our action-independent evidence module is incorporated within a pipeline to calculate confidence scores and action classes. We achieve an average mAP of 34.6% on ActivityNet-1.3, particularly outperforming previous methods with the highest IoU of 0.95. TVNet also achieves mAP of 56.0% when combined with PGCN and 59.1% with MUSES at 0.5 IoU on THUMOS14 and outperforms prior work at all thresholds. Our code is available at https://github.com/hanielwang/TVNet.

Paper Citation

in Harvard Style

Wang H., Damen D., Mirmehdi M. and Perrett T. (2022). TVNet: Temporal Voting Network for Action Localization. In Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 5: VISAPP; ISBN 978-989-758-555-5, SciTePress, pages 550-558. DOI: 10.5220/0010868900003124

in Bibtex Style

@conference{visapp22,
author={Hanyuan Wang and Dima Damen and Majid Mirmehdi and Toby Perrett},
title={TVNet: Temporal Voting Network for Action Localization},
booktitle={Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 5: VISAPP},
year={2022},
pages={550-558},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010868900003124},
isbn={978-989-758-555-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 5: VISAPP
TI - TVNet: Temporal Voting Network for Action Localization
SN - 978-989-758-555-5
AU - Wang H.
AU - Damen D.
AU - Mirmehdi M.
AU - Perrett T.
PY - 2022
SP - 550
EP - 558
DO - 10.5220/0010868900003124
PB - SciTePress