S3Aug: Segmentation, Sampling, and Shift for Action Recognition

Taiki Sugiura, Toru Tamaki

2024

Abstract

Action recognition is a well-established area of research in computer vision. In this paper, we propose S3Aug, a video data augmenatation for action recognition. Unlike conventional video data augmentation methods that involve cutting and pasting regions from two videos, the proposed method generates new videos from a single training video through segmentation and label-to-image transformation. Furthermore, the proposed method modifies certain categories of label images by sampling to generate a variety of videos, and shifts intermediate features to enhance the temporal coherency between frames of the generate videos. Experimental results on the UCF101, HMDB51, and Mimetics datasets demonstrate the effectiveness of the proposed method, paricularlly for out-of-context videos of the Mimetics dataset.

Paper Citation

in Harvard Style

Sugiura T. and Tamaki T. (2024). S3Aug: Segmentation, Sampling, and Shift for Action Recognition. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP; ISBN 978-989-758-679-8, SciTePress, pages 71-79. DOI: 10.5220/0012310400003660

in Bibtex Style

@conference{visapp24,
author={Taiki Sugiura and Toru Tamaki},
title={S3Aug: Segmentation, Sampling, and Shift for Action Recognition},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP},
year={2024},
pages={71-79},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012310400003660},
isbn={978-989-758-679-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP
TI - S3Aug: Segmentation, Sampling, and Shift for Action Recognition
SN - 978-989-758-679-8
AU - Sugiura T.
AU - Tamaki T.
PY - 2024
SP - 71
EP - 79
DO - 10.5220/0012310400003660
PB - SciTePress