Implicitly using Human Skeleton in Self-supervised Learning: Influence on Spatio-temporal Puzzle Solving and on Video Action Recognition

Mathieu Riand, Mathieu Riand, Laurent Dollé, Patrick Le Callet

2021

Abstract

In this paper we studied the influence of adding skeleton data on top of human actions videos when performing self-supervised learning and action recognition. We show that adding this information without additional constraints actually hurts the accuracy of the network; we argue that the added skeleton is not considered by the network and seen as a noise masking part of the natural image. We bring first results on puzzle solving and video action recognition to support this hypothesis.

Download


Paper Citation


in Harvard Style

Riand M., Dollé L. and Le Callet P. (2021). Implicitly using Human Skeleton in Self-supervised Learning: Influence on Spatio-temporal Puzzle Solving and on Video Action Recognition. In Proceedings of the 2nd International Conference on Robotics, Computer Vision and Intelligent Systems - Volume 1: ROBOVIS, ISBN 978-989-758-537-1, pages 128-135. DOI: 10.5220/0010689500003061


in Bibtex Style

@conference{robovis21,
author={Mathieu Riand and Laurent Dollé and Patrick Le Callet},
title={Implicitly using Human Skeleton in Self-supervised Learning: Influence on Spatio-temporal Puzzle Solving and on Video Action Recognition},
booktitle={Proceedings of the 2nd International Conference on Robotics, Computer Vision and Intelligent Systems - Volume 1: ROBOVIS,},
year={2021},
pages={128-135},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010689500003061},
isbn={978-989-758-537-1},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 2nd International Conference on Robotics, Computer Vision and Intelligent Systems - Volume 1: ROBOVIS,
TI - Implicitly using Human Skeleton in Self-supervised Learning: Influence on Spatio-temporal Puzzle Solving and on Video Action Recognition
SN - 978-989-758-537-1
AU - Riand M.
AU - Dollé L.
AU - Le Callet P.
PY - 2021
SP - 128
EP - 135
DO - 10.5220/0010689500003061