A survey on deep learning techniques for action anticipation
The ability to anticipate possible future human actions is essential for a wide range of applications, including autonomous driving and human-robot interaction. Consequently, numerous methods have been introduced for action anticipation in recent years, with deep learning-based approaches being particularly popular. In this work, we review the recent advances of action anticipation algorithms with a particular focus on daily-living scenarios. Additionally, we classify these methods according to their primary contributions and summarize them in tabular form, allowing readers to grasp the details at a glance. Furthermore, we delve into the common evaluation metrics and datasets used for action anticipation and provide future directions with systematical discussions.
- Veröffentlicht in:
arXiv - Typ:
Article - Autoren:
- Jahr:
2023 - Source:
https://arxiv.org/abs/2309.17257
Informationen zur Zitierung
: A survey on deep learning techniques for action anticipation, arXiv, 2023, https://arxiv.org/abs/2309.17257, Zhong.etal.2023b,
@Article{Zhong.etal.2023b,
author={Zhong, Zeyun; Martin, Manuel; Voit, Michael; Gall, Jürgen; Beyerer, Jürgen},
title={A survey on deep learning techniques for action anticipation},
journal={arXiv},
url={https://arxiv.org/abs/2309.17257},
year={2023},
abstract={The ability to anticipate possible future human actions is essential for a wide range of applications, including autonomous driving and human-robot interaction. Consequently, numerous methods have been introduced for action anticipation in recent years, with deep learning-based approaches being particularly popular. In this work, we review the recent advances of action anticipation algorithms...}}
