Temporal Perceptive Network for Skeleton-Based Action Recognition
Yueyu Hu, Chunhui Liu, Yanghao Li and Jiaying Liu
Abstract
The major challenge for skeleton-based action recognition is to distinguish the difference between various actions. Traditional Recurrent Neural Network (RNN) structure
may lead to unsatisfactory results due to the inefficiency in capturing local temporal
features, especially for large-scale datasets. To address this issue, we propose a novel
Temporal Perceptive Network (TPNet) to enable the robust feature learning for action
recognition. We design a temporal convolutional subnetwork, which can be embedded
between RNN layers, to enhance automatical feature extraction for local temporal dynamics. Experiments show that the proposed method achieves superior performance to
other methods and generates new state-of-the-art results.
Session
Posters
Files
Paper (PDF)
DOI
10.5244/C.31.72
https://dx.doi.org/10.5244/C.31.72
Citation
Yueyu Hu, Chunhui Liu, Yanghao Li and Jiaying Liu. Temporal Perceptive Network for Skeleton-Based Action Recognition. In T.K. Kim, S. Zafeiriou, G. Brostow and K. Mikolajczyk, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 72.1-72.12. BMVA Press, September 2017.
Bibtex
@inproceedings{BMVC2017_72,
title={Temporal Perceptive Network for Skeleton-Based Action Recognition},
author={Yueyu Hu, Chunhui Liu, Yanghao Li and Jiaying Liu},
year={2017},
month={September},
pages={72.1-72.12},
articleno={72},
numpages={12},
booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
publisher={BMVA Press},
editor={Tae-Kyun Kim, Stefanos Zafeiriou, Gabriel Brostow and Krystian Mikolajczyk},
doi={10.5244/C.31.72},
isbn={1-901725-60-X},
url={https://dx.doi.org/10.5244/C.31.72}
}