Home > Research > Publications & Outputs > Skeleton Cloud Colorization for Unsupervised 3D...

Links

Text available via DOI:

View graph of relations

Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learning

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published

Standard

Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learning. / Yang, Siyuan; Liu, Jun; Lu, Shijian et al.
Proceedings - 2021 IEEE/CVF International Conference on Computer Vision, ICCV 2021. Institute of Electrical and Electronics Engineers Inc., 2022. p. 13403-13413 (Proceedings of the IEEE International Conference on Computer Vision).

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Harvard

Yang, S, Liu, J, Lu, S, Er, MH & Kot, AC 2022, Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learning. in Proceedings - 2021 IEEE/CVF International Conference on Computer Vision, ICCV 2021. Proceedings of the IEEE International Conference on Computer Vision, Institute of Electrical and Electronics Engineers Inc., pp. 13403-13413, 18th IEEE/CVF International Conference on Computer Vision, ICCV 2021, Virtual, Online, Canada, 11/10/21. https://doi.org/10.1109/ICCV48922.2021.01317

APA

Yang, S., Liu, J., Lu, S., Er, M. H., & Kot, A. C. (2022). Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learning. In Proceedings - 2021 IEEE/CVF International Conference on Computer Vision, ICCV 2021 (pp. 13403-13413). (Proceedings of the IEEE International Conference on Computer Vision). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCV48922.2021.01317

Vancouver

Yang S, Liu J, Lu S, Er MH, Kot AC. Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learning. In Proceedings - 2021 IEEE/CVF International Conference on Computer Vision, ICCV 2021. Institute of Electrical and Electronics Engineers Inc. 2022. p. 13403-13413. (Proceedings of the IEEE International Conference on Computer Vision). Epub 2021 Oct 10. doi: 10.1109/ICCV48922.2021.01317

Author

Yang, Siyuan ; Liu, Jun ; Lu, Shijian et al. / Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learning. Proceedings - 2021 IEEE/CVF International Conference on Computer Vision, ICCV 2021. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 13403-13413 (Proceedings of the IEEE International Conference on Computer Vision).

Bibtex

@inproceedings{c03d0bc78fed4bacb89e699011979c29,
title = "Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learning",
abstract = "Skeleton-based human action recognition has attracted increasing attention in recent years. However, most of the existing works focus on supervised learning which requiring a large number of annotated action sequences that are often expensive to collect. We investigate unsupervised representation learning for skeleton action recognition, and design a novel skeleton cloud colorization technique that is capable of learning skeleton representations from unlabeled skeleton sequence data. Specifically, we represent a skeleton action sequence as a 3D skeleton cloud and colorize each point in the cloud according to its temporal and spatial orders in the original (unannotated) skeleton sequence. Leveraging the colorized skeleton point cloud, we design an auto-encoder framework that can learn spatial-temporal features from the artificial color labels of skeleton joints effectively. We evaluate our skeleton cloud colorization approach with action classifiers trained under different configurations, including unsupervised, semi-supervised and fully-supervised settings. Extensive experiments on NTU RGB+D and NW-UCLA datasets show that the proposed method outperforms existing unsupervised and semi-supervised 3D action recognition methods by large margins, and it achieves competitive performance in supervised 3D action recognition as well.",
author = "Siyuan Yang and Jun Liu and Shijian Lu and Er, {Meng Hwa} and Kot, {Alex C.}",
note = "Publisher Copyright: {\textcopyright} 2021 IEEE; 18th IEEE/CVF International Conference on Computer Vision, ICCV 2021 ; Conference date: 11-10-2021 Through 17-10-2021",
year = "2022",
month = feb,
day = "28",
doi = "10.1109/ICCV48922.2021.01317",
language = "English",
isbn = "9781665428132",
series = "Proceedings of the IEEE International Conference on Computer Vision",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "13403--13413",
booktitle = "Proceedings - 2021 IEEE/CVF International Conference on Computer Vision, ICCV 2021",

}

RIS

TY - GEN

T1 - Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learning

AU - Yang, Siyuan

AU - Liu, Jun

AU - Lu, Shijian

AU - Er, Meng Hwa

AU - Kot, Alex C.

N1 - Publisher Copyright: © 2021 IEEE

PY - 2022/2/28

Y1 - 2022/2/28

N2 - Skeleton-based human action recognition has attracted increasing attention in recent years. However, most of the existing works focus on supervised learning which requiring a large number of annotated action sequences that are often expensive to collect. We investigate unsupervised representation learning for skeleton action recognition, and design a novel skeleton cloud colorization technique that is capable of learning skeleton representations from unlabeled skeleton sequence data. Specifically, we represent a skeleton action sequence as a 3D skeleton cloud and colorize each point in the cloud according to its temporal and spatial orders in the original (unannotated) skeleton sequence. Leveraging the colorized skeleton point cloud, we design an auto-encoder framework that can learn spatial-temporal features from the artificial color labels of skeleton joints effectively. We evaluate our skeleton cloud colorization approach with action classifiers trained under different configurations, including unsupervised, semi-supervised and fully-supervised settings. Extensive experiments on NTU RGB+D and NW-UCLA datasets show that the proposed method outperforms existing unsupervised and semi-supervised 3D action recognition methods by large margins, and it achieves competitive performance in supervised 3D action recognition as well.

AB - Skeleton-based human action recognition has attracted increasing attention in recent years. However, most of the existing works focus on supervised learning which requiring a large number of annotated action sequences that are often expensive to collect. We investigate unsupervised representation learning for skeleton action recognition, and design a novel skeleton cloud colorization technique that is capable of learning skeleton representations from unlabeled skeleton sequence data. Specifically, we represent a skeleton action sequence as a 3D skeleton cloud and colorize each point in the cloud according to its temporal and spatial orders in the original (unannotated) skeleton sequence. Leveraging the colorized skeleton point cloud, we design an auto-encoder framework that can learn spatial-temporal features from the artificial color labels of skeleton joints effectively. We evaluate our skeleton cloud colorization approach with action classifiers trained under different configurations, including unsupervised, semi-supervised and fully-supervised settings. Extensive experiments on NTU RGB+D and NW-UCLA datasets show that the proposed method outperforms existing unsupervised and semi-supervised 3D action recognition methods by large margins, and it achieves competitive performance in supervised 3D action recognition as well.

U2 - 10.1109/ICCV48922.2021.01317

DO - 10.1109/ICCV48922.2021.01317

M3 - Conference contribution/Paper

AN - SCOPUS:85120493310

SN - 9781665428132

T3 - Proceedings of the IEEE International Conference on Computer Vision

SP - 13403

EP - 13413

BT - Proceedings - 2021 IEEE/CVF International Conference on Computer Vision, ICCV 2021

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 18th IEEE/CVF International Conference on Computer Vision, ICCV 2021

Y2 - 11 October 2021 through 17 October 2021

ER -