Home > Research > Publications & Outputs > Learning Latent Global Network for Skeleton-bas...

Electronic data

  • bare_jrnl7

    Rights statement: ©2019 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

    Accepted author manuscript, 2.17 MB, PDF document

    Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License

Links

Text available via DOI:

View graph of relations

Learning Latent Global Network for Skeleton-based Action Prediction

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Learning Latent Global Network for Skeleton-based Action Prediction. / Ke, Qiuhong; Rahmani, Hossein.

In: IEEE Transactions on Image Processing, Vol. 29, 01.01.2020, p. 959 - 970.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

APA

Vancouver

Ke Q, Rahmani H. Learning Latent Global Network for Skeleton-based Action Prediction. IEEE Transactions on Image Processing. 2020 Jan 1;29:959 - 970. Epub 2019 Sep 2. doi: 10.1109/TIP.2019.2937757

Author

Ke, Qiuhong ; Rahmani, Hossein. / Learning Latent Global Network for Skeleton-based Action Prediction. In: IEEE Transactions on Image Processing. 2020 ; Vol. 29. pp. 959 - 970.

Bibtex

@article{3df8bda760f64ede970a30037f8c9cdc,
title = "Learning Latent Global Network for Skeleton-based Action Prediction",
abstract = "Human actions represented with 3D skeleton sequences are robust to clustered backgrounds and illumination changes. In this paper, we investigate skeleton-based action prediction, which aims to recognize an action from a partial skeleton sequence that contains incomplete action information.We propose a new Latent Global Network based on adversarial learning for action prediction. We demonstrate that the proposed network provides latent long-term global information that is complementary to the local action information of the partial sequences and helps improve action prediction. We show that action prediction can be improved by combining the latent global information with the local action information. We test the proposed method on three challenging skeleton datasets and report state-of-the-art performance.",
author = "Qiuhong Ke and Hossein Rahmani",
note = "{\textcopyright}2019 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE. ",
year = "2020",
month = jan,
day = "1",
doi = "10.1109/TIP.2019.2937757",
language = "English",
volume = "29",
pages = "959 -- 970",
journal = "IEEE Transactions on Image Processing",
issn = "1057-7149",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

RIS

TY - JOUR

T1 - Learning Latent Global Network for Skeleton-based Action Prediction

AU - Ke, Qiuhong

AU - Rahmani, Hossein

N1 - ©2019 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

PY - 2020/1/1

Y1 - 2020/1/1

N2 - Human actions represented with 3D skeleton sequences are robust to clustered backgrounds and illumination changes. In this paper, we investigate skeleton-based action prediction, which aims to recognize an action from a partial skeleton sequence that contains incomplete action information.We propose a new Latent Global Network based on adversarial learning for action prediction. We demonstrate that the proposed network provides latent long-term global information that is complementary to the local action information of the partial sequences and helps improve action prediction. We show that action prediction can be improved by combining the latent global information with the local action information. We test the proposed method on three challenging skeleton datasets and report state-of-the-art performance.

AB - Human actions represented with 3D skeleton sequences are robust to clustered backgrounds and illumination changes. In this paper, we investigate skeleton-based action prediction, which aims to recognize an action from a partial skeleton sequence that contains incomplete action information.We propose a new Latent Global Network based on adversarial learning for action prediction. We demonstrate that the proposed network provides latent long-term global information that is complementary to the local action information of the partial sequences and helps improve action prediction. We show that action prediction can be improved by combining the latent global information with the local action information. We test the proposed method on three challenging skeleton datasets and report state-of-the-art performance.

U2 - 10.1109/TIP.2019.2937757

DO - 10.1109/TIP.2019.2937757

M3 - Journal article

VL - 29

SP - 959

EP - 970

JO - IEEE Transactions on Image Processing

JF - IEEE Transactions on Image Processing

SN - 1057-7149

ER -