Learning Latent Global Network for Skeleton-based Action Prediction

Qiuhong Ke, Mohammed Bennamoun, Hossein Rahmani, Senjian An, Ferdous Sohel, Farid Boussaid

Research output: Contribution to journalArticle

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.

Original languageEnglish
Pages (from-to)959-970
JournalIEEE Transactions on Image Processing
DOIs
Publication statusPublished - 2 Sep 2019

Fingerprint

Lighting

Cite this

@article{5630e60522f4413691a8c49f668104aa,
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.",
keywords = "adversarial learning, Australia, convolutional neural networks, Lighting, Recurrent neural networks, Skeleton, Skeleton-based action prediction, Three-dimensional displays, Video sequences, Videos",
author = "Qiuhong Ke and Mohammed Bennamoun and Hossein Rahmani and Senjian An and Ferdous Sohel and Farid Boussaid",
year = "2019",
month = "9",
day = "2",
doi = "10.1109/TIP.2019.2937757",
language = "English",
pages = "959--970",
journal = "IEEE Transactions on Image Processing",
issn = "1057-7149",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",

}

Learning Latent Global Network for Skeleton-based Action Prediction. / Ke, Qiuhong; Bennamoun, Mohammed; Rahmani, Hossein; An, Senjian; Sohel, Ferdous; Boussaid, Farid.

In: IEEE Transactions on Image Processing, 02.09.2019, p. 959-970.

Research output: Contribution to journalArticle

TY - JOUR

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

AU - Ke, Qiuhong

AU - Bennamoun, Mohammed

AU - Rahmani, Hossein

AU - An, Senjian

AU - Sohel, Ferdous

AU - Boussaid, Farid

PY - 2019/9/2

Y1 - 2019/9/2

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.

KW - adversarial learning

KW - Australia

KW - convolutional neural networks

KW - Lighting

KW - Recurrent neural networks

KW - Skeleton

KW - Skeleton-based action prediction

KW - Three-dimensional displays

KW - Video sequences

KW - Videos

UR - http://www.scopus.com/inward/record.url?scp=85072182411&partnerID=8YFLogxK

U2 - 10.1109/TIP.2019.2937757

DO - 10.1109/TIP.2019.2937757

M3 - Article

SP - 959

EP - 970

JO - IEEE Transactions on Image Processing

JF - IEEE Transactions on Image Processing

SN - 1057-7149

ER -