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
N1 - Funding Information:
Manuscript received February 12, 2019; revised July 22, 2019; accepted August 12, 2019. Date of publication September 2, 2019; date of current version October 9, 2019. This work was supported by the Australian Research Council under Grant DP150100294, Grant DP150104251, and Grant DE120102960. The associate editor coordinating the review of this manuscript and approving it for publication was Prof. Lisimachos P. Kondi. (Corresponding author: Qiuhong Ke.) Q. Ke is with the School of Computing and Information Systems, The University of Melbourne, Melbourne, VIC 3010, Australia, and also with the Max Planck Institute for Informatics, 66123 Saarland, Germany (e-mail: [email protected]).
Publisher Copyright:
© 1992-2012 IEEE.
PY - 2020/9/2
Y1 - 2020/9/2
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 - convolutional neural networks
KW - Skeleton-based action prediction
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
C2 - 31484121
AN - SCOPUS:85072182411
SN - 1057-7149
VL - 29
SP - 959
EP - 970
JO - IEEE Transactions on Image Processing
JF - IEEE Transactions on Image Processing
ER -