Learning Latent Global Network for Skeleton-Based Action Prediction
- 2 September 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 29 (10577149) , 959-970
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
Funding Information
- Australian Research Council (DP150100294, DP150104251, DE120102960)
This publication has 38 references indexed in Scilit:
- Recurrent Neural Networks for driver activity anticipation via sensory-fusion architecture2016
- Learning Spatiotemporal Features with 3D Convolutional Networks2015
- Long-term recurrent convolutional networks for visual recognition and description2015
- Modeling video evolution for action recognition2015
- Jointly learning heterogeneous features for RGB-D activity recognition2015
- Leveraging Hierarchical Parametric Networks for Skeletal Joints Based Action Segmentation and Recognition2014
- Human Action Recognition by Representing 3D Skeletons as Points in a Lie Group2014
- Speech recognition with deep recurrent neural networks2013
- Mining actionlet ensemble for action recognition with depth cameras2012
- Neural Networks2012