Corpus ID: 212675473

Skeleton Based Action Recognition using a Stacked Denoising Autoencoder with Constraints of Privileged Information

@article{Wu2020SkeletonBA,
  title={Skeleton Based Action Recognition using a Stacked Denoising Autoencoder with Constraints of Privileged Information},
  author={Zhi-Ze Wu and T. Weise and Le Zou and Fei Sun and Ming Tan},
  journal={ArXiv},
  year={2020},
  volume={abs/2003.05684}
}
Recently, with the availability of cost-effective depth cameras coupled with real-time skeleton estimation, the interest in skeleton-based human action recognition is renewed. Most of the existing skeletal representation approaches use either the joint location or the dynamics model. Differing from the previous studies, we propose a new method called Denoising Autoencoder with Temporal and Categorical Constraints (DAE_CTC)} to study the skeletal representation in a view of skeleton… Expand

References

SHOWING 1-10 OF 56 REFERENCES
Mining actionlet ensemble for action recognition with depth cameras
  • 1,271
  • PDF
Leveraging Hierarchical Parametric Networks for Skeletal Joints Based Action Segmentation and Recognition
  • D. Wu, L. Shao
  • Computer Science
  • 2014 IEEE Conference on Computer Vision and Pattern Recognition
  • 2014
  • 175
  • PDF
A New Representation of Skeleton Sequences for 3D Action Recognition
  • 383
  • PDF
Multimodal Deep Autoencoder for Human Pose Recovery
  • 370
Interpretable 3D Human Action Analysis with Temporal Convolutional Networks
  • T. Kim, A. Reiter
  • Computer Science
  • 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
  • 2017
  • 264
  • PDF
Accurate 3D action recognition using learning on the Grassmann manifold
  • 159
  • PDF
...
1
2
3
4
5
...