Generalized Pose Decoupled Network for Unsupervised 3D Skeleton Sequence-Based Action Representation Learning
Human action representation is derived from the description of human shape and motion. The traditional unsupervised 3-dimensional (3D) human action representation learning method uses a recurrent neural network (RNN)-based autoencoder to reconstruct the input pose sequence and then takes the midleve...
Main Authors: | Mengyuan Liu, Fanyang Meng, Yongsheng Liang |
---|---|
Format: | Article |
Language: | English |
Published: |
American Association for the Advancement of Science (AAAS)
2022-01-01
|
Series: | Cyborg and Bionic Systems |
Online Access: | https://spj.science.org/doi/10.34133/cbsystems.0002 |
Similar Items
-
Pose-Guided Graph Convolutional Networks for Skeleton-Based Action Recognition
by: Han Chen, et al.
Published: (2022-01-01) -
SKELTER: unsupervised skeleton action denoising and recognition using transformers
by: Giancarlo Paoletti, et al.
Published: (2023-08-01) -
Future Pose Prediction from 3D Human Skeleton Sequence with Surrounding Situation
by: Tomohiro Fujita, et al.
Published: (2023-01-01) -
Sequence Segmentation Attention Network for Skeleton-Based Action Recognition
by: Yujie Zhang, et al.
Published: (2023-03-01) -
Comparative Analysis of Skeleton-Based Human Pose Estimation
by: Jen-Li Chung, et al.
Published: (2022-12-01)