Representation Learning of Temporal Dynamics for Skeleton-Based Action Recognition

By Yong Du, Yun Raymond Fu, Liang Wang. 2016

147 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, Control and Systems Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

1. Jun Liu
2. Qiuhong Ke
3. Hanqing Lu
4. Yifan Zhang
5. Jian Cheng
6. Amir Shahroudy
7. Liang Wang
8. G. Wang

In Computer Vision and Pattern Recognition

1. Jun Liu
2. G. Wang
3. Qiuhong Ke
4. Mohammed Bennamoun
5. Amir Shahroudy
6. Liang Wang
7. Hanqing Lu
8. Jian Cheng

In Control and Systems Engineering

1. Hongsong Wang
2. Jun Liu
3. Liang Wang
4. Bo Li
5. Qiuhong Ke
6. Yucheng Chen
7. Wenjun Zeng
8. Mohammed Bennamoun

Citations in the corpus

• Modeling Temporal Dynamics and Spatial Configurations of Actions Using Two-Stream Recurrent Neural Networks (2017, methodology): “[7, 6] first design an end-to-end hierarchical RNN architecture for skeleton based action recognition.”
• Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition (2016, methodology): “Human action recognition using 3D skeleton information is explored in different aspects during recent years [33–50].”
• Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videos (2019, methodology): “[7] proposed to divide the skeleton joints into five parts, which are jointly modeled in a five-branch bidirectional neural network.”
• Learning Clip Representations for Skeleton-Based 3D Action Recognition (2018, methodology): “12%, which is similar to HBRNN-L [49].”
• Skeleton based action recognition using translation-scale invariant image mapping and multi-scale deep CNN (2017, background): “As for the 3D skeleton based action recognition problem, Recurrent Neural Networks (RNNs) have been widely adopted [8]–[14].”
• View Adaptive Neural Networks for High Performance Skeleton-Based Human Action Recognition (2018, background): “Usually, two of the views are used for training and the other one is used for testing [5], [47].”
• Skeleton boxes: Solving skeleton based action detection with a single deep convolutional neural network (2017, background): “Recently, 3D skeleton activity analysis has drawn great attentions [2–8].”