Informative joints based human action recognition using skeleton contexts

By Min Jiang, Jun Kong, George Bebis, Hongtao Huo. 2015

82 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, Human-Computer Interaction

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. G. Wang
3. Ling-yu Duan
4. Alex ChiChung Kot
5. Nanning Zheng
6. Pengfei Zhang
7. Jianru Xue
8. Cuiling Lan

In Computer Vision and Pattern Recognition

1. Jun Liu
2. G. Wang
3. Alex ChiChung Kot
4. Ling-yu Duan
5. Amir Shahroudy
6. Wenjun Zeng
7. Cuiling Lan
8. Nanning Zheng

In Human-Computer Interaction

1. Jun Liu
2. Alex ChiChung Kot
3. Ling-yu Duan
4. G. Wang
5. Nanning Zheng
6. Wenjun Zeng
7. Ennio Gambi
8. Susanna Spinsante

Citations in the corpus

• Skeleton-Based Human Action Recognition With Global Context-Aware Attention LSTM Networks (2017, background): “Thus, it is beneficial to selectively focus on the informative joints in each frame of the sequence, and try to ignore the features of the irrelevant ones, as the latter contribute very little for action recognition, and even bring noise which corrupts the performance [13].”
• Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates (2017, neutral): “5% SCs (Informative Joints) [85] Geometric 88.”
• Low-Rank Tensor Subspace Learning for RGB-D Action Recognition (2016, background): “• Jiang et al. [42] calculated stacked histogram of the joint parts of the human skeleton as features.”
• Global Context-Aware Attention LSTM Networks for 3D Action Recognition (2017, background): “Previous works [20, 6] have already shown that in each action sequence, there is often a subset of informative joints which are important as they contribute much more to action analysis, while the other ones can be irrelevant (or even noisy) to this action.”
• View Adaptive Neural Networks for High Performance Skeleton-Based Human Action Recognition (2018, methodology): “To be view-invariant, the commonly used strategies are to perform pre-processing of skeletons [6], [17], [25], [27], [29], [38], [42], [45], [55], [62].”
• A Human Activity Recognition System Using Skeleton Data from RGBD Sensors (2016, methodology): “Some works developed techniques to automatically select the most informative joints, aiming at increasing the recognition accuracy and reducing the noise effect on the skeleton estimation [35, 36].”