Effective Active Skeleton Representation for Low Latency Human Action Recognition

By Xingyang Cai, Wen-gang Zhou, Lei Wu, Jiebo Luo, Houqiang Li. 2016

87 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. Zhi Zhang
2. Guanghan Ning
3. Zhiquan He

In Computer Vision and Pattern Recognition

1. Wen-gang Zhou
2. Zhi Zhang
3. Weiping Li
4. Houqiang Li
5. Jie Huang
6. Guanghan Ning
7. Qilin Zhang
8. Zhiquan He

In Human-Computer Interaction

1. Zhi Zhang
2. Houqiang Li
3. Guanghan Ning
4. Wen-gang Zhou
5. Zhiquan He

Citations in the corpus

• Skeleton-Based Action Recognition Using Spatio-Temporal LSTM Network with Trust Gates (2017, neutral): “Skeleton-based action recognition has been explored in different aspects in recent years [40], [41], [42], [43], [44], [45], [46], [47], [48], [49], [50], [51], [52], [53], [54], [55], [56], [57].”
• Video-based Sign Language Recognition without Temporal Segmentation (2018, background): “Most existing SLR researches (Huang et al. 2015; Guo et al. 2016; Dan Guo and Wang 2017; Liu, Zhou, and Li 2016) fall into the category of isolated SLR, i.e., recognition of words or expressions, similar to action recognition (Cai et al. 2016).”
• Knowledge-Guided Deep Fractal Neural Networks for Human Pose Estimation (2017, background): “high-level computer vision tasks, including action and activity recognition [11]–[13], semantic content retrieval [14], humancomputer interaction, motion capture [15], and animation.”