View Adaptive Neural Networks for High Performance Skeleton-Based Human Action Recognition

Xi'an Jiaotong University · Microsoft Research Asia (China) · +2 more institutions

PubMed
Indexed incrossrefpubmed

Abstract

Skeleton-based human action recognition has recently attracted increasing attention thanks to the accessibility and the popularity of 3D skeleton data. One of the key challenges in action recognition lies in the large variations of action representations when they are captured from different viewpoints. In order to alleviate the effects of view variations, this paper introduces a novel view adaptation scheme, which automatically determines the virtual observation viewpoints over the course of an action in a learning based data driven manner. Instead of re-positioning the skeletons using a fixed human-defined prior criterion, we design two view adaptive neural networks, i.e., VA-RNN and VA-CNN, which are…

Citation impact

519
total citations
FWCI
28.37
Percentile
100%
References
82
Citations per year

Authors

6

Topics & keywords

Keywords
  • Viewpoints
  • Computer science
  • Artificial intelligence
  • Convolutional neural network
  • Machine learning
  • Artificial neural network
  • Deep learning
  • Recurrent neural network
No related works found for this paper.

Funding