Learning Human Pose Models from Synthesized Data for Robust RGB-D Action Recognition

@article{Liu2017LearningHP,
  title={Learning Human Pose Models from Synthesized Data for Robust RGB-D Action Recognition},
  author={Jian Wei Liu and Ajmal Mian},
  journal={ArXiv},
  year={2017},
  volume={abs/1707.00823}
}
We propose Human Pose Models that represent RGB and depth images of human poses independent of clothing textures, backgrounds, lighting conditions, body shapes and camera viewpoints. Learning such universal models requires training images where all factors are varied for every human pose. Capturing such data is prohibitively expensive. Therefore, we develop a framework for synthesizing the training data. First, we learn representative human poses from a large corpus of real motion captured… CONTINUE READING
9
Twitter Mentions

Similar Papers

Citations

Publications citing this paper.
SHOWING 1-4 OF 4 CITATIONS

References

Publications referenced by this paper.
SHOWING 1-10 OF 74 REFERENCES

Learning a Deep Model for Human Action Recognition from Novel Viewpoints

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2018
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Deep Multimodal Feature Analysis for Action Recognition in RGB+D Videos

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2016
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Learning a non-linear knowledge transfer model for cross-view action recognition

  • 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

Cross-View Action Modeling, Learning, and Recognition

  • 2014 IEEE Conference on Computer Vision and Pattern Recognition
  • 2014
VIEW 17 EXCERPTS
HIGHLY INFLUENTIAL

Going deeper with convolutions

  • 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2014
VIEW 13 EXCERPTS
HIGHLY INFLUENTIAL

Discriminative virtual views for cross-view action recognition

  • 2012 IEEE Conference on Computer Vision and Pattern Recognition
  • 2012
VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

Learning from Simulated and Unsupervised Images through Adversarial Training

  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Long-Term Temporal Convolutions for Action Recognition

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2016
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL