3D Action Recognition from Novel Viewpoints

@article{Rahmani20163DAR,
  title={3D Action Recognition from Novel Viewpoints},
  author={Hossein A. Rahmani and Ajmal S. Mian},
  journal={2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2016},
  pages={1506-1515}
}
We propose a human pose representation model that transfers human poses acquired from different unknown views to a view-invariant high-level space. The model is a deep convolutional neural network and requires a large corpus of multiview training data which is very expensive to acquire. Therefore, we propose a method to generate this data by fitting synthetic 3D human models to real motion capture data and rendering the human poses from numerous viewpoints. While learning the CNN model, we do… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 54 CITATIONS, ESTIMATED 51% COVERAGE

106 Citations

020402016201720182019
Citations per Year
Semantic Scholar estimates that this publication has 106 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
SHOWING 1-10 OF 33 REFERENCES

Similar Papers

Loading similar papers…