Inferring 3D body pose using variational semi-parametric regression

Yan Tian, Yonghua Jia, Yuan Shi, Yong Liu, Hao Ji, Leonid SigalICIP 2011 · OpenReview

Abstract

To deal with multi-modality in human pose estimation, mixture models or local models are introduced. However, problems with over-fitting and generalization are caused by our necessarily limited data, and the regression parameters need to be determined without resorting to slow and processor-hungry techniques, such as cross validation. To compensate these problems, we have developed a semi-parametric regression model in latent space with variational inference. Our method performed competitively in comparison to other current methods.
BibTeX
@inproceedings{tian2011inferring,
  author = {Yan Tian and Yonghua Jia and Yuan Shi and Yong Liu and Hao Ji and Leonid Sigal},
  title = {{Inferring 3D body pose using variational semi-parametric regression}},
  booktitle = {ICIP},
  year = {2011},
  url = {https://openreview.net/forum?id=Cr7XcLolSgB},
}

Loading related content...

Figure