Multiple Pose Context Trees for Estimating Human Pose in Object Context

Abstract

We address the problem of estimating pose in a static image of a human performing an action that may involve interaction with scene objects. In such scenarios, pose can be estimated more accurately using the knowledge of scene objects. Previous approaches do not make use of such contextual information. We propose Pose Context trees to jointly model human pose and object which allows both accurate and efficient inference when the nature of interaction is known. To estimate the pose in an image, we present a Bayesian framework that infers the optimal pose-object pair by maximizing the likelihood over multiple pose context trees for all interactions. We evaluate our approach on a dataset of 65 images, and show that the joint inference of pose and context gives higher pose accuracy.

Cite

Text

Singh et al. "Multiple Pose Context Trees for Estimating Human Pose in Object Context." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2010. doi:10.1109/CVPRW.2010.5543186

Markdown

[Singh et al. "Multiple Pose Context Trees for Estimating Human Pose in Object Context." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2010.](https://mlanthology.org/cvprw/2010/singh2010cvprw-multiple/) doi:10.1109/CVPRW.2010.5543186

BibTeX

@inproceedings{singh2010cvprw-multiple,
  title     = {{Multiple Pose Context Trees for Estimating Human Pose in Object Context}},
  author    = {Singh, Vivek Kumar and Khan, Furqan Muhammad and Nevatia, Ram},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2010},
  pages     = {17-24},
  doi       = {10.1109/CVPRW.2010.5543186},
  url       = {https://mlanthology.org/cvprw/2010/singh2010cvprw-multiple/}
}