Multi branch disentangling for pose estimation

Presentation

This is a work in progress so you might want to check it out later

Architecture

$E_p$ pose encoder: $E_a$ appearance encoder (ResNet18): $D$ decoder:

There will be a nice picture here at some point

Acknowledgements

The pose estimation encoder ($E_p$) is built on the work of Diogo Luvizon from the paper:

@InProceedings{Luvizon_2018_CVPR,
  author = {Luvizon, Diogo C. and Picard, David and Tabia, Hedi},
  title = {2D/3D Pose Estimation and Action Recognition Using Multitask Deep Learning},
  booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  month = {June},
  year = {2018}
}