Abstract

This paper presents an approach to parsing humans when there is significant occlusion. We model humans using a graphical model which has a tree structure building on recent work [32, 6] and exploit the connectivity prior that, even in presence of occlusion, the visible nodes form a connected subtree of the graphical model. We call each con- nected subtree a flexible composition of object parts. This involves a novel method for learning occlusion cues. Dur- ing inference we need to search over a mixture of different flexible models. By exploiting part sharing, we show that this inference can be done extremely efficiently requiring only twice as many computations as searching for the entire object (i.e., not modeling occlusion). We evaluate our model on the standard benchmarked “We Are Family” Stickmen dataset and obtain significant performance improvements over the best alternative algorithms.

CVPR 15 Paper PDF
PDF

@InProceedings{Chen_CVPR15,
  title        = {Parsing Occluded People by Flexible Compositions},
  author       = {Xianjie Chen and Alan Yuille},
  booktitle    = {Computer Vision and Pattern Recognition (CVPR)},
  year         = {2015},
}


Estimation Examples

Pose Estimation Examples