On the Representation of Occluded Shapes

Abstract

Most approaches to simultaneously recovering both model parameters and segmentation have relied on an edge field to represent segmentation. This restriction, and the implementations it leads to, have fundamental limitations in representing occluded stimuli. The authors develop a framework that overcomes these limitations by using multiple layers of explicit support to represent segmentation. Results from an initial implementation demonstrate that this method can segment images containing occluded objects. >

Cite

Text

Darrell and Pentland. "On the Representation of Occluded Shapes." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1991. doi:10.1109/CVPR.1991.139802

Markdown

[Darrell and Pentland. "On the Representation of Occluded Shapes." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1991.](https://mlanthology.org/cvpr/1991/darrell1991cvpr-representation/) doi:10.1109/CVPR.1991.139802

BibTeX

@inproceedings{darrell1991cvpr-representation,
  title     = {{On the Representation of Occluded Shapes}},
  author    = {Darrell, Trevor and Pentland, Alex},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1991},
  pages     = {728-729},
  doi       = {10.1109/CVPR.1991.139802},
  url       = {https://mlanthology.org/cvpr/1991/darrell1991cvpr-representation/}
}