Cue Integration for Figure/Ground Labeling

Abstract

We present a model of edge and region grouping using a conditional random field built over a scale-invariant representation of images to integrate multiple cues. Our model includes potentials that capture low-level similarity, mid-level curvilinear continuity and high-level object shape. Maximum likelihood parameters for the model are learned from human labeled groundtruth on a large collection of horse images using belief propagation. Using held out test data, we quantify the information gained by incorporating generic mid-level cues and high-level shape.

Cite

Text

Ren et al. "Cue Integration for Figure/Ground Labeling." Neural Information Processing Systems, 2005.

Markdown

[Ren et al. "Cue Integration for Figure/Ground Labeling." Neural Information Processing Systems, 2005.](https://mlanthology.org/neurips/2005/ren2005neurips-cue/)

BibTeX

@inproceedings{ren2005neurips-cue,
  title     = {{Cue Integration for Figure/Ground Labeling}},
  author    = {Ren, Xiaofeng and Malik, Jitendra and Fowlkes, Charless C.},
  booktitle = {Neural Information Processing Systems},
  year      = {2005},
  pages     = {1121-1128},
  url       = {https://mlanthology.org/neurips/2005/ren2005neurips-cue/}
}