ML Anthology

Piecing Together the Segmentation Jigsaw Using Context

Xi Chen, Arpit Jain, Abhinav Gupta, Larry S. Davis
CVPR 2011 pp. 2001-2008
doi:10.1109/CVPR.2011.5995367 /cvpr/2011/chen2011cvpr-piecing/

Abstract

We present an approach to jointly solve the segmentation and recognition problem using a multiple segmentation framework. We formulate the problem as segment selection from a pool of segments, assigning each selected segment a class label. Previous multiple segmentation approaches used local appearance matching to select segments in a greedy manner. In contrast, our approach formulates a cost function based on contextual information in conjunction with appearance matching. This relaxed cost function formulation is minimized using an efficient quadratic programming solver and an approximate solution is obtained by discretizing the relaxed solution. Our approach improves labeling performance compared to other segmentation based recognition approaches.

PDF CVPR Semantic Scholar

Cite

Text

Chen et al. "Piecing Together the Segmentation Jigsaw Using Context." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011. doi:10.1109/CVPR.2011.5995367

Markdown

[Chen et al. "Piecing Together the Segmentation Jigsaw Using Context." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011.](https://mlanthology.org/cvpr/2011/chen2011cvpr-piecing/) doi:10.1109/CVPR.2011.5995367

BibTeX

@inproceedings{chen2011cvpr-piecing,
  title     = {{Piecing Together the Segmentation Jigsaw Using Context}},
  author    = {Chen, Xi and Jain, Arpit and Gupta, Abhinav and Davis, Larry S.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2011},
  pages     = {2001-2008},
  doi       = {10.1109/CVPR.2011.5995367},
  url       = {https://mlanthology.org/cvpr/2011/chen2011cvpr-piecing/}
}