Max-Margin Boltzmann Machines for Object Segmentation

@article{Yang2014MaxMarginBM,
  title={Max-Margin Boltzmann Machines for Object Segmentation},
  author={Jimei Yang and Simon Safar and Ming-Hsuan Yang},
  journal={2014 IEEE Conference on Computer Vision and Pattern Recognition},
  year={2014},
  pages={320-327}
}
We present Max-Margin Boltzmann Machines (MMBMs) for object segmentation. MMBMs are essentially a class of Conditional Boltzmann Machines that model the joint distribution of hidden variables and output labels conditioned on input observations. In addition to image-to-label connections, we build direct image-to-hidden connections to facilitate global shape prediction, and thus derive a simple Iterated Conditional Modes algorithm for efficient maximum a posteriori inference. We formulate a max… CONTINUE READING
Highly Cited
This paper has 24 citations. REVIEW CITATIONS

From This Paper

Figures, tables, and topics from this paper.

Citations

Publications citing this paper.
Showing 1-10 of 17 extracted citations

Object segmentation with deep regression

2015 IEEE International Conference on Image Processing (ICIP) • 2015
View 10 Excerpts
Highly Influenced

Learning location constrained pixel classifiers for image parsing

J. Visual Communication and Image Representation • 2017
View 2 Excerpts

ShapeOdds: Variational Bayesian Learning of Generative Shape Models

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) • 2017
View 1 Excerpt

Deep conditional neural network for image segmentation

2016 IEEE International Conference on Multimedia and Expo (ICME) • 2016
View 3 Excerpts

References

Publications referenced by this paper.
Showing 1-10 of 28 references

Exploring Compositional High Order Pattern Potentials for Structured Output Learning

2013 IEEE Conference on Computer Vision and Pattern Recognition • 2013
View 20 Excerpts
Highly Influenced

Contour Detection and Hierarchical Image Segmentation

IEEE Transactions on Pattern Analysis and Machine Intelligence • 2011
View 9 Excerpts
Highly Influenced

Shape-based pedestrian parsing

CVPR 2011 • 2011
View 4 Excerpts
Highly Influenced

Deep Boltzmann Machines

View 17 Excerpts
Highly Influenced

Augmenting CRFs with Boltzmann Machine Shape Priors for Image Labeling

2013 IEEE Conference on Computer Vision and Pattern Recognition • 2013
View 3 Excerpts

Deep Learning Shape Priors for Object Segmentation

2013 IEEE Conference on Computer Vision and Pattern Recognition • 2013
View 1 Excerpt

Similar Papers

Loading similar papers…