Learning What and How of Contextual Models for Scene Labeling

Abstract

We present a data-driven approach to predict the importance of edges and construct a Markov network for image analysis based on statistical models of global and local image features. We also address the coupled problem of predicting the feature weights associated with each edge of a Markov network for evaluation of context. Experimental results indicate that this scene dependent structure construction model eliminates spurious edges and improves performance over fully-connected and neighborhood connected Markov network.

Cite

Text

Jain et al. "Learning What and How of Contextual Models for Scene Labeling." European Conference on Computer Vision, 2010. doi:10.1007/978-3-642-15561-1_15

Markdown

[Jain et al. "Learning What and How of Contextual Models for Scene Labeling." European Conference on Computer Vision, 2010.](https://mlanthology.org/eccv/2010/jain2010eccv-learning/) doi:10.1007/978-3-642-15561-1_15

BibTeX

@inproceedings{jain2010eccv-learning,
  title     = {{Learning What and How of Contextual Models for Scene Labeling}},
  author    = {Jain, Arpit and Gupta, Abhinav and Davis, Larry S.},
  booktitle = {European Conference on Computer Vision},
  year      = {2010},
  pages     = {199-212},
  doi       = {10.1007/978-3-642-15561-1_15},
  url       = {https://mlanthology.org/eccv/2010/jain2010eccv-learning/}
}