Collective Activity Detection Using Hinge-Loss Markov Random Fields
Abstract
We propose hinge-loss Markov random fields (HL-MRFs), a powerful class of continuous-valued graphical models, for high-level computer vision tasks. HL-MRFs are characterized by log-concave density functions, and are able to perform efficient, exact inference. Their templated hinge-loss potential functions naturally encode soft-valued logical rules. Using the declarative modeling language probabilistic soft logic, one can easily define HL-MRFs via familiar constructs from first-order logic. We apply HL-MRFs to the task of activity detection, using principles of collective classification. Our model is simple, intuitive and interpretable. We evaluate our model on two datasets and show that it achieves significant lift over the low-level detectors.
Cite
Text
London et al. "Collective Activity Detection Using Hinge-Loss Markov Random Fields." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2013. doi:10.1109/CVPRW.2013.157Markdown
[London et al. "Collective Activity Detection Using Hinge-Loss Markov Random Fields." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2013.](https://mlanthology.org/cvprw/2013/london2013cvprw-collective/) doi:10.1109/CVPRW.2013.157BibTeX
@inproceedings{london2013cvprw-collective,
title = {{Collective Activity Detection Using Hinge-Loss Markov Random Fields}},
author = {London, Ben and Khamis, Sameh and Bach, Stephen H. and Huang, Bert and Getoor, Lise and Davis, Larry S.},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2013},
pages = {566-571},
doi = {10.1109/CVPRW.2013.157},
url = {https://mlanthology.org/cvprw/2013/london2013cvprw-collective/}
}