Bilinear Programming for Human Activity Recognition with Unknown MRF Graphs

Zhenhua Wang, Qinfeng Shi, Chunhua Shen, Anton van den Hengel

CVPR 2013

doi:10.1109/CVPR.2013.221 /cvpr/2013/wang2013cvpr-bilinear/

Abstract

Markov Random Fields (MRFs) have been successfully applied to human activity modelling, largely due to their ability to model complex dependencies and deal with local uncertainty. However, the underlying graph structure is often manually specified, or automatically constructed by heuristics. We show, instead, that learning an MRF graph and performing MAP inference can be achieved simultaneously by solving a bilinear program. Equipped with the bilinear program based MAP inference for an unknown graph, we show how to estimate parameters efficiently and effectively with a latent structural SVM. We apply our techniques to predict sport moves (such as serve, volley in tennis) and human activity in TV episodes (such as kiss, hug and Hi-Five). Experimental results show the proposed method outperforms the state-of-the-art.

PDF CVPR Semantic Scholar

Cite

Text

Wang et al. "Bilinear Programming for Human Activity Recognition with Unknown MRF Graphs." Conference on Computer Vision and Pattern Recognition, 2013. doi:10.1109/CVPR.2013.221

Markdown

[Wang et al. "Bilinear Programming for Human Activity Recognition with Unknown MRF Graphs." Conference on Computer Vision and Pattern Recognition, 2013.](https://mlanthology.org/cvpr/2013/wang2013cvpr-bilinear/) doi:10.1109/CVPR.2013.221

BibTeX

@inproceedings{wang2013cvpr-bilinear,
  title     = {{Bilinear Programming for Human Activity Recognition with Unknown MRF Graphs}},
  author    = {Wang, Zhenhua and Shi, Qinfeng and Shen, Chunhua and van den Hengel, Anton},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2013},
  doi       = {10.1109/CVPR.2013.221},
  url       = {https://mlanthology.org/cvpr/2013/wang2013cvpr-bilinear/}
}