Social Roles in Hierarchical Models for Human Activity Recognition

Abstract

We present a hierarchical model for human activity recognition in entire multi-person scenes. Our model describes human behaviour at multiple levels of detail, ranging from low-level actions through to high-level events. We also include a model of social roles, the expected behaviours of certain people, or groups of people, in a scene. The hierarchical model includes these varied representations, and various forms of interactions between people present in a scene. The model is trained in a discriminative max-margin framework. Experimental results demonstrate that this model can improve performance at all considered levels of detail, on two challenging datasets.

Cite

Text

Lan et al. "Social Roles in Hierarchical Models for Human Activity Recognition." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2012. doi:10.1109/CVPR.2012.6247821

Markdown

[Lan et al. "Social Roles in Hierarchical Models for Human Activity Recognition." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2012.](https://mlanthology.org/cvpr/2012/lan2012cvpr-social/) doi:10.1109/CVPR.2012.6247821

BibTeX

@inproceedings{lan2012cvpr-social,
  title     = {{Social Roles in Hierarchical Models for Human Activity Recognition}},
  author    = {Lan, Tian and Sigal, Leonid and Mori, Greg},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2012},
  pages     = {1354-1361},
  doi       = {10.1109/CVPR.2012.6247821},
  url       = {https://mlanthology.org/cvpr/2012/lan2012cvpr-social/}
}