Exploiting Human Actions and Object Context for Recognition Tasks

Abstract

Our goal is to exploit human motion and object context to perform action recognition and object classification. Towards this end, we introduce a framework for recognizing actions and objects by measuring image-, object- and action-based information from video. Hidden Markov models are combined with object context to classify hand actions, which are aggregated by a Bayesian classifier to summarize activities. We also use Bayesian methods to differentiate the class of unknown objects by evaluating detected actions along with lowlevel, extracted object features. Our approach is appropriate for locating and classifying objects under a variety of conditions including full occlusion. We show experiments where both familiar and previously unseen objects are recognized using action and context information. 1.

Cite

Text

Moore et al. "Exploiting Human Actions and Object Context for Recognition Tasks." IEEE/CVF International Conference on Computer Vision, 1999. doi:10.1109/ICCV.1999.791201

Markdown

[Moore et al. "Exploiting Human Actions and Object Context for Recognition Tasks." IEEE/CVF International Conference on Computer Vision, 1999.](https://mlanthology.org/iccv/1999/moore1999iccv-exploiting/) doi:10.1109/ICCV.1999.791201

BibTeX

@inproceedings{moore1999iccv-exploiting,
  title     = {{Exploiting Human Actions and Object Context for Recognition Tasks}},
  author    = {Moore, Darnell J. and Essa, Irfan A. and Hayes, Monson H.},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {1999},
  pages     = {80-86},
  doi       = {10.1109/ICCV.1999.791201},
  url       = {https://mlanthology.org/iccv/1999/moore1999iccv-exploiting/}
}