Recognizing Human Action Efforts: An Adaptive Three-Mode PCA Framework

Abstract

We present a computational framework capable of labeling the effort of an action corresponding to the perceived level of exertion by the performer (low – high). The approach initially factorizes examples (at different efforts) of an action into its three-mode principal components to reduce the dimensionality. Then a learning phase is introduced to compute expressive-feature weights to adjust the model’s estimation of effort to conform to given perceptual labels for the examples. Experiments are demonstrated recognizing the efforts of a person carrying bags of different weight and for multiple people walking at different paces. 1.

Cite

Text

Davis and Gao. "Recognizing Human Action Efforts: An Adaptive Three-Mode PCA Framework." IEEE/CVF International Conference on Computer Vision, 2003. doi:10.1109/ICCV.2003.1238662

Markdown

[Davis and Gao. "Recognizing Human Action Efforts: An Adaptive Three-Mode PCA Framework." IEEE/CVF International Conference on Computer Vision, 2003.](https://mlanthology.org/iccv/2003/davis2003iccv-recognizing/) doi:10.1109/ICCV.2003.1238662

BibTeX

@inproceedings{davis2003iccv-recognizing,
  title     = {{Recognizing Human Action Efforts: An Adaptive Three-Mode PCA Framework}},
  author    = {Davis, James W. and Gao, Hui},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year      = {2003},
  pages     = {1463-1469},
  doi       = {10.1109/ICCV.2003.1238662},
  url       = {https://mlanthology.org/iccv/2003/davis2003iccv-recognizing/}
}