Title
Exploring The Space Of A Human Action
Abstract
One of the fundamental challenges of recognizing actions is accounting for the variability that arises when arbitrary cameras capture humans performing actions. In this paper, we explicitly identify three important sources of variability: (1) viewpoint, (2) execution rate, and (3) anthropometry of actors, and propose a model of human actions that allows us to investigate all three. Our hypothesis is that the variability associated with the execution of an action can be closely approximated by a linear combination of action bases in joint spatio-temporal space. We demonstrate that such a model bounds the rank of a matrix of image measurements and that this bound can be used to achieve recognition of actions based only on imaged data. A test employing principal angles between subspaces that is robust to statistical fluctuations in measurement data is presented to find the membership of an instance of an action. The algorithm is applied to recognize several actions, and promising results have been obtained. © 2005 IEEE.
Publication Date
12-1-2005
Publication Title
Proceedings of the IEEE International Conference on Computer Vision
Volume
I
Number of Pages
144-149
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/ICCV.2005.90
Copyright Status
Unknown
Socpus ID
33745968247 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/33745968247
STARS Citation
Sheikh, Yaser; Sheikh, Mumtaz; and Shah, Mubarak, "Exploring The Space Of A Human Action" (2005). Scopus Export 2000s. 3289.
https://stars.library.ucf.edu/scopus2000/3289