Human Interaction Recognition Based on the Co-occurence of Visual Words

Khadidja Nour el houda Slimani, Yannick Benezeth, Feriel Souami; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2014, pp. 455-460

Abstract


This paper describes a novel methodology for automated recognition of high-level activities. A key aspect of our framework relies on the concept of co-occurring visual words for describing interactions between several persons. Motivated by the numerous success of human activity recognition methods using bag-of-words, this paradigm is extended. A 3-D XYT spatio-temporal volume is generated for each interacting person and a set of visual words is extracted to represent his activity. The interaction is then represented by the frequency of co-occurring visual words between persons. For our experiments, we used the UT-interaction dataset which contains several complex human-human interactions.

Related Material


[pdf]
[bibtex]
@InProceedings{Slimani_2014_CVPR_Workshops,
author = {Nour el houda Slimani, Khadidja and Benezeth, Yannick and Souami, Feriel},
title = {Human Interaction Recognition Based on the Co-occurence of Visual Words},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2014}
}