Unsupervised Activity Discovery and Characterization From Event-Streams
Abstract
We present a framework to discover and characterize different classes of everyday activities from event-streams. We begin by representing activities as bags of event n-grams. This allows us to analyze the global structural information of activities, using their local event statistics. We demonstrate how maximal cliques in an undirected edge-weighted graph of activities, can be used for activity-class discovery in an unsupervised manner. We show how modeling an activity as a variable length Markov process, can be used to discover recurrent event-motifs to characterize the discovered activity-classes. We present results over extensive data-sets, collected from multiple active environments, to show the competence and generalizability of our proposed framework.
Keywords
Cite
@article{arxiv.1207.1381,
title = {Unsupervised Activity Discovery and Characterization From Event-Streams},
author = {Rafay Hammid and Siddhartha Maddi and Amos Johnson and Aaron Bobick and Irfan Essa and Charles Lee Isbell},
journal= {arXiv preprint arXiv:1207.1381},
year = {2012}
}
Comments
Appears in Proceedings of the Twenty-First Conference on Uncertainty in Artificial Intelligence (UAI2005)