TY - GEN
T1 - Unsupervised analysis of activity sequences using event-motifs
AU - Hamid, Raffay
AU - Maddi, Siddhartha
AU - Bobick, Aaron
AU - Essa, Irfan
PY - 2006
Y1 - 2006
N2 - We present an unsupervised framework to discover characterizations of everyday human activities, and demonstrate how such representations can be used to extract points of interest in event-streams. We begin with the usage of Suffix Trees as an efficient activity-representation to analyze the global structural information of activities, using their local event statistics over the entire continuum of their temporal resolution. Exploiting this representation, we discover characterizing event-subsequences and present their usage in an ensemble-based framework for activity classification. Finally, we propose a method to automatically detect subsequences of events that are locally atypical in a structural sense. Results over extensive data-sets, collected from multiple sensor-rich environments are presented, to show the competence and scalability of the proposed framework.
AB - We present an unsupervised framework to discover characterizations of everyday human activities, and demonstrate how such representations can be used to extract points of interest in event-streams. We begin with the usage of Suffix Trees as an efficient activity-representation to analyze the global structural information of activities, using their local event statistics over the entire continuum of their temporal resolution. Exploiting this representation, we discover characterizing event-subsequences and present their usage in an ensemble-based framework for activity classification. Finally, we propose a method to automatically detect subsequences of events that are locally atypical in a structural sense. Results over extensive data-sets, collected from multiple sensor-rich environments are presented, to show the competence and scalability of the proposed framework.
UR - https://www.scopus.com/pages/publications/34547465696
U2 - 10.1145/1178782.1178794
DO - 10.1145/1178782.1178794
M3 - Conference contribution
AN - SCOPUS:34547465696
SN - 1595934960
SN - 9781595934963
T3 - Proceedings of the ACM International Multimedia Conference and Exhibition
SP - 71
EP - 78
BT - Proceedings of the 4th ACM International Workshop on Video Surveillance and Sensor Networks, VSSN'06
T2 - 4th ACM International Workshop on Video Surveillance and Sensor Networks, VSSN'06, co-located with the 2006 ACM International Multimedia Conference
Y2 - 27 October 2007 through 27 October 2007
ER -