TY - CONF
T1 - Epitomic Representation of Human Activities
T2 - Computer Vision and Pattern Recognition, 2007. CVPR '07. IEEE Conference on
Y1 - 2007
A1 - Cuntoor, N.P.
A1 - Chellapa, Rama
KW - action
KW - activities
KW - airport
KW - dataset;epitomic
KW - dataset;UCF
KW - decomposition;modelling;statistics;video
KW - decomposition;TSA
KW - dynamical
KW - human
KW - indoor
KW - Iwasawa
KW - matrix
KW - matrix;human
KW - modeling;input
KW - processing;
KW - representation;estimated
KW - sequences;image
KW - sequences;matrix
KW - signal
KW - statistics;linear
KW - Surveillance
KW - system
KW - systems;video
AB - We introduce an epitomic representation for modeling human activities in video sequences. A video sequence is divided into segments within which the dynamics of objects is assumed to be linear and modeled using linear dynamical systems. The tuple consisting of the estimated system matrix, statistics of the input signal and the initial state value is said to form an epitome. The system matrices are decomposed using the Iwasawa matrix decomposition to isolate the effect of rotation, scaling and projective action on the state vector. "We demonstrate the usefulness of the proposed representation and decomposition for activity recognition using the TSA airport surveillance dataset and the UCF indoor human action dataset.
JA - Computer Vision and Pattern Recognition, 2007. CVPR '07. IEEE Conference on
M3 - 10.1109/CVPR.2007.383135
ER -