| | |
Summary: Int J Comput Vis
DOI 10.1007/s11263-007-0122-4
Unsupervised Learning of Human Action Categories Using
Spatial-Temporal Words
Juan Carlos Niebles · Hongcheng Wang · Li Fei-Fei
Received: 16 March 2007 / Accepted: 26 December 2007
© Springer Science+Business Media, LLC 2008
Abstract We present a novel unsupervised learning method
for human action categories. A video sequence is repre-
sented as a collection of spatial-temporal words by extract-
ing space-time interest points. The algorithm automatically
learns the probability distributions of the spatial-temporal
words and the intermediate topics corresponding to human
action categories. This is achieved by using latent topic
models such as the probabilistic Latent Semantic Analysis
(pLSA) model and Latent Dirichlet Allocation (LDA). Our
approach can handle noisy feature points arisen from dy-
namic background and moving cameras due to the appli-
cation of the probabilistic models. Given a novel video se-
quence, the algorithm can categorize and localize the human
|
