Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network

  Advanced Search  

Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words

Summary: Unsupervised Learning of Human Action
Categories Using Spatial-Temporal Words
Juan Carlos Niebles1,2, Hongcheng Wang1, Li Fei-Fei1
1University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA
2Universidad del Norte, Barranquilla, Colombia
Email: {jnieble2,hwang13,feifeili}@uiuc.edu
We present a novel unsupervised learning method for human action cate-
gories. A video sequence is represented as a collection of spatial-temporal
words by extracting space-time interest points. The algorithm automatically
learns the probability distributions of the spatial-temporal words and interme-
diate topics corresponding to human action categories. This is achieved by
using a probabilistic Latent Semantic Analysis (pLSA) model. Given a novel
video sequence, the model can categorize and localize the human action(s)
contained in the video. We test our algorithm on two challenging datasets:
the KTH human action dataset and a recent dataset of figure skating actions.
Our results are on par or slightly better than the best reported results. In ad-
dition, our algorithm can recognize and localize multiple actions in long and
complex video sequences containing multiple motions.
1 Introduction


Source: Ahuja, Narendra - Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign


Collections: Computer Technologies and Information Sciences; Engineering