Novel Kernel-Based Recognizers of Human Actions. (16th May 2010)

• Record Type: Journal Article
• Authors: Danafar Danafar, Somayeh Somayeh; Giusti Giusti, Alessandro Alessandro; Schmidhuber Schmidhuber, Jürgen Jürgen
• Other Names: Kim Kim ChangIck ChangIck Academic Editor.
• Is Part Of: EURASIP journal on advances in signal processing. Volume 2010(2010)
• Publication Date: 2010-05-16
• Subjects: Signal processing -- Periodicals; Traitement du signal; Signal processing; Periodicals; 621.3822
• DOI: 10.1155/2010/202768
• Languages: English
• ISSNs: 1687-6172

Abstract

Abstract : We study unsupervised and supervised recognition of human actions in video sequences. The videos are represented by probability distributions and then meaningfully compared in a probabilistic framework. We introduce two novel approaches outperforming state-of-the-art algorithms when tested on the KTH and Weizmann public datasets: an unsupervised nonparametric kernel-based method exploiting the Maximum Mean Discrepancy test statistic; and a supervised method based on Support Vector Machine with a characteristic kernel specifically tailored to histogram-based information.