Discovery - University of Dundee - Online Publications

Library & Learning Centre

Action categorization with modified hidden conditional random field

Action categorization with modified hidden conditional random field

Research output: Contribution to journalArticle

View graph of relations

Authors

Research units

Info

Original languageEnglish
Pages (from-to)197-203
Number of pages7
JournalPattern Recognition
Volume43
Issue number1
DOIs
StatePublished - 2010

Abstract

In this paper, we present a method for action categorization with a modified hidden conditional random field (HCRF). Specifically, effective silhouette-based action features are extracted using motion moments and spectrum of chain code. We formulate a modified HCRF (mHCRF) to have a guaranteed global optimum in the modelling of the temporal action dependencies after the HMM pathing stage. Experimental results on action categorization using this model are compared favorably against several existing model-based methods including GMM, SVM, Logistic Regression, HMM, CRF and HCRF.

Documents

DOI

Library & Learning Centre

Contact | Accessibility | Policy