You are not logged in.

Learning discriminative sequence models from partially labelled data for activity recognition

Truyen, Tran The, Bui, Hung H., Phung, Dinh Q. and Venkatesh, Svetha 2008, Learning discriminative sequence models from partially labelled data for activity recognition, in PRICAI 2008 : Trends in Artificial Intelligence : 10th Pacific Rim International Conference on Artificial Intelligence, Hanoi, Vietnam, December 15-19, 2008, proceedings, Springer, Berlin, Germany, pp. 903-912, doi: 10.1007/978-3-540-89197-0_84.

Attached Files
Name Description MIMEType Size Downloads

Title Learning discriminative sequence models from partially labelled data for activity recognition
Author(s) Truyen, Tran TheORCID iD for Truyen, Tran The orcid.org/0000-0001-6531-8907
Bui, Hung H.
Phung, Dinh Q.ORCID iD for Phung, Dinh Q. orcid.org/0000-0002-9977-8247
Venkatesh, SvethaORCID iD for Venkatesh, Svetha orcid.org/0000-0001-8675-6631
Conference name Pacific Rim International Conference on Artificial Intelligence (10th : 2008 : Hanoi, Vietnam)
Conference location Hanoi, Vietnam
Conference dates 15-19 Dec. 2008
Title of proceedings PRICAI 2008 : Trends in Artificial Intelligence : 10th Pacific Rim International Conference on Artificial Intelligence, Hanoi, Vietnam, December 15-19, 2008, proceedings
Editor(s) Ho, Tu-Bao
Zhou, Zhi-Hua
Publication date 2008
Series Lecture notes in artificial intelligence ; 5351
Conference series Pacific Rim International Conference on Artificial Intelligence
Start page 903
End page 912
Total pages 10
Publisher Springer
Place of publication Berlin, Germany
Keyword(s) activity recognition
conditional random fields
discriminative models
indoor video surveillance
maximum entropy Markov models
partially labelled data
Summary Recognising daily activity patterns of people from low-level sensory data is an important problem. Traditional approaches typically rely on generative models such as the hidden Markov models and training on fully labelled data. While activity data can be readily acquired from pervasive sensors, e.g. in smart environments, providing manual labels to support fully supervised learning is often expensive. In this paper, we propose a new approach based on partially-supervised training of discriminative sequence models such as the conditional random field (CRF) and the maximum entropy Markov model (MEMM). We show that the approach can reduce labelling effort, and at the same time, provides us with the flexibility and accuracy of the discriminative framework. Our experimental results in the video surveillance domain illustrate that these models can perform better than their generative counterpart (i.e. the partially hidden Markov model), even when a substantial amount of labels are unavailable.
ISBN 9783540891963
354089196X
ISSN 0302-9743
Language eng
DOI 10.1007/978-3-540-89197-0_84
Field of Research 089999 Information and Computing Sciences not elsewhere classified
Socio Economic Objective 970108 Expanding Knowledge in the Information and Computing Sciences
HERDC Research category E1.1 Full written paper - refereed
Copyright notice ©2008, Springer
Persistent URL http://hdl.handle.net/10536/DRO/DU:30044672

Document type: Conference Paper
Collection: School of Information Technology
Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in TR Web of Science
Scopus Citation Count Cited 4 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 278 Abstract Views, 4 File Downloads  -  Detailed Statistics
Created: Fri, 20 Apr 2012, 13:24:29 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.