Human action segmentation via controlled use of missing data in HMMs Peursum, Patrick, Bui, Hung H., Venkatesh, Svetha and West, Geoff 2004, Human action segmentation via controlled use of missing data in HMMs, in ICPR 2004 : Proceedings of the 17th International Conference on Pattern Recognition, IEEE, Washington, D. C., pp. 440-445. Attached Files Name Description MIMEType Size Downloads venkatesh-humanaction-2004.pdf Published version application/pdf 436.31KB 92 Title Human action segmentation via controlled use of missing data in HMMs Author(s) Peursum, Patrick Bui, Hung H. Venkatesh, Svetha orcid.org/0000-0001-8675-6631 West, Geoff Conference name International Conference on Pattern Recognition (17th : 2004 : Cambridge, U. K.) Conference location Cambridge, U. K. Conference dates 23-26 Aug. 2004 Title of proceedings ICPR 2004 : Proceedings of the 17th International Conference on Pattern Recognition Editor(s) Kittler, J. Petrou, M. Nixon, M. Publication date 2004 Conference series International Conference on Pattern Recognition Start page 440 End page 445 Total pages 6 Publisher IEEE Place of publication Washington, D. C. Keyword(s) action labeling hidden Markov models (HMM) human action segmentation sliding windows Summary Segmentation of individual actions from a stream of human motion is an open problem in computer vision. This paper approaches the problem of segmenting higher-level activities into their component sub-actions using Hidden Markov Models modified to handle missing data in the observation vector. By controlling the use of missing data, action labels can be inferred from the observation vector during inferencing, thus performing segmentation and classification simultaneously. The approach is able to segment both prominent and subtle actions, even when subtle actions are grouped together. The advantage of this method over sliding windows and Viterbi state sequence interrogation is that segmentation is performed as a trainable task, and the temporal relationship between actions is encoded in the model and used as evidence for action labelling. Notes This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder. ISBN 0769521282 ISSN 1051-4651 Language eng 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 ©2004, IEEE Free to Read? Yes Persistent URL http://hdl.handle.net/10536/DRO/DU:30044634 Document type: Conference Paper Collections: School of Information Technology Open Access Collection Related Links Link Description Connect to published version (restricted access) Go to link with your DU access privileges     Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved. 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. Versions Version Filter Type Fri, 20 Apr 2012, 11:36:37 EST Fri, 27 Apr 2012, 16:39:04 EST Fri, 27 Apr 2012, 16:40:29 EST Thu, 03 May 2012, 13:30:22 EST Tue, 06 Sep 2016, 18:47:11 EST Sat, 21 Oct 2017, 02:01:09 EST Tue, 05 Dec 2017, 12:31:39 EST Filtered Full Citation counts:   Cited 9 times in TR Web of Science Cited 13 times in Scopus Search Google Scholar Access Statistics: 323 Abstract Views, 91 File Downloads  -  Detailed Statistics Created: Fri, 20 Apr 2012, 11:36:37 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.