Hierarchical semi-markov conditional random fields for recursive sequential data Truyen, Tran The, Phung, Dinh Q., Bui, Hung H. and Venkatesh, Svetha 2008, Hierarchical semi-markov conditional random fields for recursive sequential data, in NIPS 2008 : Advances in Neural Information Processing Systems 21 : Proceedings of the 2008 Conference, Curran Associates, Red Hook, N. Y., pp. 1657-1664. Attached Files Name Description MIMEType Size Downloads phung-hierarchicalsemi-2008.pdf Published version application/pdf 126.52KB 53 Title Hierarchical semi-markov conditional random fields for recursive sequential data Author(s) Truyen, Tran The orcid.org/0000-0001-6531-8907 Phung, Dinh Q. orcid.org/0000-0002-9977-8247 Bui, Hung H. Venkatesh, Svetha orcid.org/0000-0001-8675-6631 Conference name Advances in Neural Information Processing. Conference (22nd : 2008 : Vancouver, B. C.) Conference location Vancouver, B. C. Conference dates 8-11 Dec. 2008 Title of proceedings NIPS 2008 : Advances in Neural Information Processing Systems 21 : Proceedings of the 2008 Conference Editor(s) Koller, Daphne Bengio, Yoshua Schuurmans, Dale Bottou, Leon Culotta, Aron Publication date 2008 Conference series Advances in Neural Information Processing. Conference Start page 1657 End page 1664 Total pages 8 Publisher Curran Associates Place of publication Red Hook, N. Y. Keyword(s) efficient algorithm generalisation hierarchical model human activities indoor surveillance model complexes observed data polynomial-time algorithms reasonable accuracy semi-Markov sequential data Summary Inspired by the hierarchical hidden Markov models (HHMM), we present the hierarchical semi-Markov conditional random field (HSCRF), a generalisation of embedded undirected Markov chains to model complex hierarchical, nested Markov processes. It is parameterised in a discriminative framework and has polynomial time algorithms for learning and inference. Importantly, we develop efficient algorithms for learning and constrained inference in a partially-supervised setting, which is important issue in practice where labels can only be obtained sparsely. We demonstrate the HSCRF in two applications: (i) recognising human activities of daily living (ADLs) from indoor surveillance cameras, and (ii) noun-phrase chunking. We show that the HSCRF is capable of learning rich hierarchical models with reasonable accuracy in both fully and partially observed data cases. ISBN 9781605609492 1605609498 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 ©2009, Curran Associates Persistent URL http://hdl.handle.net/10536/DRO/DU:30044754 Document type: Conference Paper Collections: School of Information Technology Open Access Collection   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 Tue, 01 May 2012, 10:56:01 EST Tue, 01 May 2012, 12:59:08 EST Tue, 01 May 2012, 13:02:39 EST Mon, 07 May 2012, 09:37:32 EST Tue, 28 Jan 2014, 14:34:48 EST Tue, 23 Feb 2016, 14:06:03 EST Tue, 06 Sep 2016, 18:49:34 EST Filtered Full Citation counts:   Cited 0 times in TR Web of Science Cited 21 times in Scopus Search Google Scholar Access Statistics: 305 Abstract Views, 54 File Downloads  -  Detailed Statistics Created: Tue, 01 May 2012, 10:56:01 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.