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.
History
Event
Advances in Neural Information Processing. Conference (22nd : 2008 : Vancouver, B. C.)
Pagination
1657 - 1664
Publisher
Curran Associates
Location
Vancouver, B. C.
Place of publication
Red Hook, N. Y.
Start date
2008-12-08
End date
2008-12-11
ISBN-13
9781605609492
ISBN-10
1605609498
Language
eng
Publication classification
E1.1 Full written paper - refereed
Copyright notice
2009, Curran Associates
Editor/Contributor(s)
D Koller, Y Bengio, D Schuurmans, L Bottou, A Culotta
Title of proceedings
NIPS 2008 : Advances in Neural Information Processing Systems 21 : Proceedings of the 2008 Conference