Sridhar, M, Cohn, AG and Hogg, DC (2010) Unsupervised Learning of Event Classes from Video. In: Proceedings of the Twenty-Fourth AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence, 11-15 July 2010, Atlanta, Georgia, USA. AAAI Press , North America , 1631-1638 . ISBN 978-1577354635
We present a method for unsupervised learning of event classes from videos in which multiple actions might occur simultaneously. It is assumed that all such activities are produced from an underlying set of event class generators. The learning task is then to recover this generative process from visual data. A set of event classes is derived from the most likely decomposition of the tracks into a set of labelled events involving subsets of interacting tracks. Interactions between subsets of tracks are modelled as a relational graph structure that captures qualitative spatio-temporal relationships between these tracks. The posterior probability of candidate solutions favours decompositions in which events of the same class have a similar relational structure, together with other measures of well-formedness. A Markov Chain Monte Carlo (MCMC) procedure is used to efficiently search for the MAP solution. This search moves between possible decompositions of the tracks into sets of unlabelled events and at each move adds a close to optimal labelling (for this decomposition) using spectral clustering. Experiments on real data show that the discovered event classes are often semantically meaningful and correspond well with groundtruth event classes assigned by hand.
|Institution:||The University of Leeds|
|Academic Units:||The University of Leeds > Faculty of Engineering (Leeds) > School of Computing (Leeds) > Artificial Intelligence & Biological Systems (Leeds)
The University of Leeds > Faculty of Engineering (Leeds) > School of Computing (Leeds) > Institute for Computational and Systems Science (Leeds)
|Depositing User:||Symplectic Publications|
|Date Deposited:||29 Oct 2012 15:29|
|Last Modified:||08 Feb 2013 17:40|