Please use this identifier to cite or link to this item:
|Title:||Visual workflow recognition using a variational bayesian treatment of multistream fused hidden markov models||Authors:||Chatzis, Sotirios P.
Chatzis, Sotirios P.
|Keywords:||Markov processes;Couplings;Artificial intelligence;video surveillance||Issue Date:||2012||Publisher:||IEEE Xplore||Source:||IEEE transactions on circuits and systems for video technology, Volume 22, Issue 7, 2012, Pages 1076-1086||Abstract:||In this paper, we provide a variational Bayesian (VB) treatment of multistream fused hidden Markov models (MFHMMs), and apply it in the context of active learning-based visual workflow recognition (WR). Contrary to training methods yielding point estimates, such as maximum likelihood or maximum a posteriori training, the VB approach provides an estimate of the posterior distribution over the MFHMM parameters. As a result, our approach provides an elegant solution toward the amelioration of the overfitting issues of point estimate-based methods. Additionally, it provides a measure of confidence in the accuracy of the learned model, thus allowing for the easy and cost-effective utilization of active learning in the context of MFHMMs. Two alternative active learning algorithms are considered in this paper: query by committee, which selects unlabeled data that minimize the classification variance, and a maximum information gain method that aims to maximize the alteration in model variance by proper data labeling. We demonstrate the efficacy of the proposed treatment of MFHMMs by examining two challenging WR scenarios, and show that the application of active learning, which is facilitated by our VB approach, allows for a significant reduction of the MFHMM training costs||URI:||http://ktisis.cut.ac.cy/handle/10488/7240||ISSN:||1051-8215||DOI:||10.1109/TCSVT.2012.2189795||Rights:||© 2012 IEEE||Type:||Article|
|Appears in Collections:||Άρθρα/Articles|
Show full item record
checked on Dec 1, 2018
WEB OF SCIENCETM
checked on Dec 8, 2018
Page view(s) 5050
checked on Dec 9, 2018
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.