HMM-MIO

an enhanced hidden Markov model for action recognition

Oscar Perez Concha*, Richard Yi Da Xu, Zia Moghaddam, Massimo Piccardi

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contribution

10 Citations (Scopus)

Abstract

Generative models can be flexibly employed in a variety of tasks such as classification, detection and segmentation thanks to their explicit modelling of likelihood functions. However, likelihood functions are hard to model accurately in many real cases. In this paper, we present an enhanced hidden Markov model capable of dealing with the noisy, high-dimensional and sparse measurements typical of action feature sets. The modified model, named hidden Markov model with multiple, independent observations (HMM-MIO), joins: a) robustness to observation outliers, b) dimensionality reduction, and c) processing of sparse observations. In the paper, a set of experimental results over the Weizmann and KTH datasets shows that this model can be tuned to achieve classification accuracy comparable to that of discriminative classifiers. While discriminative approaches remain the natural choice for classification tasks, our results prove that likelihoods, too, can be modelled to a high level of accuracy. In the near future, we plan extension of HMM-MIO along the lines of infinite Markov models and its integration into a switching model for continuous human action recognition.

Original languageEnglish
Title of host publication2011 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2011
Place of PublicationPiscataway
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages62-69
Number of pages8
ISBN (Electronic)9781457705304, 9781457705281
ISBN (Print)9781457705298
DOIs
Publication statusPublished - Aug 2011
Externally publishedYes
Event2011 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2011 - Colorado Springs, CO, United States
Duration: 20 Jun 201125 Jun 2011

Other

Other2011 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2011
CountryUnited States
CityColorado Springs, CO
Period20/06/1125/06/11

Fingerprint Dive into the research topics of 'HMM-MIO: an enhanced hidden Markov model for action recognition'. Together they form a unique fingerprint.

  • Cite this

    Concha, O. P., Da Xu, R. Y., Moghaddam, Z., & Piccardi, M. (2011). HMM-MIO: an enhanced hidden Markov model for action recognition. In 2011 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2011 (pp. 62-69). Piscataway: Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/CVPRW.2011.5981803