Show simple item record

dc.contributor.authorCarvajal, Johanna
dc.contributor.authorSanderson, Conrad
dc.contributor.authorMcCool, Chris
dc.contributor.authorLovell, Brian C
dc.date.accessioned2020-07-30T00:37:26Z
dc.date.available2020-07-30T00:37:26Z
dc.date.issued2014
dc.identifier.isbn9781450331593
dc.identifier.doi10.1145/2689746.2689748
dc.identifier.urihttp://hdl.handle.net/10072/395890
dc.description.abstractIn this paper we propose a novel approach to multi-action recognition that performs joint segmentation and classification. This approach models each action using a Gaussian mixture using robust low-dimensional action features. Segmentation is achieved by performing classification on overlapping temporal windows, which are then merged to produce the final result. This approach is considerably less complicated than previous methods which use dynamic programming or computationally expensive hidden Markov models (HMMs). Initial experiments on a stitched version of the KTH dataset show that the proposed approach achieves an accuracy of 78.3%, outperforming a recent HMM-based approach which obtained 71.2%.
dc.description.peerreviewedYes
dc.publisherACM Press
dc.relation.ispartofconferencename2nd Workshop on Machine Learning for Sensory Data Analysis (MLSDA 2014)
dc.relation.ispartofconferencetitleProceedings of the MLSDA 2014: The 2nd Workshop on Machine Learning for Sensory Data Analysis
dc.relation.ispartofdatefrom2014-12-02
dc.relation.ispartofdateto2014-12-02
dc.relation.ispartoflocationGold Coast, QLD, Australia
dc.relation.ispartofpagefrom19
dc.relation.ispartofpageto24
dc.subject.fieldofresearchComputer vision
dc.subject.fieldofresearchMachine learning not elsewhere classified
dc.subject.fieldofresearchcode460304
dc.subject.fieldofresearchcode461199
dc.titleMulti-Action Recognition via Stochastic Modelling of Optical Flow and Gradients
dc.typeConference output
dc.type.descriptionE1 - Conferences
dcterms.bibliographicCitationCarvajal, J; Sanderson, C; McCool, C; Lovell, BC, Multi-Action Recognition via Stochastic Modelling of Optical Flow and Gradients, Proceedings of the MLSDA 2014 2nd Workshop on Machine Learning for Sensory Data Analysis - MLSDA'14, 2014
dc.date.updated2020-07-29T07:11:39Z
dc.description.versionAccepted Manuscript (AM)
gro.rights.copyright© ACM, 2014. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in MLSDA'14: Proceedings of the MLSDA 2014 2nd Workshop on Machine Learning for Sensory Data Analysis, ISBN: 978-1-4503-3159-3, https://doi.org/10.1145/2689746.2689748
gro.hasfulltextFull Text
gro.griffith.authorSanderson, Conrad


Files in this item

This item appears in the following Collection(s)

  • Conference outputs
    Contains papers delivered by Griffith authors at national and international conferences.

Show simple item record