dc.contributor.author | Carvajal, Johanna | |
dc.contributor.author | Sanderson, Conrad | |
dc.contributor.author | McCool, Chris | |
dc.contributor.author | Lovell, Brian C | |
dc.date.accessioned | 2020-07-30T00:37:26Z | |
dc.date.available | 2020-07-30T00:37:26Z | |
dc.date.issued | 2014 | |
dc.identifier.isbn | 9781450331593 | |
dc.identifier.doi | 10.1145/2689746.2689748 | |
dc.identifier.uri | http://hdl.handle.net/10072/395890 | |
dc.description.abstract | In 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.peerreviewed | Yes | |
dc.publisher | ACM Press | |
dc.relation.ispartofconferencename | 2nd Workshop on Machine Learning for Sensory Data Analysis (MLSDA 2014) | |
dc.relation.ispartofconferencetitle | Proceedings of the MLSDA 2014: The 2nd Workshop on Machine Learning for Sensory Data Analysis | |
dc.relation.ispartofdatefrom | 2014-12-02 | |
dc.relation.ispartofdateto | 2014-12-02 | |
dc.relation.ispartoflocation | Gold Coast, QLD, Australia | |
dc.relation.ispartofpagefrom | 19 | |
dc.relation.ispartofpageto | 24 | |
dc.subject.fieldofresearch | Computer vision | |
dc.subject.fieldofresearch | Machine learning not elsewhere classified | |
dc.subject.fieldofresearchcode | 460304 | |
dc.subject.fieldofresearchcode | 461199 | |
dc.title | Multi-Action Recognition via Stochastic Modelling of Optical Flow and Gradients | |
dc.type | Conference output | |
dc.type.description | E1 - Conferences | |
dcterms.bibliographicCitation | Carvajal, 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.updated | 2020-07-29T07:11:39Z | |
dc.description.version | Accepted 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.hasfulltext | Full Text | |
gro.griffith.author | Sanderson, Conrad | |