Show simple item record

dc.contributor.authorCarvajal, Johanna
dc.contributor.authorMcCool, Chris
dc.contributor.authorLovell, Brian
dc.contributor.authorSanderson, Conrad
dc.date.accessioned2020-07-30T02:33:46Z
dc.date.available2020-07-30T02:33:46Z
dc.date.issued2016
dc.identifier.isbn978-3-319-42996-0
dc.identifier.issn0302-9743
dc.identifier.doi10.1007/978-3-319-42996-0_10
dc.identifier.urihttp://hdl.handle.net/10072/395913
dc.description.abstractWe propose a hierarchical approach to multi-action recognition that performs joint classification and segmentation. A given video (containing several consecutive actions) is processed via a sequence of overlapping temporal windows. Each frame in a temporal window is represented through selective low-level spatio-temporal features which efficiently capture relevant local dynamics. Features from each window are represented as a Fisher vector, which captures first and second order statistics. Instead of directly classifying each Fisher vector, it is converted into a vector of class probabilities. The final classification decision for each frame is then obtained by integrating the class probabilities at the frame level, which exploits the overlapping of the temporal windows. Experiments were performed on two datasets: s-KTH (a stitched version of the KTH dataset to simulate multi-actions), and the challenging CMU-MMAC dataset. On s-KTH, the proposed approach achieves an accuracy of 85.0 %, significantly outperforming two recent approaches based on GMMs and HMMs which obtained 78.3 % and 71.2 %, respectively. On CMU-MMAC, the proposed approach achieves an accuracy of 40.9 %, outperforming the GMM and HMM approaches which obtained 33.7 % and 38.4 %, respectively. Furthermore, the proposed system is on average 40 times faster than the GMM based approach.
dc.description.peerreviewedYes
dc.publisherSpringer
dc.relation.ispartofconferencenamePacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2016)
dc.relation.ispartofconferencetitleLecture Notes in Computer Science
dc.relation.ispartofdatefrom2016-04-19
dc.relation.ispartofdateto2016-04-22
dc.relation.ispartoflocationAuckland, New Zealand
dc.relation.ispartofpagefrom115
dc.relation.ispartofpageto127
dc.relation.ispartofvolume9794
dc.subject.fieldofresearchArtificial intelligence
dc.subject.fieldofresearchcode4602
dc.titleJoint Recognition and Segmentation of Actions via Probabilistic Integration of Spatio-Temporal Fisher Vectors
dc.typeConference output
dc.type.descriptionE1 - Conferences
dcterms.bibliographicCitationCarvajal, J; McCool, C; Lovell, B; Sanderson, C, Joint Recognition and Segmentation of Actions via Probabilistic Integration of Spatio-Temporal Fisher Vectors, Lecture Notes in Computer Science , 2016, vol. 9794
dc.date.updated2020-07-29T04:50:37Z
dc.description.versionAccepted Manuscript (AM)
gro.rights.copyright© Springer International Publishing Switzerland 2016. This is the author-manuscript version of this paper. Reproduced in accordance with the copyright policy of the publisher. The original publication is available at www.springerlink.com
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