Please use this identifier to cite or link to this item:
Scopus Web of Science® Altmetric
Full metadata record
DC FieldValueLanguage
dc.contributor.authorWang, Z.-
dc.contributor.authorShi, Q.-
dc.contributor.authorShen, C.-
dc.contributor.authorVan Den Hengel, A.-
dc.identifier.citationProceedings, 2013 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2013, 23-28 June 2013, Portland, Oregon, USA: pp. 1690-1697-
dc.description.abstractMarkov Random Fields (MRFs) have been successfully applied to human activity modelling, largely due to their ability to model complex dependencies and deal with local uncertainty. However, the underlying graph structure is often manually specified, or automatically constructed by heuristics. We show, instead, that learning an MRF graph and performing MAP inference can be achieved simultaneously by solving a bilinear program. Equipped with the bilinear program based MAP inference for an unknown graph, we show how to estimate parameters efficiently and effectively with a latent structural SVM. We apply our techniques to predict sport moves (such as serve, volley in tennis) and human activity in TV episodes (such as kiss, hug and Hi-Five). Experimental results show the proposed method outperforms the state-of-the-art.-
dc.description.statementofresponsibilityZhenhua Wang, Qinfeng Shi, Chunhua Shen and Anton van den Hengel-
dc.relation.ispartofseriesIEEE Conference on Computer Vision and Pattern Recognition-
dc.subjectHuman activity recognition-
dc.subjectbilinear programming, linear programming-
dc.titleBilinear programming for human activity recognition with unknown MRF graphs-
dc.typeConference paper-
dc.contributor.conferenceIEEE Conference on Computer Vision and Pattern Recognition (26th : 2013 : Portland, Oregon)-
dc.publisher.placeUnited States of America-
dc.identifier.orcidShi, Q. [0000-0002-9126-2107]-
dc.identifier.orcidVan Den Hengel, A. [0000-0003-3027-8364]-
Appears in Collections:Aurora harvest
Computer Science publications

Files in This Item:
File Description SizeFormat 
hdl_77411.pdfAccepted version2.78 MBAdobe PDFView/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.