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.en
dc.contributor.authorShi, Q.en
dc.contributor.authorShen, C.en
dc.contributor.authorVan Den Hengel, A.en
dc.identifier.citationProceedings, 2013 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2013, 23-28 June 2013, Portland, Oregon, USA: pp. 1690-1697en
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.en
dc.description.statementofresponsibilityZhenhua Wang, Qinfeng Shi, Chunhua Shen and Anton van den Hengelen
dc.relation.ispartofseriesIEEE Conference on Computer Vision and Pattern Recognitionen
dc.subjectHuman activity recognition; MRF; bilinear programming, linear programmingen
dc.titleBilinear programming for human activity recognition with unknown MRF graphsen
dc.typeConference paperen
dc.contributor.conferenceIEEE Conference on Computer Vision and Pattern Recognition (26th : 2013 : Portland, Oregon)en
dc.publisher.placeUnited States of Americaen
pubs.library.collectionComputer Science publicationsen
dc.identifier.orcidShi, Q. [0000-0002-9126-2107]en
dc.identifier.orcidShen, C. [0000-0002-8648-8718]en
dc.identifier.orcidVan Den Hengel, A. [0000-0003-3027-8364]en
Appears in Collections: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.