Show simple item record

dc.contributor.authorSener, Fadime
dc.contributor.authorIkizler-Cinbis, Nazli
dc.date.accessioned2019-12-13T06:51:42Z
dc.date.available2019-12-13T06:51:42Z
dc.date.issued2015
dc.identifier.issn1047-3203
dc.identifier.urihttps://doi.org/10.1016/j.jvcir.2015.07.016
dc.identifier.urihttp://hdl.handle.net/11655/18661
dc.description.abstractIn this work, we look into the problem of recognizing two-person interactions in videos. Our method integrates multiple visual features in a weakly supervised manner by utilizing an embedding-based multiple instance learning framework. In our proposed method, first, several visual features that capture the shape and motion of the interacting people are extracted from each detected person region in a video. Then, two-person visual descriptors are formed. Since the relative spatial locations of interacting people are likely to complement the visual descriptors, we propose to use spatial multiple instance embedding, which implicitly incorporates the distances between people into the multiple instance learning process. Experimental results on two benchmark datasets validate that using two-person visual descriptors together with spatial multiple instance learning offers an effective way for inferring the type of the interaction. (C) 2015 Elsevier Inc. All rights reserved.
dc.language.isoen
dc.publisherAcademic Press Inc Elsevier Science
dc.relation.isversionof10.1016/j.jvcir.2015.07.016
dc.rightsinfo:eu-repo/semantics/openAccess
dc.subjectComputer Science
dc.titleTwo-Person Interaction Recognition Via Spatial Multiple Instance Embedding
dc.typeinfo:eu-repo/semantics/article
dc.typeinfo:eu-repo/semantics/publishedVersion
dc.relation.journalJournal Of Visual Communication And Image Representation
dc.contributor.departmentBilgisayar Mühendisliği
dc.identifier.volume32
dc.identifier.startpage63
dc.identifier.endpage73
dc.description.indexWoS


Files in this item

This item appears in the following Collection(s)

Show simple item record