A framework for combined recognition of actions and objects

dc.contributor.authorAr, İlktan
dc.contributor.authorAkgül, Yusuf Sinan
dc.date.accessioned2019-06-27T08:04:16Z
dc.date.available2019-06-27T08:04:16Z
dc.date.issued2012
dc.departmentFakülteler, Mühendislik ve Doğa Bilimleri Fakültesi, Bilgisayar Mühendisliği Bölümüen_US
dc.description.abstractThis paper proposes a novel approach to recognize actions and objects within the context of each other. Assuming that the different actions involve different objects in image sequences and there is one-to-one relation between object and action type we present a Bayesian network based framework which combines motion patterns and object usage information to recognize actions/objects. More specifically our approach recognizes high-level actions and the related objects without any body-part segmentation hand tracking and temporal segmentation methods. Additionally we present a novel motion representation based on 3D Haar-like features which can be formed by depth color or both images. Our approach is also appropriate for object and action recognition where the involved object is partially or fully occluded. Finally experiments show that our approach improves the accuracy of both action and object recognition significantly.en_US]
dc.identifier.citation1
dc.identifier.doi10.1007/978-3-642-33564-8_32en_US
dc.identifier.endpage271
dc.identifier.isbn9783642335648
dc.identifier.isbn9783642335631
dc.identifier.issn0302-9743en_US
dc.identifier.issn0302-9743
dc.identifier.scopus2-s2.0-84868021586en_US
dc.identifier.scopusqualityQ2
dc.identifier.startpage264en_US
dc.identifier.urihttps://hdl.handle.net/20.500.12469/918
dc.identifier.urihttps://doi.org/10.1007/978-3-642-33564-8_32
dc.identifier.volume7594en_US
dc.identifier.wosWOS:000313005700032en_US
dc.identifier.wosqualityN/A
dc.institutionauthorAr, İlktanen_US
dc.language.isoenen_US
dc.publisherSpringer-Verlag Berlinen_US
dc.relation.journalInternational Conference on Computer Vision and Graphicsen_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectAction and object recognitionen_US
dc.subjectBayesian networken_US
dc.subjectMotion patternen_US
dc.titleA framework for combined recognition of actions and objectsen_US
dc.typeConference Objecten_US
dspace.entity.typePublication

Files