Show simple item record

dc.contributor.authorSfikas, Konstantinosen_US
dc.contributor.authorTheoharis, Theoharisen_US
dc.contributor.authorPratikakis, Ioannisen_US
dc.contributor.editorIoannis Pratikakis and Florent Dupont and Maks Ovsjanikoven_US
dc.date.accessioned2017-04-22T17:17:39Z
dc.date.available2017-04-22T17:17:39Z
dc.date.issued2017
dc.identifier.isbn978-3-03868-030-7
dc.identifier.issn1997-0471
dc.identifier.urihttp://dx.doi.org/10.2312/3dor.20171045
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/3dor20171045
dc.description.abstractA novel 3D model classification and retrieval method, based on the PANORAMA representation and Convolutional Neural Networks, is presented. Initially, the 3D models are pose normalized using the SYMPAN method and consecutively the PANORAMA representation is extracted and used to train a convolutional neural network. The training is based on an augmented view of the extracted panoramic representation views. The proposed method is tested in terms of classification and retrieval accuracy on standard large scale datasets.en_US
dc.publisherThe Eurographics Associationen_US
dc.subjectI.3.6 [Computer Graphics]
dc.subjectMethodology and Techniques
dc.subjectI.3.7 [Computer Graphics]
dc.subjectThree Dimensional Graphics and Realism
dc.subjectVisible line/surface algorithms
dc.subjectI.3.3 [Computer Graphics]
dc.subjectPicture/Image Generation
dc.subjectViewing Algorithms
dc.subjectI.5.1 [Pattern Recognition]
dc.subjectModels
dc.subjectNeural Nets
dc.titleExploiting the PANORAMA Representation for Convolutional Neural Network Classification and Retrievalen_US
dc.description.seriesinformationEurographics Workshop on 3D Object Retrieval
dc.description.sectionheadersPaper Session I
dc.identifier.doi10.2312/3dor.20171045
dc.identifier.pages1-7


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record