Show simple item record

dc.contributor.authorZhang, Jianmingen_US
dc.contributor.authorMa, Shugaoen_US
dc.contributor.authorSameki, Mehrnooshen_US
dc.contributor.authorSclaroff, Stanen_US
dc.contributor.authorBetke, Margriten_US
dc.contributor.authorLin, Zheen_US
dc.contributor.authorShen, Xiaohuien_US
dc.contributor.authorPrice, Brianen_US
dc.contributor.authorMech, Radomiren_US
dc.date.accessioned2018-02-05T18:37:57Z
dc.date.available2018-02-05T18:37:57Z
dc.date.issued2017-09-01
dc.identifierhttp://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000406751100004&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=6e74115fe3da270499c3d65c9b17d654
dc.identifier.citationJianming Zhang, Shugao Ma, Mehrnoosh Sameki, Stan Sclaroff, Margrit Betke, Zhe Lin, Xiaohui Shen, Brian Price, Radomir Mech. 2017. "Salient Object Subitizing." INTERNATIONAL JOURNAL OF COMPUTER VISION, Volume 124, Issue 2, pp. 169 - 186 (18).
dc.identifier.issn0920-5691
dc.identifier.issn1573-1405
dc.identifier.urihttps://hdl.handle.net/2144/26689
dc.description.abstractWe study the problem of salient object subitizing, i.e. predicting the existence and the number of salient objects in an image using holistic cues. This task is inspired by the ability of people to quickly and accurately identify the number of items within the subitizing range (1–4). To this end, we present a salient object subitizing image dataset of about 14 K everyday images which are annotated using an online crowdsourcing marketplace. We show that using an end-to-end trained convolutional neural network (CNN) model, we achieve prediction accuracy comparable to human performance in identifying images with zero or one salient object. For images with multiple salient objects, our model also provides significantly better than chance performance without requiring any localization process. Moreover, we propose a method to improve the training of the CNN subitizing model by leveraging synthetic images. In experiments, we demonstrate the accuracy and generalizability of our CNN subitizing model and its applications in salient object detection and image retrieval.en_US
dc.description.sponsorshipThis research was supported in part by US NSF Grants 0910908 and 1029430, and gifts from Adobe and NVIDIA. (0910908 - US NSF; 1029430 - US NSF)en_US
dc.description.urihttps://arxiv.org/abs/1607.07525
dc.description.urihttps://arxiv.org/pdf/1607.07525.pdf
dc.format.extent169 - 186 (18)en_US
dc.languageEnglish
dc.publisherSPRINGERen_US
dc.relation.ispartofINTERNATIONAL JOURNAL OF COMPUTER VISION
dc.subjectScience & technologyen_US
dc.subjectComputer science, artificial intelligenceen_US
dc.subjectComputer scienceen_US
dc.subjectSalient objecten_US
dc.subjectSubitizingen_US
dc.subjectDeep learningen_US
dc.subjectConvolutional neural networken_US
dc.subjectVisual numberen_US
dc.subjectArtificial intelligence and image processingen_US
dc.subjectArtificial intelligence & image processingen_US
dc.titleSalient object subitizingen_US
dc.typeArticleen_US
dc.description.versionAccepted manuscripten_US
dc.identifier.doi10.1007/s11263-017-1011-0
pubs.elements-sourceweb-of-scienceen_US
pubs.notesEmbargo: No embargoen_US
pubs.organisational-groupBoston Universityen_US
pubs.organisational-groupBoston University, College of Arts & Sciencesen_US
pubs.organisational-groupBoston University, College of Arts & Sciences, Department of Computer Scienceen_US
pubs.publication-statusPublisheden_US
dc.identifier.orcid0000-0002-0711-4313 (Sclaroff, Stan)


This item appears in the following Collection(s)

Show simple item record