FAME: Face association through model evolution

Simple item page
dc.citation.epage49en_US
dc.citation.spage43en_US
dc.contributor.authorGölge, Erenen_US
dc.contributor.authorDuygulu, Pınaren_US
dc.coverage.spatialBoston, MA, USA
dc.date.accessioned2016-02-08T12:13:34Z
dc.date.available2016-02-08T12:13:34Z
dc.date.issued2015-06en_US
dc.departmentDepartment of Computer Engineeringen_US
dc.descriptionDate of Conference: 7-12 June 2015
dc.descriptionConference name: 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
dc.description.abstractWe attack the problem of building classifiers for public faces from web images collected through querying a name. The search results are very noisy even after face detection, with several irrelevant faces corresponding to other people. Moreover, the photographs are taken in the wild with large variety in poses and expressions. We propose a novel method, Face Association through Model Evolution (FAME), that is able to prune the data in an iterative way, for the models associated to a name to evolve. The idea is based on capturing discriminative and representative properties of each instance and eliminating the outliers. The final models are used to classify faces on novel datasets with different characteristics. On benchmark datasets, our results are comparable to or better than the state-of-the-art studies for the task of face identification. © 2015 IEEE.en_US
dc.identifier.doi10.1109/CVPRW.2015.7301353en_US
dc.identifier.urihttp://hdl.handle.net/11693/28185
dc.language.isoEnglishen_US
dc.publisherIEEEen_US
dc.relation.isversionofhttp://dx.doi.org/10.1109/CVPRW.2015.7301353en_US
dc.source.titleIEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshopsen_US
dc.subjectAccuracyen_US
dc.subjectBuildingsen_US
dc.subjectComputational modelingen_US
dc.subjectData modelsen_US
dc.subjectFaceen_US
dc.subjectNoise measurementen_US
dc.subjectTrainingen_US
dc.subjectBuildingsen_US
dc.subjectClassification (of information)en_US
dc.subjectData structuresen_US
dc.subjectFace recognitionen_US
dc.subjectIterative methodsen_US
dc.subjectPattern recognitionen_US
dc.subjectPersonnel trainingen_US
dc.subjectAccuracyen_US
dc.subjectBenchmark datasetsen_US
dc.subjectComputational modelen_US
dc.subjectFaceen_US
dc.subjectFace identificationen_US
dc.subjectModel evolutionen_US
dc.subjectNoise measurementsen_US
dc.subjectState of the arten_US
dc.subjectComputer visionen_US
dc.titleFAME: Face association through model evolutionen_US
dc.typeConference Paperen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
FAME- Face Association through Model Evolution.pdf
Size:
482.24 KB
Format:
Adobe Portable Document Format
Description:
Full Printable Version
Download

Collections

Department of Computer Engineering