FAST–AT: FAST AUTOMATIC THUMBNAIL GENERATION USING DEEP NEURAL NETWORKS

Simple item page
dc.contributor.advisorDavis, Larry Sen_US
dc.contributor.authorEsmaeili, Seyed Abdulazizen_US
dc.contributor.departmentElectrical Engineeringen_US
dc.contributor.publisherDigital Repository at the University of Marylanden_US
dc.contributor.publisherUniversity of Maryland (College Park, Md.)en_US
dc.date.accessioned2017-09-13T05:35:07Z
dc.date.available2017-09-13T05:35:07Z
dc.date.issued2017en_US
dc.description.abstractFast-AT is an automatic thumbnail generation system based on deep neural networks. It is a fully-convolutional CNN, which learns specific filters for thumbnails of different sizes and aspect ratios. During inference, the appropriate filter is selected depending on the dimensions of the target thumbnail. Unlike most previous work, Fast-AT does not utilize saliency but addresses the problem directly. In addition, it eliminates the need to conduct region search on the saliency map. The model generalizes to thumbnails of different sizes including those with extreme aspect ratios and can generate thumbnails in real time. A data set of more than 70,000 thumbnail annotations was collected to train Fast-AT. We show competitive results in comparison to existing techniques.en_US
dc.identifierhttps://doi.org/10.13016/M20G3GZ5C
dc.identifier.urihttp://hdl.handle.net/1903/19796
dc.language.isoenen_US
dc.subject.pqcontrolledElectrical engineeringen_US
dc.subject.pquncontrolledAutomatic thumbnail generationen_US
dc.subject.pquncontrolledComputer Visionen_US
dc.subject.pquncontrolledDeep Learningen_US
dc.subject.pquncontrolledObject Detectionen_US
dc.titleFAST–AT: FAST AUTOMATIC THUMBNAIL GENERATION USING DEEP NEURAL NETWORKSen_US
dc.typeThesisen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Esmaeili_umd_0117N_18207.pdf
Size:
1.44 MB
Format:
Adobe Portable Document Format
Download

Collections

UMD Theses and Dissertations
Electrical & Computer Engineering Theses and Dissertations