Haber videolarında nesne tanıma ve otomatik etiketleme

Simple item page
dc.contributor.authorBaştan, Muhammeten_US
dc.contributor.authorDuygulu, Pınaren_US
dc.coverage.spatialAntalya, Turkey
dc.date.accessioned2016-02-08T11:46:57Z
dc.date.available2016-02-08T11:46:57Z
dc.date.issued2006-04en_US
dc.departmentDepartment of Computer Engineeringen_US
dc.descriptionDate of Conference: 17-19 April 2006
dc.descriptionConference name: IEEE 14th Signal Processing and Communications Applications, 2006
dc.description.abstractWe propose a new approach to object recognition problem motivated by the availability of large annotated image and video collections. Similar to translation from one language to another, this approach considers the object recognition problem as the translation of visual elements to words. The visual elements represented in feature space are first categorized into a finite set of blobs. Then, the correspondences between the blobs and the words are learned using a method adapted from Statistical Machine Translation. Finally, the correspondences, in the form of a probability table, are used to predict words for particular image regions (region naming), for entire images (auto-annotation), or to associate the automatically generated speech transcript text with the correct video frames (video alignment). Experimental results are presented on TRECVID 2004 data set, which consists of about 150 hours of news videos associated with manual annotations and speech transcript text. © 2006 IEEE.en_US
dc.identifier.doi10.1109/SIU.2006.1659821en_US
dc.identifier.urihttp://hdl.handle.net/11693/27184
dc.language.isoTurkishen_US
dc.publisherIEEE
dc.relation.isversionofhttp://dx.doi.org/10.1109/SIU.2006.1659821en_US
dc.source.title2006 IEEE 14th Signal Processing and Communications Applications Conferenceen_US
dc.subjectAuto annotationen_US
dc.subjectStatistical Machine Translationen_US
dc.subjectVideo alignmenten_US
dc.subjectVideo framesen_US
dc.subjectComputational methodsen_US
dc.subjectImage codingen_US
dc.subjectMultimedia servicesen_US
dc.subjectTranslation (languages)en_US
dc.subjectVideo streamingen_US
dc.subjectWord processingen_US
dc.subjectObject recognitionen_US
dc.titleHaber videolarında nesne tanıma ve otomatik etiketlemeen_US
dc.title.alternativeObject recognition and auto-annotation in news videosen_US
dc.typeConference Paperen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Object recognition and auto-annotation in news videos [Haber videolarinda nesne tanima ve otomatik etiketleme].pdf
Size:
3.56 MB
Format:
Adobe Portable Document Format
Description:
Full printable version
Download

Collections

Department of Computer Engineering