RICH AND EFFICIENT VISUAL DATA REPRESENTATION

Simple item page
dc.contributor.advisorDavis, Larry Sen_US
dc.contributor.authorRastegari, Mohammaden_US
dc.contributor.departmentComputer Scienceen_US
dc.contributor.publisherDigital Repository at the University of Marylanden_US
dc.contributor.publisherUniversity of Maryland (College Park, Md.)en_US
dc.date.accessioned2016-06-22T05:52:19Z
dc.date.available2016-06-22T05:52:19Z
dc.date.issued2016en_US
dc.description.abstractIncreasing the size of training data in many computer vision tasks has shown to be very effective. Using large scale image datasets (e.g. ImageNet) with simple learning techniques (e.g. linear classifiers) one can achieve state-of-the-art performance in object recognition compared to sophisticated learning techniques on smaller image sets. Semantic search on visual data has become very popular. There are billions of images on the internet and the number is increasing every day. Dealing with large scale image sets is intense per se. They take a significant amount of memory that makes it impossible to process the images with complex algorithms on single CPU machines. Finding an efficient image representation can be a key to attack this problem. A representation being efficient is not enough for image understanding. It should be comprehensive and rich in carrying semantic information. In this proposal we develop an approach to computing binary codes that provide a rich and efficient image representation. We demonstrate several tasks in which binary features can be very effective. We show how binary features can speed up large scale image classification. We present learning techniques to learn the binary features from supervised image set (With different types of semantic supervision; class labels, textual descriptions). We propose several problems that are very important in finding and using efficient image representation.en_US
dc.identifierhttps://doi.org/10.13016/M2MV17
dc.identifier.urihttp://hdl.handle.net/1903/18248
dc.language.isoenen_US
dc.subject.pqcontrolledComputer scienceen_US
dc.subject.pqcontrolledArtificial intelligenceen_US
dc.subject.pquncontrolledBinary Codingen_US
dc.subject.pquncontrolledBinary Image Representationen_US
dc.subject.pquncontrolledComputer Visionen_US
dc.titleRICH AND EFFICIENT VISUAL DATA REPRESENTATIONen_US
dc.typeDissertationen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Rastegari_umd_0117E_16984.pdf
Size:
23.99 MB
Format:
Adobe Portable Document Format
Download

Collections

UMD Theses and Dissertations
Computer Science Theses and Dissertations