خط مشی دسترسیدرباره ما
ثبت نامثبت نام
راهنماراهنما
فارسی
ورودورود
صفحه اصلیصفحه اصلی
جستجوی مدارک
تمام متن
منابع دیجیتالی
رکورد قبلیرکورد بعدی
Document Type : Latin Dissertation
Language of Document : English
Record Number : 149764
Doc. No : ET21556
Main Entry : Lexing Xie
Title Proper : Unsupervised Pattern Discovery for Multimedia Sequences
Note : This document is digital این مدرک بصورت الکترونیکی می باشد
Abstract : This thesis investigates the problem of discovering patterns from multimedia se-quences. The problem is of interest as capturing and storing large amounts ofmultimedia data has become commonplace, yet our capability to process, interpret,and use these rich corpora has notably lagged behind.Patterns refer to the the recurrent and statistically consistent units in a datacollection, their recurrence and consistency provide useful bases for organizing largecorpra. Unsupervised pattern discovery is important, as it is desirable to adapt to di-verse media collections without extensive annotation. Moreover, the patterns shouldbe meaningful, since meanings are what we humans perceive from multimedia. Thegoal of this thesis is to devise a general framework for finding multi-modal tem-poral patterns from a collection of multimedia sequences, using the self-similarityin both the appearance and the temporaltested for theQ1 PC1 bus cardBoth these projects mere sofixare des elopment efforts tonards contributing to dlfferentaspects of Roboucs and lZ1echatronics projects m the Controls and Roboucs Group..
Subject : Electericl tess
: برق
electronic file name : TL44730.pdf
Title and statement of responsibility and : Unsupervised Pattern Discovery for Multimedia Sequences [Thesis]
 
 
 
(در صورت عدم وضوح تصویر اینجا را کلیک نمایید)