Automatic index construction for multimedia digital libraries

San Yih Hwang, Wan-Shiou Yang, Kang Di Ting

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Indexing remains one of the most popular tools provided by digital libraries to help users identify and understand the characteristics of the information they need. Despite extensive studies of the problem of automatic index construction for text-based digital libraries, the construction of multimedia digital libraries continues to represent a challenge, because multimedia objects usually lack sufficient text information to ensure reliable index learning. This research attempts to tackle the problem of automatic index construction for multimedia objects by employing Web usage logs and limited keywords pertaining to multimedia objects. The tests of two proposed algorithms use two different data sets with different amounts of textual information. Web usage logs offer precious information for building indexes of multimedia digital libraries with limited textual information. The proposed methods generally yield better indexes, especially for the artwork data set.

Original languageEnglish
Pages (from-to)295-307
Number of pages13
JournalInformation Processing and Management
Volume46
Issue number3
DOIs
Publication statusPublished - 2010 May 1

Fingerprint

index construction
Digital libraries
multimedia
indexing
Index construction
Multimedia
lack
learning

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Media Technology
  • Computer Science Applications
  • Management Science and Operations Research
  • Library and Information Sciences

Cite this

@article{53a789c1d02a4659ab9c0a4f60dd144a,
title = "Automatic index construction for multimedia digital libraries",
abstract = "Indexing remains one of the most popular tools provided by digital libraries to help users identify and understand the characteristics of the information they need. Despite extensive studies of the problem of automatic index construction for text-based digital libraries, the construction of multimedia digital libraries continues to represent a challenge, because multimedia objects usually lack sufficient text information to ensure reliable index learning. This research attempts to tackle the problem of automatic index construction for multimedia objects by employing Web usage logs and limited keywords pertaining to multimedia objects. The tests of two proposed algorithms use two different data sets with different amounts of textual information. Web usage logs offer precious information for building indexes of multimedia digital libraries with limited textual information. The proposed methods generally yield better indexes, especially for the artwork data set.",
author = "Hwang, {San Yih} and Wan-Shiou Yang and Ting, {Kang Di}",
year = "2010",
month = "5",
day = "1",
doi = "10.1016/j.ipm.2009.10.006",
language = "English",
volume = "46",
pages = "295--307",
journal = "Information Processing and Management",
issn = "0306-4573",
publisher = "Elsevier Limited",
number = "3",

}

Automatic index construction for multimedia digital libraries. / Hwang, San Yih; Yang, Wan-Shiou; Ting, Kang Di.

In: Information Processing and Management, Vol. 46, No. 3, 01.05.2010, p. 295-307.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Automatic index construction for multimedia digital libraries

AU - Hwang, San Yih

AU - Yang, Wan-Shiou

AU - Ting, Kang Di

PY - 2010/5/1

Y1 - 2010/5/1

N2 - Indexing remains one of the most popular tools provided by digital libraries to help users identify and understand the characteristics of the information they need. Despite extensive studies of the problem of automatic index construction for text-based digital libraries, the construction of multimedia digital libraries continues to represent a challenge, because multimedia objects usually lack sufficient text information to ensure reliable index learning. This research attempts to tackle the problem of automatic index construction for multimedia objects by employing Web usage logs and limited keywords pertaining to multimedia objects. The tests of two proposed algorithms use two different data sets with different amounts of textual information. Web usage logs offer precious information for building indexes of multimedia digital libraries with limited textual information. The proposed methods generally yield better indexes, especially for the artwork data set.

AB - Indexing remains one of the most popular tools provided by digital libraries to help users identify and understand the characteristics of the information they need. Despite extensive studies of the problem of automatic index construction for text-based digital libraries, the construction of multimedia digital libraries continues to represent a challenge, because multimedia objects usually lack sufficient text information to ensure reliable index learning. This research attempts to tackle the problem of automatic index construction for multimedia objects by employing Web usage logs and limited keywords pertaining to multimedia objects. The tests of two proposed algorithms use two different data sets with different amounts of textual information. Web usage logs offer precious information for building indexes of multimedia digital libraries with limited textual information. The proposed methods generally yield better indexes, especially for the artwork data set.

UR - http://www.scopus.com/inward/record.url?scp=77950297015&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77950297015&partnerID=8YFLogxK

U2 - 10.1016/j.ipm.2009.10.006

DO - 10.1016/j.ipm.2009.10.006

M3 - Article

AN - SCOPUS:77950297015

VL - 46

SP - 295

EP - 307

JO - Information Processing and Management

JF - Information Processing and Management

SN - 0306-4573

IS - 3

ER -