Multi-modal Image Retrieval for Search-based Image Annotation
with RF

D 2018

Multi-modal Image Retrieval for Search-based Image Annotation with RF

BUDÍKOVÁ, Petra, Michal BATKO and Pavel ZEZULA

Basic information

Original name

Multi-modal Image Retrieval for Search-based Image Annotation with RF

Authors

BUDÍKOVÁ, Petra (203 Czech Republic, guarantor, belonging to the institution), Michal BATKO (203 Czech Republic, belonging to the institution) and Pavel ZEZULA (203 Czech Republic, belonging to the institution)

Edition

NEW YORK, 2018 IEEE INTERNATIONAL SYMPOSIUM ON MULTIMEDIA (ISM 2018), p. 52-60, 9 pp. 2018

Publisher

IEEE

Other information

Language

English

Type of outcome

Stať ve sborníku

Field of Study

10201 Computer sciences, information science, bioinformatics

Country of publisher

United States of America

Confidentiality degree

není předmětem státního či obchodního tajemství

Publication form

electronic version available online

RIV identification code

RIV/00216224:14330/18:00101829

Organization unit

Faculty of Informatics

ISBN

978-1-5386-6857-3

DOI

http://dx.doi.org/10.1109/ISM.2018.00017

UT WoS

000459863600009

Keywords in English

image annotation; relevance feedback; multi-modal image retrieval

Abstract

V originále

Search-based annotation methods can be used for proposing descriptive keywords to users who need to annotate images e.g. in image stock databases. From the annotation output, users select keywords which they want to assign to the given image. The selected keywords can serve as a relevance feedback for additional annotation refinement. In this paper, we study the possibilities of exploiting the annotation relevance feedback, which is a novel problem that has not been systematically addressed yet. In particular, we focus on the subtask of utilizing the feedback for the retrieval of related annotated images that are subsequently used for mining of candidate keywords. We select three multi-modal search techniques that can be applied to this problem, implement them within a state-of-the-art search-based annotation system, and experimentally evaluate their usefulness for annotation quality improvement.

Links

GA16-18889S, research and development project

Name: Analytika pro velká nestrukturovaná data (Acronym: Big Data Analytics for Unstructured Data)

Investor: Czech Science Foundation

Citovat

BUDÍKOVÁ, Petra, Michal BATKO and Pavel ZEZULA. Multi-modal Image Retrieval for Search-based Image Annotation with RF. Online. In 2018 IEEE INTERNATIONAL SYMPOSIUM ON MULTIMEDIA (ISM 2018). NEW YORK: IEEE, 2018, p. 52-60. ISBN 978-1-5386-6857-3. Available from: https://dx.doi.org/10.1109/ISM.2018.00017.

@inproceedings{1524636,
   author = {Budíková, Petra and Batko, Michal and Zezula, Pavel},
   address = {NEW YORK},
   booktitle = {2018 IEEE INTERNATIONAL SYMPOSIUM ON MULTIMEDIA (ISM 2018)},
   doi = {http://dx.doi.org/10.1109/ISM.2018.00017},
   keywords = {image annotation; relevance feedback; multi-modal image retrieval},
   howpublished = {elektronická verze "online"},
   language = {eng},
   location = {NEW YORK},
   isbn = {978-1-5386-6857-3},
   pages = {52-60},
   publisher = {IEEE},
   title = {Multi-modal Image Retrieval for Search-based Image Annotation with RF},
   year = {2018}
}

TY  - JOUR
ID  - 1524636
AU  - Budíková, Petra - Batko, Michal - Zezula, Pavel
PY  - 2018
TI  - Multi-modal Image Retrieval for Search-based Image Annotation with RF
PB  - IEEE
CY  - NEW YORK
SN  - 9781538668573
KW  - image annotation
KW  - relevance feedback
KW  - multi-modal image retrieval
N2  - Search-based annotation methods can be used for proposing descriptive keywords to users who need to annotate images e.g. in image stock databases. From the annotation output, users select keywords which they want to assign to the given image. The selected keywords can serve as a relevance feedback for additional annotation refinement. In this paper, we study the possibilities of exploiting the annotation relevance feedback, which is a novel problem that has not been systematically addressed yet. In particular, we focus on the subtask of utilizing the feedback for the retrieval of related annotated images that are subsequently used for mining of candidate keywords. We select three multi-modal search techniques that can be applied to this problem, implement them within a state-of-the-art search-based annotation system, and experimentally evaluate their usefulness for annotation quality improvement.
ER  -

BUDÍKOVÁ, Petra, Michal BATKO and Pavel ZEZULA. Multi-modal Image Retrieval for Search-based Image Annotation with RF. Online. In \textit{2018 IEEE INTERNATIONAL SYMPOSIUM ON MULTIMEDIA (ISM 2018)}. NEW YORK: IEEE, 2018, p.~52-60. ISBN~978-1-5386-6857-3. Available from: https://dx.doi.org/10.1109/ISM.2018.00017.

Detailed Information on Publication Record