Inherent Fusion: Towards Scalable Multi-Modal Similarity Search

J 2016

Inherent Fusion: Towards Scalable Multi-Modal Similarity Search

BUDÍKOVÁ, Petra, Michal BATKO, David NOVÁK and Pavel ZEZULA

Basic information

Original name

Inherent Fusion: Towards Scalable Multi-Modal Similarity Search

Authors

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

Edition

Journal of Database Management, IGI Global, 2016, 1063-8016

Other information

Language

English

Type of outcome

Článek v odborném periodiku

Field of Study

10201 Computer sciences, information science, bioinformatics

Country of publisher

United States of America

Confidentiality degree

není předmětem státního či obchodního tajemství

Impact factor

Impact factor: 0.462

RIV identification code

RIV/00216224:14330/16:00088723

Organization unit

Faculty of Informatics

DOI

http://dx.doi.org/10.4018/JDM.2016100101

UT WoS

000396491200001

Keywords in English

Content-Based Retrieval; Evaluation; Image Retrieval; Late Fusion; Multi-Modal Search; Scalability; Similarity Searching

Abstract

V originále

The rapid growth of unstructured data, commonly denoted as the Big Data challenge, requires new technologies that are capable of dealing with complex data objects such as multimedia. In this work, the authors focus on the content-based retrieval approach, which is able to organize such data by exploiting the similarity of data content. In particular, they focus on solutions that are able to combine multiple similarity measures during the query evaluation. The authors introduce a classification of existing approaches and analyze their performance in terms of effectiveness, efficiency, and scalability. Further, they present a novel technique of inherent fusion that combines the efficiency of fast indexed retrieval with the effectiveness of ranking methods. The performance of all discussed methods is evaluated by extensive experiments with user participation.

Links

GBP103/12/G084, research and development project

Name: Centrum pro multi-modální interpretaci dat velkého rozsahu

Investor: Czech Science Foundation

Citovat

BUDÍKOVÁ, Petra, Michal BATKO, David NOVÁK and Pavel ZEZULA. Inherent Fusion: Towards Scalable Multi-Modal Similarity Search. Journal of Database Management. IGI Global, 2016, vol. 27, No 4, p. 1-23. ISSN 1063-8016. Available from: https://dx.doi.org/10.4018/JDM.2016100101.

@article{1374148,
   author = {Budíková, Petra and Batko, Michal and Novák, David and Zezula, Pavel},
   article_number = {4},
   doi = {http://dx.doi.org/10.4018/JDM.2016100101},
   keywords = {Content-Based Retrieval; Evaluation; Image Retrieval; Late Fusion; Multi-Modal Search; Scalability; Similarity Searching},
   language = {eng},
   issn = {1063-8016},
   journal = {Journal of Database Management},
   title = {Inherent Fusion: Towards Scalable Multi-Modal Similarity Search},
   volume = {27},
   year = {2016}
}

TY  - JOUR
ID  - 1374148
AU  - Budíková, Petra - Batko, Michal - Novák, David - Zezula, Pavel
PY  - 2016
TI  - Inherent Fusion: Towards Scalable Multi-Modal Similarity Search
JF  - Journal of Database Management
VL  - 27
IS  - 4
SP  - 1-23
EP  - 1-23
PB  - IGI Global
SN  - 10638016
KW  - Content-Based Retrieval
KW  - Evaluation
KW  - Image Retrieval
KW  - Late Fusion
KW  - Multi-Modal Search
KW  - Scalability
KW  - Similarity Searching
N2  - The rapid growth of unstructured data, commonly denoted as the Big Data challenge, requires new technologies that are capable of dealing with complex data objects such as multimedia. In this work, the authors focus on the content-based retrieval approach, which is able to organize such data by exploiting the similarity of data content. In particular, they focus on solutions that are able to combine multiple similarity measures during the query evaluation. The authors introduce a classification of existing approaches and analyze their performance in terms of effectiveness, efficiency, and scalability. Further, they present a novel technique of inherent fusion that combines the efficiency of fast indexed retrieval with the effectiveness of ranking methods. The performance of all discussed methods is evaluated by extensive experiments with user participation.
ER  -

BUDÍKOVÁ, Petra, Michal BATKO, David NOVÁK and Pavel ZEZULA. Inherent Fusion: Towards Scalable Multi-Modal Similarity Search. \textit{Journal of Database Management}. IGI Global, 2016, vol.~27, No~4, p.~1-23. ISSN~1063-8016. Available from: https://dx.doi.org/10.4018/JDM.2016100101.

Detailed Information on Publication Record