Fusion Strategies for Large-Scale Multi-modal Image Retrieval

D 2017

Fusion Strategies for Large-Scale Multi-modal Image Retrieval

BUDÍKOVÁ, Petra; Michal BATKO a Pavel ZEZULA

Základní údaje

Originální název

Fusion Strategies for Large-Scale Multi-modal Image Retrieval

Autoři

BUDÍKOVÁ, Petra; Michal BATKO a Pavel ZEZULA

Vydání

Berlin, Heidelberg, Transactions on Large-Scale Data- and Knowledge-Centered Systems XXXIII, od s. 146-184, 39 s. 2017

Nakladatel

Springer

Další údaje

Jazyk

angličtina

Typ výsledku

Stať ve sborníku

Obor

10201 Computer sciences, information science, bioinformatics

Stát vydavatele

Spojené státy

Utajení

není předmětem státního či obchodního tajemství

Forma vydání

tištěná verze "print"

Impakt faktor

Impact factor: 0.402 v roce 2005

Kód RIV

RIV/00216224:14330/17:00094968

Organizační jednotka

Fakulta informatiky

ISBN

978-3-662-55695-5

ISSN

DOI

https://doi.org/10.1007/978-3-662-55696-2_5

EID Scopus

2-s2.0-85027384793

Klíčová slova anglicky

Multimodal image retrieval; fusion strategies; evaluation

Štítky

DISA

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 13. 4. 2018 09:57, RNDr. Pavel Šmerk, Ph.D.

Anotace

V originále

Large-scale data management and retrieval in complex domains such as images, videos, or biometrical data remains one of the most important and challenging information processing tasks. Even after two decades of intensive research, many questions still remain to be answered before working tools become available for everyday use. In this work, we focus on the practical applicability of different multi-modal retrieval techniques. Multi-modal searching, which combines several complementary views on complex data objects, follows the human thinking process and represents a very promising retrieval paradigm. However, a rapid development of modality fusion techniques in several diverse directions and a lack of comparisons between individual approaches have resulted in a confusing situation when the applicability of individual solutions is unclear. Aiming at improving the research community’s comprehension of this topic, we analyze and systematically categorize existing multimodal search techniques, identify their strengths, and describe selected representatives. In the second part of the paper, we focus on the specific problem of large-scale multi-modal image retrieval on the web. We analyze the requirements of such task, implement several applicable fusion methods, and experimentally evaluate their performance in terms of both efficiency and effectiveness. The extensive experiments provide a unique comparison of diverse approaches to modality fusion in equal settings on two large real-world datasets.

Návaznosti

GA16-18889S, projekt VaV

Název: Analytika pro velká nestrukturovaná data (Akronym: Big Data Analytics for Unstructured Data)

Investor: Grantová agentura ČR, Big Data Analytics for Unstructured Data

Citovat

BUDÍKOVÁ, Petra; Michal BATKO a Pavel ZEZULA. Fusion Strategies for Large-Scale Multi-modal Image Retrieval. In Transactions on Large-Scale Data- and Knowledge-Centered Systems XXXIII. Berlin, Heidelberg: Springer, 2017, s. 146-184. ISBN 978-3-662-55695-5. Dostupné z: https://doi.org/10.1007/978-3-662-55696-2_5.

@inproceedings{1390178,
   author = {Budíková, Petra and Batko, Michal and Zezula, Pavel},
   address = {Berlin, Heidelberg},
   booktitle = {Transactions on Large-Scale Data- and Knowledge-Centered Systems XXXIII},
   doi = {https://doi.org/10.1007/978-3-662-55696-2_5},
   keywords = {Multimodal image retrieval; fusion strategies; evaluation},
   howpublished = {tištěná verze "print"},
   language = {eng},
   location = {Berlin, Heidelberg},
   isbn = {978-3-662-55695-5},
   pages = {146-184},
   publisher = {Springer},
   title = {Fusion Strategies for Large-Scale Multi-modal Image Retrieval},
   year = {2017}
}

TY  - CONF
ID  - 1390178
AU  - Budíková, Petra - Batko, Michal - Zezula, Pavel
PY  - 2017
TI  - Fusion Strategies for Large-Scale Multi-modal Image Retrieval
PB  - Springer
CY  - Berlin, Heidelberg
SN  - 9783662556955
KW  - Multimodal image retrieval
KW  - fusion strategies
KW  - evaluation
N2  - Large-scale data management and retrieval in complex domains such as images, videos, or biometrical data remains one of the most important and challenging information processing tasks. Even after two decades of intensive research, many questions still remain to be answered before working tools become available for everyday use. In this work, we focus on the practical applicability of different multi-modal retrieval techniques. Multi-modal searching, which combines several complementary views on complex data objects, follows the human thinking process and represents a very promising retrieval paradigm. However, a rapid development of modality fusion techniques in several diverse directions and a lack of comparisons between individual approaches have resulted in a confusing situation when the applicability of individual solutions is unclear. Aiming at improving the research community’s comprehension of this topic, we analyze and systematically categorize existing multimodal search techniques, identify their strengths, and describe selected representatives. In the second part of the paper, we focus on the specific problem of large-scale multi-modal image retrieval on the web. We analyze the requirements of such task, implement several applicable fusion methods, and experimentally evaluate their performance in terms of both efficiency and effectiveness. The extensive experiments provide a unique comparison of diverse approaches to modality fusion in equal settings on two large real-world datasets.
ER  -

BUDÍKOVÁ, Petra; Michal BATKO a Pavel ZEZULA. Fusion Strategies for Large-Scale Multi-modal Image Retrieval. In \textit{Transactions on Large-Scale Data- and Knowledge-Centered Systems XXXIII}. Berlin, Heidelberg: Springer, 2017, s.~146-184. ISBN~978-3-662-55695-5. Dostupné z: https://doi.org/10.1007/978-3-662-55696-2\_{}5.

Přehled o publikaci