Multi-modal Similarity Retrieval with Distributed Key-value Store

NOVÁK, David. Multi-modal Similarity Retrieval with Distributed Key-value Store. MOBILE NETWORKS & APPLICATIONS. DORDRECHT: SPRINGER, 2015, vol. 20, No 4, p. 521-532. ISSN 1383-469X. Available from: https://dx.doi.org/10.1007/s11036-014-0561-4.

Basic information

• Original name: Multi-modal Similarity Retrieval with Distributed Key-value Store
• Authors: NOVÁK, David (203 Czech Republic, guarantor, belonging to the institution).
• Edition: MOBILE NETWORKS & APPLICATIONS, DORDRECHT, SPRINGER, 2015, 1383-469X.

Other information

• Original language: English
• Type of outcome: Article in a journal
• Field of Study: 10201 Computer sciences, information science, bioinformatics
• Country of publisher: Netherlands
• Confidentiality degree: is not subject to a state or trade secret
• Impact factor: Impact factor: 1.538
• RIV identification code: RIV/00216224:14330/15:00081691
• Organization unit: Faculty of Informatics
• Doi: http://dx.doi.org/10.1007/s11036-014-0561-4
• UT WoS: 000360003900013
• Keywords in English: Similarity search; Multi-modal search; Big Data; Scalability; Distributed hash table
• Tags: DISA
• Tags: International impact, Reviewed

Abstract

We propose a system architecture for large-scale similarity search in various types of digital data. The architecture combines contemporary highly-scalable distributed data stores with recent efficient similarity indexes and also with other types of search indexes. The system enables various types of data access by distance-based similarity queries, standard term and attribute queries, and advanced queries combining several search aspects (modalities). The first part of this work describes the generic architecture and similarity index PPP-Codes, which is suitable for our system. In the second part, we describe two specific instances of this architecture that manage two large collections of digital images and provide content-based visual search, keyword search, attribute-based access, and their combinations. The first collection is the CoPhIR benchmark with 106 million images accessed by MPEG7 visual descriptors and the second collection contains 20 million images with complex features obtained from deep convolutional neural network.

Links

• GAP103/10/0886, research and development project: Name: Vizuální vyhledávání obrázků na Webu (Acronym: VisualWeb)

Investor: Czech Science Foundation, Content-based Image Retrieval on the Web Scale