Indexing vectors of locally aggregated descriptors using inverted files
| Autor: | Paolo Bolettieri, Giuseppe Amato, Claudio Gennaro, Fabrizio Falchi |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2014 |
| Předmět: |
Contextual image classification
Exploit business.industry Computer science Search engine indexing ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Full text search Pattern recognition landmarks recognition computer.software_genre Image (mathematics) Software Data mining Artificial intelligence Information Storage and Retrievals business Representation (mathematics) Scale (map) computer image classification local features |
| Zdroj: | ICMR'14-ACM International Conference on Multimedia Retrieval, pp. 439–442, Glasgow, UK, 1-4 April 2014 info:cnr-pdr/source/autori:Amato G.; Bolettieri P.; Falchi F.; Gennaro C./congresso_nome:ICMR'14-ACM International Conference on Multimedia Retrieval/congresso_luogo:Glasgow, UK/congresso_data:1-4 April 2014/anno:2014/pagina_da:439/pagina_a:442/intervallo_pagine:439–442 ICMR |
| Popis: | Vector of locally aggregated descriptors (VLAD) is a promising approach for addressing the problem of image search on a very large scale. This representation is proposed to overcome the quantization error problem faced in Bag-of-Words (BoW) representation. In this paper, we propose to enable inverted files of standard text search engines to exploit VLAD representation to deal with large-scale image search scenarios. We show that the use of inverted files with VLAD significantly outperforms BoW in terms of efficiency and effectiveness on the same hardware and software infrastructure. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|