Aggregating local image descriptors into compact codes

Autores
Jegou, H.; Perronnin, F.; Douze, M.; Sanchez, Jorge Adrian; Perez, P.; Schmid, C.
Año de publicación
2012
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
This paper addresses the problem of large-scale image search. Three constraints have to be taken into account: search accuracy, efficiency, and memory usage. We first present and evaluate different ways of aggregating local image descriptors into a vector and show that the Fisher kernel achieves better performance than the reference bag-of-visual words approach for any given vector dimension. We then jointly optimize dimensionality reduction and indexing in order to obtain a precise vector comparison as well as a compact representation. The evaluation shows that the image representation can be reduced to a few dozen bytes while preserving high accuracy. Searching a 100 million image data set takes about 250 ms on one processor core.
Fil: Jegou, H.. National Institute for Research in Digital Science and Technology; Francia
Fil: Perronnin, F.. Xerox; Francia
Fil: Douze, M.. National Institute for Research in Digital Science and Technology; Francia
Fil: Sanchez, Jorge Adrian. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía y Física; Argentina
Fil: Perez, P.. Technicolor; Francia
Fil: Schmid, C.. National Institute for Research in Digital Science and Technology; Francia
Materia
IMAGE SEARCH
IMAGE RETRIEVAL
INDEXING
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/198005
Acceder
id CONICETDig_e8bc63ed7469d2294a03a4f7d8eecfab
oai_identifier_str oai:ri.conicet.gov.ar:11336/198005
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Aggregating local image descriptors into compact codesJegou, H.Perronnin, F.Douze, M.Sanchez, Jorge AdrianPerez, P.Schmid, C.IMAGE SEARCHIMAGE RETRIEVALINDEXINGhttps://purl.org/becyt/ford/1.2https://purl.org/becyt/ford/1This paper addresses the problem of large-scale image search. Three constraints have to be taken into account: search accuracy, efficiency, and memory usage. We first present and evaluate different ways of aggregating local image descriptors into a vector and show that the Fisher kernel achieves better performance than the reference bag-of-visual words approach for any given vector dimension. We then jointly optimize dimensionality reduction and indexing in order to obtain a precise vector comparison as well as a compact representation. The evaluation shows that the image representation can be reduced to a few dozen bytes while preserving high accuracy. Searching a 100 million image data set takes about 250 ms on one processor core.Fil: Jegou, H.. National Institute for Research in Digital Science and Technology; FranciaFil: Perronnin, F.. Xerox; FranciaFil: Douze, M.. National Institute for Research in Digital Science and Technology; FranciaFil: Sanchez, Jorge Adrian. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía y Física; ArgentinaFil: Perez, P.. Technicolor; FranciaFil: Schmid, C.. National Institute for Research in Digital Science and Technology; FranciaIEEE Computer Society2012-09info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/198005Jegou, H.; Perronnin, F.; Douze, M.; Sanchez, Jorge Adrian; Perez, P.; et al.; Aggregating local image descriptors into compact codes; IEEE Computer Society; IEEE Transactions on Pattern Analysis and Machine Intelligence; 34; 9; 9-2012; 1704-17160162-8828CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/doi/info:eu-repo/semantics/altIdentifier/doi/10.1109/TPAMI.2011.235info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-sa/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-09-29T10:05:58Zoai:ri.conicet.gov.ar:11336/198005instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982025-09-29 10:05:58.8CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Aggregating local image descriptors into compact codes
title Aggregating local image descriptors into compact codes
spellingShingle Aggregating local image descriptors into compact codes
Jegou, H.
IMAGE SEARCH
IMAGE RETRIEVAL
INDEXING
title_short Aggregating local image descriptors into compact codes
title_full Aggregating local image descriptors into compact codes
title_fullStr Aggregating local image descriptors into compact codes
title_full_unstemmed Aggregating local image descriptors into compact codes
title_sort Aggregating local image descriptors into compact codes
dc.creator.none.fl_str_mv Jegou, H.
Perronnin, F.
Douze, M.
Sanchez, Jorge Adrian
Perez, P.
Schmid, C.
author Jegou, H.
author_facet Jegou, H.
Perronnin, F.
Douze, M.
Sanchez, Jorge Adrian
Perez, P.
Schmid, C.
author_role author
author2 Perronnin, F.
Douze, M.
Sanchez, Jorge Adrian
Perez, P.
Schmid, C.
author2_role author
author
author
author
author
dc.subject.none.fl_str_mv IMAGE SEARCH
IMAGE RETRIEVAL
INDEXING
topic IMAGE SEARCH
IMAGE RETRIEVAL
INDEXING
purl_subject.fl_str_mv https://purl.org/becyt/ford/1.2
https://purl.org/becyt/ford/1
dc.description.none.fl_txt_mv This paper addresses the problem of large-scale image search. Three constraints have to be taken into account: search accuracy, efficiency, and memory usage. We first present and evaluate different ways of aggregating local image descriptors into a vector and show that the Fisher kernel achieves better performance than the reference bag-of-visual words approach for any given vector dimension. We then jointly optimize dimensionality reduction and indexing in order to obtain a precise vector comparison as well as a compact representation. The evaluation shows that the image representation can be reduced to a few dozen bytes while preserving high accuracy. Searching a 100 million image data set takes about 250 ms on one processor core.
Fil: Jegou, H.. National Institute for Research in Digital Science and Technology; Francia
Fil: Perronnin, F.. Xerox; Francia
Fil: Douze, M.. National Institute for Research in Digital Science and Technology; Francia
Fil: Sanchez, Jorge Adrian. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad Nacional de Córdoba. Facultad de Matemática, Astronomía y Física; Argentina
Fil: Perez, P.. Technicolor; Francia
Fil: Schmid, C.. National Institute for Research in Digital Science and Technology; Francia
description This paper addresses the problem of large-scale image search. Three constraints have to be taken into account: search accuracy, efficiency, and memory usage. We first present and evaluate different ways of aggregating local image descriptors into a vector and show that the Fisher kernel achieves better performance than the reference bag-of-visual words approach for any given vector dimension. We then jointly optimize dimensionality reduction and indexing in order to obtain a precise vector comparison as well as a compact representation. The evaluation shows that the image representation can be reduced to a few dozen bytes while preserving high accuracy. Searching a 100 million image data set takes about 250 ms on one processor core.
publishDate 2012
dc.date.none.fl_str_mv 2012-09
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/198005
Jegou, H.; Perronnin, F.; Douze, M.; Sanchez, Jorge Adrian; Perez, P.; et al.; Aggregating local image descriptors into compact codes; IEEE Computer Society; IEEE Transactions on Pattern Analysis and Machine Intelligence; 34; 9; 9-2012; 1704-1716
0162-8828
CONICET Digital
CONICET
url http://hdl.handle.net/11336/198005
identifier_str_mv Jegou, H.; Perronnin, F.; Douze, M.; Sanchez, Jorge Adrian; Perez, P.; et al.; Aggregating local image descriptors into compact codes; IEEE Computer Society; IEEE Transactions on Pattern Analysis and Machine Intelligence; 34; 9; 9-2012; 1704-1716
0162-8828
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/doi/
info:eu-repo/semantics/altIdentifier/doi/10.1109/TPAMI.2011.235
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv IEEE Computer Society
publisher.none.fl_str_mv IEEE Computer Society
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1844613902336262144
score 13.070432

Publicaciones similares