About: Negative Evidences and Co-occurences in Image Retrieval: The Benefit of PCA and Whitening

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: Negative Evidences and Co-occurences in Image Retrieval: The Benefit of PCA and Whitening Goto Sponge NotDistinct Permalink

An Entity of Type : http://linked.opendata.cz/ontology/domain/vavai/Vysledek, within Data Space : linked.opendata.cz associated with source document(s)

Attributes	Values
rdf:type	skos:Concept http://linked.opendata.cz/ontology/domain/vavai/Vysledek
Description	The paper addresses large scale image retrieval with short vector representations. We study dimensionality reduction by Principal Component Analysis (PCA) and propose improvements to its different phases.We show and explicitly exploit relations between i) mean subtraction and the negative evidence, i.e., a visual word that is mutually missing in two descriptions being compared, and ii) the axis de-correlation and the co-occurrences phenomenon. Finally, we propose an effective way to alleviate the quantization artifacts through a joint dimensionality reduction of multiple vocabularies. The proposed techniques are simple, yet significantly and consistently improve over the state of the art on compact image representations. Complementary experiments in image classification show that the methods are generally applicable. The paper addresses large scale image retrieval with short vector representations. We study dimensionality reduction by Principal Component Analysis (PCA) and propose improvements to its different phases.We show and explicitly exploit relations between i) mean subtraction and the negative evidence, i.e., a visual word that is mutually missing in two descriptions being compared, and ii) the axis de-correlation and the co-occurrences phenomenon. Finally, we propose an effective way to alleviate the quantization artifacts through a joint dimensionality reduction of multiple vocabularies. The proposed techniques are simple, yet significantly and consistently improve over the state of the art on compact image representations. Complementary experiments in image classification show that the methods are generally applicable. (en)
Title	Negative Evidences and Co-occurences in Image Retrieval: The Benefit of PCA and Whitening Negative Evidences and Co-occurences in Image Retrieval: The Benefit of PCA and Whitening (en)
skos:prefLabel	Negative Evidences and Co-occurences in Image Retrieval: The Benefit of PCA and Whitening Negative Evidences and Co-occurences in Image Retrieval: The Benefit of PCA and Whitening (en)
skos:notation	RIV/68407700:21230/12:00200571!RIV13-GA0-21230___
http://linked.open...avai/riv/aktivita	P
http://linked.open...avai/riv/aktivity	P(GAP103/12/2310)
http://linked.open...vai/riv/dodaniDat	2013
http://linked.open...aciTvurceVysledku	Chum, Ondřej
http://linked.open.../riv/druhVysledku	D - Článek ve sborníku
http://linked.open...iv/duvernostUdaju	S - Úplné a pravdivé údaje nepodléhající ochraně podle zvláštních právních předpisů
http://linked.open...titaPredkladatele	České vysoké učení technické v Praze / Fakulta elektrotechnická
http://linked.open...dnocenehoVysledku	153543
http://linked.open...ai/riv/idVysledku	RIV/68407700:21230/12:00200571
http://linked.open...riv/jazykVysledku	eng - angličtina
http://linked.open.../riv/klicovaSlova	image retrieval; short codes; PCA (en)
http://linked.open.../riv/klicoveSlovo	PCA image retrieval short codes
http://linked.open...ontrolniKodProRIV	[55B271FACEF6]
http://linked.open...v/mistoKonaniAkce	Firenze
http://linked.open...i/riv/mistoVydani	Heidelberg
http://linked.open...i/riv/nazevZdroje	Computer Vision - ECCV 2012
http://linked.open...in/vavai/riv/obor	JD
http://linked.open...ichTvurcuVysledku	1 (xsd:int)
http://linked.open...cetTvurcuVysledku	2 (xsd:int)
http://linked.open...vavai/riv/projekt	Large Scale Image and Object Search as a Teacher
http://linked.open...UplatneniVysledku	2012
http://linked.open...iv/tvurceVysledku	Chum, Ondřej Jégou, H.
http://linked.open...vavai/riv/typAkce	WRD - Světová
http://linked.open.../riv/zahajeniAkce	2012-10-07 (xsd:date)
issn	0302-9743
number of pages	14 (xsd:int)
http://purl.org/ne...btex#hasPublisher	Springer-Verlag
https://schema.org/isbn	978-3-642-33708-6
http://localhost/t...ganizacniJednotka	21230

Faceted Search & Find service v1.16.118 as of Jun 21 2024

Alternative Linked Data Documents: ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 07.20.3240 as of Jun 21 2024, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (126 GB total memory, 58 GB memory in use)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software