About: Efficient Representation of Local Geometry for Large Scale Object Retrieval

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

About: Efficient Representation of Local Geometry for Large Scale Object Retrieval 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	State of the art methods for image and object retrieval exploit both appearance (via visual words) and local geometry (spatial extent, relative pose). In large scale problems, memory becomes a limiting factor - local geometry is stored for each feature detected in each image and requires storage larger than the inverted file and term frequency and inverted document frequency weights together. We propose a novel method for learning discretized local geometry representation based on minimization of average reprojection error in the space of ellipses. The representation requires only 24 bits per feature without drop in performance. Additionally, we show that if the gravity vector assumption is used consistently from the feature description to spatial verification, it improves retrieval performance and decreases the memory footprint. The proposed method outperforms state of the art retrieval algorithms in a standard image retrieval benchmark. State of the art methods for image and object retrieval exploit both appearance (via visual words) and local geometry (spatial extent, relative pose). In large scale problems, memory becomes a limiting factor - local geometry is stored for each feature detected in each image and requires storage larger than the inverted file and term frequency and inverted document frequency weights together. We propose a novel method for learning discretized local geometry representation based on minimization of average reprojection error in the space of ellipses. The representation requires only 24 bits per feature without drop in performance. Additionally, we show that if the gravity vector assumption is used consistently from the feature description to spatial verification, it improves retrieval performance and decreases the memory footprint. The proposed method outperforms state of the art retrieval algorithms in a standard image retrieval benchmark. (en)
Title	Efficient Representation of Local Geometry for Large Scale Object Retrieval Efficient Representation of Local Geometry for Large Scale Object Retrieval (en)
skos:prefLabel	Efficient Representation of Local Geometry for Large Scale Object Retrieval Efficient Representation of Local Geometry for Large Scale Object Retrieval (en)
skos:notation	RIV/68407700:21230/09:00163137!RIV10-MSM-21230___
http://linked.open...avai/riv/aktivita	P R
http://linked.open...avai/riv/aktivity	P(GA102/07/1317), R
http://linked.open...vai/riv/dodaniDat	2010
http://linked.open...aciTvurceVysledku	Matas, Jiří Chum, Ondřej Perďoch, Michal
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	312520
http://linked.open...ai/riv/idVysledku	RIV/68407700:21230/09:00163137
http://linked.open...riv/jazykVysledku	eng - angličtina
http://linked.open.../riv/klicovaSlova	large scale object retrieval; geometry representation; geometric vocabulary (en)
http://linked.open.../riv/klicoveSlovo	geometric vocabulary geometry representation large scale object retrieval
http://linked.open...ontrolniKodProRIV	[856271135198]
http://linked.open...v/mistoKonaniAkce	Fontainebleau Resort, Miami Beach, Florida
http://linked.open...i/riv/mistoVydani	Madison
http://linked.open...i/riv/nazevZdroje	CVPR 2009: Proceedings of the 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
http://linked.open...in/vavai/riv/obor	JD
http://linked.open...ichTvurcuVysledku	3 (xsd:int)
http://linked.open...cetTvurcuVysledku	3 (xsd:int)
http://linked.open...vavai/riv/projekt	Methods for Visual Recognition of Large Collections of Non-rigid Objects
http://linked.open...UplatneniVysledku	2009
http://linked.open...iv/tvurceVysledku	Matas, Jiří Perďoch, Michal Chum, Ondřej
http://linked.open...vavai/riv/typAkce	WRD - Světová
http://linked.open.../riv/zahajeniAkce	2009-06-20 (xsd:date)
issn	1063-6919
number of pages	8 (xsd:int)
http://purl.org/ne...btex#hasPublisher	Omnipress
https://schema.org/isbn	978-1-4244-3991-1
http://localhost/t...ganizacniJednotka	21230
is http://linked.open...avai/riv/vysledek of	Efficient Representation of Local Geometry for Large Scale Object Retrieval Efficient Representation of Local Geometry for Large Scale Object Retrieval Efficient Representation of Local Geometry for Large Scale Object Retrieval Efficient Representation of Local Geometry for Large Scale Object Retrieval

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