About: Geometric min-Hashing: Finding a (thick) needle in a haystack

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

About: Geometric min-Hashing: Finding a (thick) needle in a haystack 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	We propose a novel hashing scheme for image retrieval, clustering and automatic object discovery. Unlike commonly used bag-of-words approaches, the spatial extent of image features is exploited in our method. The geometric information is used both to construct repeatable hash keys and to increase the discriminability of the description. Each hash key combines visual appearance (visual words) with semi-local geometric information. Compared with the state-of-the-art min-hash, the proposed method has both higher recall (probability of collision for hashes on the same object) and lower false positive rates (random collisions). The advantages of geometric min-hashing approach are most pronounced in the presence of viewpoint and scale change, significant occlusion or small physical overlap of the viewing fields. We demonstrate the power of the proposed method on small object discovery in a large unordered collection of images and on a large scale image clustering problem. We propose a novel hashing scheme for image retrieval, clustering and automatic object discovery. Unlike commonly used bag-of-words approaches, the spatial extent of image features is exploited in our method. The geometric information is used both to construct repeatable hash keys and to increase the discriminability of the description. Each hash key combines visual appearance (visual words) with semi-local geometric information. Compared with the state-of-the-art min-hash, the proposed method has both higher recall (probability of collision for hashes on the same object) and lower false positive rates (random collisions). The advantages of geometric min-hashing approach are most pronounced in the presence of viewpoint and scale change, significant occlusion or small physical overlap of the viewing fields. We demonstrate the power of the proposed method on small object discovery in a large unordered collection of images and on a large scale image clustering problem. (en)
Title	Geometric min-Hashing: Finding a (thick) needle in a haystack Geometric min-Hashing: Finding a (thick) needle in a haystack (en)
skos:prefLabel	Geometric min-Hashing: Finding a (thick) needle in a haystack Geometric min-Hashing: Finding a (thick) needle in a haystack (en)
skos:notation	RIV/68407700:21230/09:00163136!RIV10-MSM-21230___
http://linked.open...avai/riv/aktivita	P
http://linked.open...avai/riv/aktivity	P(7E08031), P(GP102/09/P423)
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	316325
http://linked.open...ai/riv/idVysledku	RIV/68407700:21230/09:00163136
http://linked.open...riv/jazykVysledku	eng - angličtina
http://linked.open.../riv/klicovaSlova	geometric min-hash; large scale image clustering; automatic object discovery (en)
http://linked.open.../riv/klicoveSlovo	automatic object discovery geometric min-hash large scale image clustering
http://linked.open...ontrolniKodProRIV	[7CD136E738A4]
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	Dynamic Interactive Perception-action Learning in Cognitive Systems High-dimensional Similarity Measures for Web Scale Object and Category Search
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	Geometric min-Hashing: Finding a (thick) needle in a haystack Geometric min-Hashing: Finding a (thick) needle in a haystack Geometric min-Hashing: Finding a (thick) needle in a haystack Geometric min-Hashing: Finding a (thick) needle in a haystack

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