About: Learning A Fast Emulator of a Binary Decision Process

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

About: Learning A Fast Emulator of a Binary Decision Process 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	Computation time is an important performance characteristic of computer vision algorithms. This paper shows how existing (slow) binary-valued decision algorithms can be approximated by a trained WaldBoost classifier, which minimises the decision time while guaranteeing predefined approximation precision. The core idea is to take an existing algorithm as a black box performing some useful binary decision task and to train the WaldBoost classifier as its emulator. Two interest point detectors, Hessian-Laplace and Kadir-Brady saliency detector, are emulated to demonstrate the approach. The experiments show similar repeatability and matching score of the original and emulated algorithms while achieving a 70-fold speed-up for Kadir-Brady detector. Computation time is an important performance characteristic of computer vision algorithms. This paper shows how existing (slow) binary-valued decision algorithms can be approximated by a trained WaldBoost classifier, which minimises the decision time while guaranteeing predefined approximation precision. The core idea is to take an existing algorithm as a black box performing some useful binary decision task and to train the WaldBoost classifier as its emulator. Two interest point detectors, Hessian-Laplace and Kadir-Brady saliency detector, are emulated to demonstrate the approach. The experiments show similar repeatability and matching score of the original and emulated algorithms while achieving a 70-fold speed-up for Kadir-Brady detector. (en) Computation time is an important performance characteristic of computer vision algorithms. This paper shows how existing (slow) binary-valued decision algorithms can be approximated by a trained WaldBoost classifier, which minimises the decision time while guaranteeing predefined approximation precision. The core idea is to take an existing algorithm as a black box performing some useful binary decision task and to train the WaldBoost classifier as its emulator. Two interest point detectors, Hessian-Laplace and Kadir-Brady saliency detector, are emulated to demonstrate the approach. The experiments show similar repeatability and matching score of the original and emulated algorithms while achieving a 70-fold speed-up for Kadir-Brady detector. (cs)
Title	Learning A Fast Emulator of a Binary Decision Process Learning A Fast Emulator of a Binary Decision Process (en) Learning A Fast Emulator of a Binary Decision Process (cs)
skos:prefLabel	Learning A Fast Emulator of a Binary Decision Process Learning A Fast Emulator of a Binary Decision Process (en) Learning A Fast Emulator of a Binary Decision Process (cs)
skos:notation	RIV/68407700:21230/07:03135673!RIV08-GA0-21230___
http://linked.open.../vavai/riv/strany	236;245
http://linked.open...avai/riv/aktivita	P
http://linked.open...avai/riv/aktivity	P(GA102/07/1317)
http://linked.open...vai/riv/dodaniDat	2008
http://linked.open...aciTvurceVysledku	Matas, Jiří Šochman, Jan
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	430677
http://linked.open...ai/riv/idVysledku	RIV/68407700:21230/07:03135673
http://linked.open...riv/jazykVysledku	eng - angličtina
http://linked.open.../riv/klicovaSlova	Hessian-Laplace; WaldBoost; interest points; saliency (en)
http://linked.open.../riv/klicoveSlovo	Hessian-Laplace saliency WaldBoost interest points
http://linked.open...ontrolniKodProRIV	[91ACE056C67F]
http://linked.open...v/mistoKonaniAkce	Tokyo
http://linked.open...i/riv/mistoVydani	Heidelberg
http://linked.open...i/riv/nazevZdroje	Computer Vision - ACCV 2007. Proceedings 8th Asian Conference on Computer Vision
http://linked.open...in/vavai/riv/obor	JD
http://linked.open...ichTvurcuVysledku	2 (xsd:int)
http://linked.open...cetTvurcuVysledku	2 (xsd:int)
http://linked.open...vavai/riv/projekt	Methods for Visual Recognition of Large Collections of Non-rigid Objects
http://linked.open...UplatneniVysledku	2007
http://linked.open...iv/tvurceVysledku	Matas, Jiří Šochman, Jan
http://linked.open...vavai/riv/typAkce	WRD - Světová
http://linked.open.../riv/zahajeniAkce	2007-11-18 (xsd:date)
number of pages	10 (xsd:int)
http://purl.org/ne...btex#hasPublisher	Springer-Verlag
https://schema.org/isbn	978-3-540-76385-7
http://localhost/t...ganizacniJednotka	21230
is http://linked.open...avai/riv/vysledek of	Learning A Fast Emulator of a Binary Decision Process Learning A Fast Emulator of a Binary Decision Process Learning A Fast Emulator of a Binary Decision Process

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, 85 GB memory in use)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software