Lost in Quantization: Improving Particular Object Retrieval in Large Scale Image Databases

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F08%3A03150851" target="_blank" >RIV/68407700:21230/08:03150851 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Lost in Quantization: Improving Particular Object Retrieval in Large Scale Image Databases

Popis výsledku v původním jazyce

The state of the art in visual object retrieval from large databases is achieved by systems that are inspired by text retrieval. A key component of these approaches is that local regions of images are characterized using high-dimensional descriptors which are then mapped to .visual words. selected from a discrete vocabulary. This paper explores techniques to map each visual region to a weighted set of words, allowing the inclusion of features which were lost in the quantization stage of previous systems. The set of visual words is obtained by selecting words based on proximity in descriptor space. We describe how this representation may be incorporated into a standard tf-idf architecture, and how spatial verification is modified in the case of this soft-assignment.

Název v anglickém jazyce

Lost in Quantization: Improving Particular Object Retrieval in Large Scale Image Databases

Popis výsledku anglicky

The state of the art in visual object retrieval from large databases is achieved by systems that are inspired by text retrieval. A key component of these approaches is that local regions of images are characterized using high-dimensional descriptors which are then mapped to .visual words. selected from a discrete vocabulary. This paper explores techniques to map each visual region to a weighted set of words, allowing the inclusion of features which were lost in the quantization stage of previous systems. The set of visual words is obtained by selecting words based on proximity in descriptor space. We describe how this representation may be incorporated into a standard tf-idf architecture, and how spatial verification is modified in the case of this soft-assignment.

Druh

D - Stať ve sborníku

CEP obor

JD - Využití počítačů, robotika a její aplikace

OECD FORD obor

—

Projekt

<a href="/cs/project/7E08031" target="_blank" >7E08031: Dynamic Interactive Perception-action Learning in Cognitive Systems</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2008

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

CVPR 2008: Proceedings of the 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition

ISBN

978-1-4244-2242-5

ISSN

1063-6919

e-ISSN

—

Počet stran výsledku

1

Strana od-do

—

Název nakladatele

Omnipress

Místo vydání

Medison

Místo konání akce

Anchorage, Alaska

Datum konání akce

24. 6. 2008

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000259736801124