Graph-based particular object discovery

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F19%3A00332224" target="_blank" >RIV/68407700:21230/19:00332224 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1007/s00138-019-01005-z" target="_blank" >https://doi.org/10.1007/s00138-019-01005-z</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/s00138-019-01005-z" target="_blank" >10.1007/s00138-019-01005-z</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Graph-based particular object discovery

Popis výsledku v původním jazyce

Severe background clutter is challenging in many computer vision tasks, including large-scale image retrieval. Global descriptors, which are popular due to their memory and search efficiency, are especially prone to corruption by such a clutter. Eliminating the impact of the clutter on the image descriptor increases the chance of retrieving relevant images and prevents topic drift due to actually retrieving the clutter in the case of query expansion. In this work, we propose a novel salient region detection method. It captures, in an unsupervised manner, patterns that are both discriminative and common in the dataset. Saliency is based on a centrality measure of a nearest neighbor graph constructed from regional CNN representations of dataset images. The proposed method exploits recent CNN architectures trained for object retrieval to construct the image representation from the salient regions. We improve particular object retrieval on challenging datasets containing small objects.

Název v anglickém jazyce

Graph-based particular object discovery

Popis výsledku anglicky

Severe background clutter is challenging in many computer vision tasks, including large-scale image retrieval. Global descriptors, which are popular due to their memory and search efficiency, are especially prone to corruption by such a clutter. Eliminating the impact of the clutter on the image descriptor increases the chance of retrieving relevant images and prevents topic drift due to actually retrieving the clutter in the case of query expansion. In this work, we propose a novel salient region detection method. It captures, in an unsupervised manner, patterns that are both discriminative and common in the dataset. Saliency is based on a centrality measure of a nearest neighbor graph constructed from regional CNN representations of dataset images. The proposed method exploits recent CNN architectures trained for object retrieval to construct the image representation from the salient regions. We improve particular object retrieval on challenging datasets containing small objects.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/EF16_019%2F0000765" target="_blank" >EF16_019/0000765: Výzkumné centrum informatiky</a><br>

Návaznosti

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

Rok uplatnění

2019

Kód důvěrnosti údajů

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

Název periodika

Machine Vision and Applications

ISSN

0932-8092

e-ISSN

1432-1769

Svazek periodika

30

Číslo periodika v rámci svazku

2

Stát vydavatele periodika

DE - Spolková republika Německo

Počet stran výsledku

12

Strana od-do

243-254

Kód UT WoS článku

000462151000005

EID výsledku v databázi Scopus

2-s2.0-85061245675