Efficient Contour Match Kernel
Identifikátory výsledku
Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F18%3A00321788" target="_blank" >RIV/68407700:21230/18:00321788 - isvavai.cz</a>
Výsledek na webu
<a href="https://www.sciencedirect.com/science/article/pii/S0262885618300647?via%3Dihub" target="_blank" >https://www.sciencedirect.com/science/article/pii/S0262885618300647?via%3Dihub</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1016/j.imavis.2018.04.006" target="_blank" >10.1016/j.imavis.2018.04.006</a>
Alternativní jazyky
Jazyk výsledku
angličtina
Název v původním jazyce
Efficient Contour Match Kernel
Popis výsledku v původním jazyce
We propose a novel concept of asymmetric feature maps (AFM), which allows to evaluate multiple kernels between a query and database entries without increasing the memory requirements. To demonstrate the advantages of the AFM method, we derive an efficient contour match kernel – short vector image representation that, due to asymmetric feature maps, supports efficient scale and translation invariant sketch-based image retrieval. Unlike most of the short-code based retrieval systems, the proposed method provides the query localization in the retrieved image. The efficiency of the search is boosted by approximating a 2D translation search via trigonometric polynomial of scores by 1D projections. The projections are a special case of AFM. An order of magnitude speed-up is achieved compared to traditional trigonometric polynomials. The results are boosted by an image-based average query expansion approach and, without any learning, significantly outperform the state-of-the-art hand-crafted descriptors on standard benchmarks. Our method competes well with recent CNN-based approaches that require large amounts of labeled sketches, images and sketch-image pairs.
Název v anglickém jazyce
Efficient Contour Match Kernel
Popis výsledku anglicky
We propose a novel concept of asymmetric feature maps (AFM), which allows to evaluate multiple kernels between a query and database entries without increasing the memory requirements. To demonstrate the advantages of the AFM method, we derive an efficient contour match kernel – short vector image representation that, due to asymmetric feature maps, supports efficient scale and translation invariant sketch-based image retrieval. Unlike most of the short-code based retrieval systems, the proposed method provides the query localization in the retrieved image. The efficiency of the search is boosted by approximating a 2D translation search via trigonometric polynomial of scores by 1D projections. The projections are a special case of AFM. An order of magnitude speed-up is achieved compared to traditional trigonometric polynomials. The results are boosted by an image-based average query expansion approach and, without any learning, significantly outperform the state-of-the-art hand-crafted descriptors on standard benchmarks. Our method competes well with recent CNN-based approaches that require large amounts of labeled sketches, images and sketch-image pairs.
Klasifikace
Druh
J<sub>imp</sub> - 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)
Návaznosti výsledku
Projekt
<a href="/cs/project/LL1303" target="_blank" >LL1303: Vyhledávání vizuálních kategorií ve velkém množství obrázků</a><br>
Návaznosti
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Ostatní
Rok uplatnění
2018
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Údaje specifické pro druh výsledku
Název periodika
Image and Vision Computing
ISSN
0262-8856
e-ISSN
1872-8138
Svazek periodika
76
Číslo periodika v rámci svazku
August
Stát vydavatele periodika
GB - Spojené království Velké Británie a Severního Irska
Počet stran výsledku
13
Strana od-do
14-26
Kód UT WoS článku
000442333500002
EID výsledku v databázi Scopus
2-s2.0-85048097333