Multiple-Kernel Local-Patch Descriptor
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F17%3A00312614" target="_blank" >RIV/68407700:21230/17:00312614 - isvavai.cz</a>
Result on the web
<a href="http://cmp.felk.cvut.cz/~chum/papers/Mukundan-BMVC17.pdf" target="_blank" >http://cmp.felk.cvut.cz/~chum/papers/Mukundan-BMVC17.pdf</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.5244/C.31.184" target="_blank" >10.5244/C.31.184</a>
Alternative languages
Result language
angličtina
Original language name
Multiple-Kernel Local-Patch Descriptor
Original language description
We propose a multiple-kernel local-patch descriptor based on efficient match kernels of patch gradients. It combines two parametrizations of gradient position and direction, each parametrization provides robustness to a different type of patch miss-registration: polar parametrization for noise in the patch dominant orientation detection, Cartesian for imprecise location of the feature point. Even though handcrafted, the proposed method consistently outperforms the state-of-the-art methods on two local patch benchmarks.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
<a href="/en/project/LL1303" target="_blank" >LL1303: Large Scale Category Retrieval</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach
Others
Publication year
2017
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
28th British Machine Vision Conference 2017 Proceedings
ISBN
978-1-901725-60-5
ISSN
—
e-ISSN
—
Number of pages
11
Pages from-to
—
Publisher name
British Machine Vision Association
Place of publication
—
Event location
London
Event date
Sep 4, 2017
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—