Deep Shape Matching
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F18%3A00325476" target="_blank" >RIV/68407700:21230/18:00325476 - isvavai.cz</a>
Result on the web
<a href="http://cmp.felk.cvut.cz/~radenfil/publications/Radenovic-ECCV18.pdf" target="_blank" >http://cmp.felk.cvut.cz/~radenfil/publications/Radenovic-ECCV18.pdf</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-030-01228-1_46" target="_blank" >10.1007/978-3-030-01228-1_46</a>
Alternative languages
Result language
angličtina
Original language name
Deep Shape Matching
Original language description
We cast shape matching as metric learning with convolutional networks. We break the end-to-end process of image representation into two parts. Firstly, well established efficient methods are chosen to turn the images into edge maps. Secondly, the network is trained with edge maps of landmark images, which are automatically obtained by a structure-from-motion pipeline. The learned representation is evaluated on a range of different tasks, providing improvements on challenging cases of domain generalization, generic sketch-based image retrieval or its fine-grained counterpart. In contrast to other methods that learn a different model per task, object category, or domain, we use the same network throughout all our experiments, achieving state-of-the-art results in multiple 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)
Others
Publication year
2018
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
ECCV2018: Proceedings of the European Conference on Computer Vision, Part V
ISBN
978-3-030-01227-4
ISSN
0302-9743
e-ISSN
—
Number of pages
18
Pages from-to
774-791
Publisher name
Springer, Cham
Place of publication
—
Event location
Munich
Event date
Sep 8, 2018
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—