Towards augmented database schemes by discovery of latent visual attributes

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F19%3A10396528" target="_blank" >RIV/00216208:11320/19:10396528 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.5441/002/edbt.2019.83" target="_blank" >https://doi.org/10.5441/002/edbt.2019.83</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.5441/002/edbt.2019.83" target="_blank" >10.5441/002/edbt.2019.83</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Towards augmented database schemes by discovery of latent visual attributes

Popis výsledku v původním jazyce

When searching for complex data entities, such as products in an e-shop, relational attributes are used as filters within structured queries. However, in many domains the visual appearance of an item is important for a user, while coverage of visual appearance by relational attributes is left to database designer at design time and is by nature an incomplete and imperfect representation of the entity. Recent advances in computer vision, dominated by deep convolutional neural networks (DCNNs), are a promising tool to cover the gaps. It has been shown that activations of neurons of DCNNs correspond to understandable visual-semantic features of an input image. We envision that activations of neurons are of great use for search queries in domains with strong visual information, even when obtained from DCNNs models pre-trained on general imagery. Locally scoped visual features obtained using them can be combined to form search masks which would correlate to what humans understand as an attribute, when applied on the entire dataset. Ultimately, combination of visual features can be identified automatically and formed into immediate suggestion of a new relational attribute, leaving one last task for humans to turn this into augmentation of the database schema - putting a label on it.

Název v anglickém jazyce

Towards augmented database schemes by discovery of latent visual attributes

Popis výsledku anglicky

When searching for complex data entities, such as products in an e-shop, relational attributes are used as filters within structured queries. However, in many domains the visual appearance of an item is important for a user, while coverage of visual appearance by relational attributes is left to database designer at design time and is by nature an incomplete and imperfect representation of the entity. Recent advances in computer vision, dominated by deep convolutional neural networks (DCNNs), are a promising tool to cover the gaps. It has been shown that activations of neurons of DCNNs correspond to understandable visual-semantic features of an input image. We envision that activations of neurons are of great use for search queries in domains with strong visual information, even when obtained from DCNNs models pre-trained on general imagery. Locally scoped visual features obtained using them can be combined to form search masks which would correlate to what humans understand as an attribute, when applied on the entire dataset. Ultimately, combination of visual features can be identified automatically and formed into immediate suggestion of a new relational attribute, leaving one last task for humans to turn this into augmentation of the database schema - putting a label on it.

Druh

D - Stať ve sborníku

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/GA17-22224S" target="_blank" >GA17-22224S: Analytika uživatelských preferencí v modelech multimediální explorace</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 statě ve sborníku

Advances in Database Technology — EDBT 2019 Proceedings of the 22nd International Conference on Extending Database Technology Lisbon, Portugal, March 26–29, 2019

ISBN

978-3-89318-081-3

ISSN

2367-2005

e-ISSN

—

Počet stran výsledku

4

Strana od-do

670-673

Název nakladatele

OpenProceedings

Místo vydání

Venice, Italy

Místo konání akce

Lisbon, Portugal

Datum konání akce

26. 3. 2019

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—