Skip to Content

CBMI 2015

Date: 
10.06.2015

13th International Workshop on Content-Based Multimedia Indexing (CBMI)

http://siret.ms.mff.cuni.cz/cbmi2015/

Evaluating Multilayer Multimedia Exploration

Authors: 
J. Moško, J. Lokoč, T. Grošup, P. Čech, T. Skopal, J. Lánský
Indexed by WOS: 
Indexed by WOS
Indexed by SCOPUS: 
Indexed by SCOPUS
Type: 
Proceedings
State: 
Published
Language: 
EN
Conference/Journal name: 
SISAP
Publisher: 
Springer
Year: 
2015
Pages: 
162-169
Location: 
Glasgow, Scotland, UK
ISBN: 
978-3-319-25087-8
ISSN: 
0302-9743

MLES: Multilayer Exploration Structure for Multimedia Exploration

Authors: 
J. Moško, J. Lokoč, T. Grošup, P. Čech, T. Skopal, J. Lánský
Indexed by WOS: 
Indexed by WOS
Indexed by SCOPUS: 
Indexed by SCOPUS
Type: 
Proceedings
State: 
Published
Language: 
EN
Conference/Journal name: 
ADBIS - Advances in Databases and Information Systems
Publisher: 
Springer International Publishing
Year: 
2015
Volume: 
539
Pages: 
135-144
Location: 
Poitiers, France
ISBN: 
978-3-319-23200-3

What Are The Salient Keyframes In Short Casual Videos? An Extensive User Study Using A New Video Dataset

Authors: 
J. Lokoč, B. Münzer, K. Schoeffmann, M. Del Fabro, M. J. Primus, T. Skopal, J. Lánský
Indexed by WOS: 
Not indexed by WOS
Indexed by SCOPUS: 
Not indexed by SCOPUS
Type: 
Proceedings
State: 
Accepted
Language: 
EN
Conference/Journal name: 
International Workshop on Mobile Multimedia Computing
Publisher: 
IEEE
Year: 
2015

Find the image

Type: 
Multimedia
One line description: 
Online tool for comparisons of different multimedia exploration approaches
Annotation: 

Find the image is an artificial search scenario designed for testing and comparison of our exploration techniques. The task is to use a web-based exploration application to find as much images from a predetermined class as possible. This predetermined class should correspond to a search intention that cannot be easily transformed to a text-based query or to a query-by-example.

Developers: 
jakub.lokoc
juraj.mosko
premek.cech
tomas.grosup

Find the image is an artificial search scenario designed for testing and comparison of our exploration techniques. The task is to use a web-based exploration application to find as much images from a predetermined class as possible. This predetermined class should correspond to a search intention that cannot be easily transformed to a text-based query or to a query-by-example.

Exploration Portal

Type: 
Multimedia
One line description: 
Image exploration demo
Annotation: 

Exploration portal is a demonstration application for Multimedia exploration framework and a logical successor of SIR. The portal uses all framework features and implements example use cases for all important framework parts.

The portal can be used for exploration of static data sets, Bing search results and personal Facebook albums. It provides a variety of configuration options to affect feature extraction, similarity model, index creation and many other parameters.

The result is visualized using a similarity-based layout and supports different query options, such as zoom-in, zoom-out, multi-query or panning in 4 different directions.

Developers: 
jakub.lokoc
juraj.mosko
premek.cech
tomas.grosup

Exploration portal is a demonstration application for Multimedia exploration framework and a logical successor of SIR. The portal uses all framework features and implements example use cases for all important framework parts.

Multimedia exploration framework

Type: 
Multimedia
One line description: 
Creation of efficient multimedia exploration applications
Annotation: 

Multimedia exploration framework is an extensible solution for creation of multimedia exploration applications.

It uses a modular architecture and already provides several implementantions for every component. Besides managing the software architecture and data flow, the framework also takes care of data source management, data retrieval, feature extraction, distance computation, metric indexing, query execution, data visiualization and GUI creation.

Contact the developers directly if you are interested in building an application using our framework.

Developers: 
jakub.lokoc
premek.cech
tomas.grosup
tomas.skopal

Multimedia exploration framework is an extensible solution for creation of multimedia exploration applications.

It uses a modular architecture and already provides several implementantions for every component. Besides managing the software architecture and data flow, the framework also takes care of data source management, data retrieval, feature extraction, distance computation, metric indexing, query execution, data visiualization and GUI creation.

Contact the developers directly if you are interested in building an application using our framework.

Using Neo4j for mining protein graphs: a case study

Authors: 
David Hoksza, Jan Jelínek
Indexed by WOS: 
Not indexed by WOS
Indexed by SCOPUS: 
Indexed by SCOPUS
Type: 
Proceedings
State: 
Accepted
Language: 
EN
Conference/Journal name: 
NoSQL-Net - International Workshop on NoSQL Databases, Emerging Database Technologies and Applications, DEXA
Publisher: 
IEEE
Year: 
2015
Pages: 
230-235
Location: 
Valencia, Spain
ISBN: 
978-1-4799-5722-4

Efficient Extraction of Clustering-Based Feature Signatures Using GPU Architectures

Authors: 
M. Kruliš, J. Lokoč, T. Skopal
Indexed by WOS: 
Indexed by WOS
Indexed by SCOPUS: 
Indexed by SCOPUS
Type: 
Journal
State: 
Accepted
Language: 
EN
Conference/Journal name: 
Multimedia tools and applications
Publisher: 
Springer
Year: 
2016
Volume: 
75
Issue: 
13
Pages: 
8071–8103
ISSN: 
1380-7501

Neo4j database of proteins for protein-protein interaction identification

THE NEW VERSION OF THIS PAGE AFTER THE DATA LOSS

This page contains updated version of the data described in  the paper "Using Neo4j for mining protein graphs: a case study". Sadly, the original data were lost due to a hack of our systems and therefore we recreated them in August 2019. However since the underlying data in the PDB has changed, our DB is marginally different from the one based on which the results in the paper are reported.

Syndicate content