The Lab has extensive experience and expertise in semantic multimedia analysis, indexing and retrieval, social media and big data analytics, knowledge structures, reasoning and personalization for multimedia applications, eHealth and environmental applications

MKLab researchers achieve first position in image forensics contest!

Researchers from MKLab are the winners of the first task of the Find-it! Fraud Detection Contest! The contest task called for approaches to detect documents containing at least one forgery in a flow of documents. The documents contained in the task dataset comprise 1969 scans of receipts. The MKLab researchers set up a system based on image steganographic features, a bag of SVM classifiers and class-rebalancing during training. Using the training set provided by the organizers, this system managed to detect all forged documents without any error, achieving an F-score of 1.

V4Design - New project to support architects and VR game designers!

MKLab coordinates the H2020 project V4Design website, started in January 1st, 2018. V4Design aims at reusing and repurposing visual and textual content for inspiring architecture and virtual reality game (VR) designing. Visual content analysis is performed through 3D reconstruction and modelling, localization of objects in visual data, automated extraction of aesthetics/style information and language understanding from visual and textual data. 3D objects are also enhanced with semantics and explanatory text descriptions.

H2020 – EOPEN launches a new website!

The H2020 project EOPEN, started in November 1st, 2017 aims at developing an open interoperable platform for unified access and analysis of earth observation data. EOPEN will provide a platform targeting non-expert Earth Observation (EO) data users (non-traditional user communities), experts and the SME community that reveals and makes Copernicus data and services easy to use for Big Data applications by providing EO data analytics services, decision making and infrastructure to support the Big Data processing life-cycle allowing the chaining of value adding activities across multiple platforms.

SUITCEYES project to assist the deafblind

MKLab proudly participates in SUITCEYES, a new exciting project aimed at creating a smart garment that can act as a communicative interface for deafblind people, which will begin in early 2018. The deafblind are a group in society dependent on other people, such as family members or assistants to sense the world. Now, researchers in the EU project SUITCEYES will develop a prototype made from smart textiles to provide the deafblind with new communication opportunities.

Press Article for ROBORDER project in Greece

A press article about ROBORDER is published in the Έθνος newspaper (in Greek). The article is accessible here (A, B). The article describes the objectives of ROBORDER project focusing on developing a swarm of autonomous and heterogeneous robots for border surveillance and its application impact in Greece and Europe.

Assistive Technology for the Elderly behind a Vast Change

As scientists, we are used to evaluating and presenting our results with numbers, tables and graphs. What we all tend to forget is that research in the bigger picture is about improving people's lives and has direct impact to our society. Therefore, we were more than glad when such a prominent example appeared. One participant in our research project in assistive technology for the elderly, presented such a vast change that, she, much to our surprise, appeared on the popular TV show “Greece Got Talent”, on a major Greek TV network.

Best Poster Award @ ACM ICMR 2017

The paper “Concept Language Models and Event-based Concept Number Selection for Zero-example Event Detection”, by D. Galanopoulos, F. Markatopoulou, V. Mezaris, and I. Patras, received the Best Poster Award at the ACM International Conference on Multimedia Retrieval (ICMR 2017) that took place in Bucharest, Romania.

MKLab will present their work on Learning to Detect Misleading Content on Twitter and YouTube to ICMR 2017

MKLab have been working for some time now on the problems of fake news and of misinformation in social media. Our work has recently led to some important achievements: we developed a very effective machine learning-based algorithm for automatically deciding whether a tweet is credible, i.e. whether it accurately reflects the event to which it refers. Training this algorithm became possible by creating a large corpus of past tweets that have been annotated as “fake” or “real”.

MKLab Published its First MOOC on Udemy

MKLab proudly announces the release of its "Dynamics of Knowledge Organisation" MOOC on Udemy. Featuring more than 2 hours of recorded video content, the course studies the involvement and application of semantics in Digital Preservation and has been produced within the context of the PERICLES FP7 project. The MOOC is taught by Prof. Sándor Darányi (School of Library and Information Science, University of Borås) and Dr. Efstratios Kontopoulos (MKLab, CERTH/ITI), and is supported by Mr. Panagiotis Mitzias (MKLab, CERTH/ITI).

Release of concept detection scores for IACC.3

We provide a complete set of concept detection scores, using our state of the art concept detectors, for the videos of the IACC.3 dataset that is used in the TRECVID AVS Task from 2016 and on (600 hr of internet archive videos). Concept detection scores for 1345 concepts (1000 ImageNet concepts and 345 TRECVID SIN concepts) have been generated using two different automatic video annotation methods. The dataset and the related publications can be found at: https://www.

BDV associate member

Improve My City Mobile

imc logo

Improve My City Mobile, allows citizens to report local problems and suggest solutions for improving their neighbourhood. Learn more...

Motorola collaborations

Motorola Logo

The Multimedia Group has been collaborating with Motorola in several Motorola funded R&D projects.

GPU-LIBSVM

NVIDIA links Multimedia Group for the GPU-LIBSVM implementation

HR Excellence in Research

HR Excellence in Research