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
Feb 20, 2015
MKLab participates in two new Horizon 2020 projects: STEP and KRISTINA, which are starting in spring 2015. STEP deals with developing a cloud eParticipation SaaS platform, enhanced with web/social media mining, gamification, machine translation, and visualisation features, which will promote the societal and political participation of young people in the decision-making process on environmental issues. KRISTINA aims at developing a human-like socially competent agent that serves for migrants with language and cultural barriers in the host country as a trusted information provision party and mediator in questions related to basic care and healthcare.
Jan 29, 2015
Find out more
Jan 03, 2015
The 2nd International Workshop on Environmental Multimedia Retrieval (EMR2015) is organized in conjunction with the ACM Conference on Multimedia Retrieval (ICMR) 2015, Shanghai, China, June 23-26, 2015. EMR 2015 welcomes original papers relevant (but not limited) to environmental multimedia indexing and retrieval, plant and animals identification, participatory and social environmental media analysis, discovery of environmental information in the web, content extraction from environmental multimedia and underwater scene understanding.
Dec 12, 2014
MKLab participated again this year in the annual TRECVID benchmarking activity, organized by the US National Institute for Standards and Technology (NIST). MKLab participated in four TRECVID tasks: Semantic Indexing (SIN), Event Detection in Internet Multimedia (MED), Multimedia Event Recounting (MER), and Instance Search (INS). Our results in these tasks were very good, significantly improving the results we had obtained in previous years.
Particularly for our participation in the Event Detection in Internet Multimedia (MED) task, we used a new, very fast machine learning method for big data problems, which we developed.
Dec 01, 2014
The paper "Brain source localization of MMN, P300 and N400: aging and gender differences" by A. Tsolaki, V. Kosmidou, L. Hadjileontiadis, I. Kompatsiaris and M. Tsolaki, has been accepted for publication in the Brain Research Journal, Elsevier (IF=2,828). This work has been supported by the ARISTEIA project CBP: Cognitive Brain signal Processing lab.
Nov 23, 2014
The paper "Fusion of meteorological and air quality data extracted from the web for personalized environmental information services" by L. Johansson, V. Epitropou, K. Karatzas, A. Karppinen, L. Wanner, S. Vrochidis, A. Bassoukos, J. Kukkonen, I. Kompatsiaris, has been accepted for publication in the Environmental Modelling & Software Journal, Elsevier (IF=4,538). This work has been supported by the FP7 project PESCaDO: Personalized Environmental Service Configuration and Delivery Orchestration.
Nov 20, 2014
A tutorial on “Video Hyperlinking” was delivered at two major scientific conferences, the IEEE Int. Conf. on Image Processing (ICIP; Paris, France, Oct. 2014) and the ACM Int. Conf. on Multimedia (ACMMM; Orlando, FL, USA, Nov. 2014), by Vasileios Mezaris (CERTH) and Benoit Huet (EURECOM). The slides of the tutorial, discussing various state of the art video analysis techniques (ranging from temporal video fragmentation to high-level description of the video’s content using concept and event labels) and their use towards video hyperlink generation, are available online, in three parts: - PartA: Motivation and Vision, http://www.
Sep 15, 2014
The paper on “Multi-entity bayesian networks for knowledge-driven analysis of ICH content” by Giannis Chantas, Alexandros Kitsikidis, Spiros Nikolopoulos, Kosmas Dimitropoulos, Stella Douka, Ioannis Kompatsiaris and Nikos Grammalidis received the Best Student Paper Award at the ECCV Workshop on Computer vision + ONTology Applied Cross-disciplinary Technologies, which was held in Zurich, Switzerland, in September 2014.
Sep 05, 2014
The Dem@Care Lab Ontology for Dementia Assessement has been integrated in the Linked Open Vocabularies (LOV) dataset, enabling its sharing and reuse by other datasets in the Linked Data Cloud (a human-readable description of the vocabulary is available here). The ontology has been developed in the framework of the Dem@Care project for representing the experimentation protocol towards diagnostic support and assessment of Dementia in a controlled environment. The aim of the protocol is to provide a brief overview of their health status of the participants during consultation (cognition, behaviours and function), and to correlate the system (sensor) data with the data collected using typical dementia care assessment tools.
Sep 01, 2014
A tribute article in the Pattern Recognition Letters on the late CERTH – ITI director Prof. Maria Petrou, describing her research and administration activities and achievements as director of CERTH-ITI.