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

Invited speech at ICT Innovations 2011 conference

WeKnowIt related invited speech on "Extracting Emergent Semantics from Large-Scale User Generated Content" given by Yiannis Kompatsiaris at the ICT Innovations 2011 conference.

Call for Papers IEEE TRANSACTIONS ON MULTIMEDIA Special Issue on “Social Media as Sensors”

Summary and important dates

White paper on Search Computing: Bussiness areas, Research and socio-economic challenges

Y. Kompatsiaris and S. Nikolopoulos are the editors of the just published white paper on "Search Computing: Bussiness areas, Research and socio-economic challenges" that consolidates the expert's opinion about the future opportunities and trends in the search industry. The effort was coordinated by the CHORUS+ project, with the contribution of the Media Search Cluster network. The paper can accessed through http://www.avmediasearch.eu/white_paper_Search_computing.

Successful CERTH participation in the Social Event Detection task @ MediaEval 2011

CERTH-ITI successfully participated in the Social Event Detection task of the MediaEval 2011 workshop. MediaEval, a workshop focused on focused evaluation tasks with respect to multimedia analysis, took place in Pisa, Italy (1-2 September 2011). CERTH took part in the Social Event Detection (SED) task that involved two challenges: (a) detection of soccer events in two major European cities, (b) detection of events taking place in two specific venues. Both challenges were defined on a large set of about 75000 images from Flickr.

Multimedia, Broadcasting and eCulture

Read our chapter "Multimedia, Broadcasting and eCulture" in the new Handbook of Semantic Web Technologies

Knowledge-Driven Multimedia Information Extraction and Ontology Evolution - Bridging the Semantic Gap

  The book Knowledge-Driven Multimedia Information Extraction and Ontology Evolution - Bridging the Semantic Gap is now available. It covers the state of the art in the fields of ontology evolution and information extraction from multimedia, while  promoting the synergy between these two fields, by presenting a sound theoretical framework as well as concrete examples of applications. The contents stem largely from the research work conducted over a period of three years under the framework of the EU research project BOEMIE (Bootstrapping Ontology Evolution with Multimedia Information Extraction).

Version 2.0RC of 3D IVUS ANGIO Tool is released

VERSION 2.0RC with built-in 3D vessel reconstruction is released. New features:     - Create realistic 3D models from lumen and media-adventitia boundaries     - 3D model reconstruction takes less than a second to be created     - Follow catheter path feature. Just click the button and "take a tour" inside the vessel     - Simulating a virtual camera. See the actual IVUS frame while "inside" the 3D vessel     - Interactive.

ITI extracts concepts from patent images

Patent searchers are searching using concepts to retrieve patents of interest. In many cases the concepts are described by complex patent images. ITI proposes a supervised machine learning-based approach to extract concepts from patent images combining visual and textual information. Read more here.. The approach and the results are to be presented at the Image Retrieval session of the IRF Symposium 2011 at Vienna.

Survey article accepted in Data Mining and Knowledge Discovery journal

The article "Community Detection in Social Media" by Symeon Papadopoulos, Yiannis Kompatsiaris and Athena Vakali has been accepted for publication in the Data Mining and Knowledge Discovery journal (impact factor: 2.95).

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