Dr. Yiannis (Ioannis) Kompatsiaris, Senior Researcher
Yiannis Kompatsiaris received the Diploma degree in electrical engineering and the Ph.D. degree in 3-D model based image sequence coding from Aristotle University of Thessaloniki (AUTH), Thessaloniki, Greece in 1996 and 2001, respectively. He is a Senior Researcher with the Informatics and Telematics Institute, Thessaloniki.Prior to his current position, he was a Leading Researcher on 2-D and 3-D Imaging at AUTH.
His research interests include multimedia content processing, multimodal techniques, multimedia and the Semantic Web, multimedia analysis and annotation ontologies, knowledge-based, context aware inference for semantic multimedia analysis, semantic metadata representation, semantic adaptation, personalization and retrieval, MPEG-4 and MPEG-7 standards.
News:
WeKnowIt presentation in CIVR 2010 Practitioner's Day
WeKnowIt was presented at the CIVR 2010 Practicioner's Day event on July 7th, 2010, in Xi'an, China. Yiannis Kompatsiaris gave a presentation entitled "WeKnowIt: Making the Collective Intelligence of Social Media Searchable" (pdf).
ICMR - International Conference on Multimedia Retrieval
2012: 2nd International Conference on Multimedia Retrieval - Call for Organizers
PatMedia Exhibition and Evaluation in IRFS 2010
The PatMedia image retrieval engine was presented and demonstrated in the Exhibition of the IRF Symposium 2010 in Vienna. PatMedia was also one of the main discussion topics in the Image Retrieval Session of the Symposium. During this session, the patent image search engine developed by ITI, was evaluated by professional patent searchers, who discussed their findings and concluded that the functionalities of PatMedia would be of added value in their search tasks. The presentations are available here..
"e-Report" idea presented at opengov.gr meeting
The "e-Report" idea, based on WeKnowIt technologies, was presented at the 2nd labs.opengov.gr meeting (in Greek). It promotes citizens participation and contribution combined with large-scale content analysis and structuring for efficient addressing local and environmental problems.
ER Log Merging and Management tool available
http://mklab.iti.gr:8080/LogMergerDemo
Managing and reviewing the log files that are created by the Emergency Response (ER) personnel in the course of an emergency incident is a critical task for understanding and improving the implemented ER actions.
ClustTour City Exploration tool available
ClustTour is an online city exploration application that helps users identify interesting spots in a city by use of photo clusters corresponding to landmarks and events.
Βραβείο καλύτερης εργασίας / Best paper award
Η εργασία με τίτλο "Εφαρμογή Αυτοματοποιημένης Τρισδιάστατης Ανασύνθεσης Στεφανιαίων Αρτηριών στην Ανίχνευση Ευάλωτων Αθηρωματικών Πλακών" έλαβε το βραβείο καλύτερης εργασίας στο 30ο Πανελλήνιο Καρδιολογικό Συνέδριο, 29-31 Οκτωβρίου 2009, Αθήνα.
The paper entitled "Application of Automated 3D reconstruction of Coronary Arteries in the Detection of Vulnerable Atheromatic Plaques" received the Best Paper award in the 30th Panhellenic Cardiological Congress, 29-31 October 2009, Athens, Greece.
Cooperation with SBOING™
SBOING™ and Informatics and Telematics Institute (ITI) of the Research and Technology-Hellas have agreed to investigate the development and evaluation of technologies for statistical analysis of large-scale navigation and tourism related data.
Patent Database
This dataset contains 2000 patent images extracted from patent documents provided by the European Patent Office (EPO). This dataset was manually classified into different categories in order to perform evaluation experiments in the context of the EU project PATExpert.
Download the patent image database here. The settings of the PATExpert experiments are available here.
The Challenge of Searching Non-Textual Information in Patents
A system for the semantic multi-modal analysis of news audio-visual content
A new journal publication, jointly authored by members of CERTH, DFKI and the University of Twente, was recently accepted for publication:
V. Mezaris, S. Gidaros, G. Th. Papadopoulos, W. Kasper, J. Steffen, R. Ordelman, M. Huijbregts, F. de Jong, I. Kompatsiaris, M. G. Strintzis, "A system for the semantic multi-modal analysis of news audio-visual content", EURASIP Journal on Advances in Signal Processing, accepted for publication, 2010.
Video Image Annotation Tool (VIA) goes Open Source!
CERTH-ITI recently released its VIA annotation tool as open source under the GPL license.
You can check it out on SourceForge.
Video Image Annotation Tool (VIA) is a windows application to manually annotate video and images. It provides a user friendly interface for the accurate and undemanding live and "frame by frame" annotation of video and and region-based annotation of still images integrating results from a segmentation algorithm.
The development of this tool has been supported by the Bootstrapping Ontology Evolution with Multimedia Information Extraction (BOEMIE)(FP6-027538) and aceMedia(FP6-001765) projects.
The source code is available at the project's SVN repository page on SouceForge:
https://sourceforge.net/scm/?type=svn&group_id=303977




