Vasileios Mezaris
Electrical and Computer Engineer, Ph.D.
| homepage | curriculum vitae | projects | research | demos | downloads | publications | contact | m r d b c p |
|
CURRENT RESEARCH PROJECTS | |
| 2023 - present | "AI4TRUST: AI-based-technologies for trustworthy solutions against disinformation", HORIZON EUROPE RIA, 2023-2026. (Principal Investigator) |
| Increasing evidence shows that disinformation spreading has non-negligible impact on our society at individual and collective levels. AI4TRUST will provide a hybrid system, where machines cooperate with humans, relying on advanced AI solutions against advanced disinformation techniques to support media professionals and policy makers. We expect that AI4TRUST's system, based on a human-centred approach to technology development that is aligned with European social and ethical values, will be integrated in the standard toolbox of data analysts working on disinformation. [Project Web site] |
| 2022 - present | "TransMIXR: Ignite the Immersive Media Sector by Enabling New Narrative Visions", HORIZON EUROPE IA, 2022-2025. (Principal Investigator) |
 
| EXtended Reality (XR) and Artificial Intelligence (AI) technologies provide a unique window of opportunity for the European Creative and Cultural Sector (CCS) to reimagine digital co-creation, interaction and engagement possibilities. TransMIXR combines the necessary interdisciplinary skillsets and domain expertise to create a range of human-centric tools for remote content production and consumption via social virtual reality. The TransMIXR platform will provide (i) a distributed XR Creation Environment that supports remote collaboration practices, and (ii) XR Media Experience Environment for the delivery and consumption of highly evocative and highly-social immersive media experiences. The ground-breaking AI techniques for the understanding and processing of complex media content will enable the reuse of heterogeneous assets across immersive content delivery platforms. [Project Web site] |
| 2022 - present | "vera.ai: Verification Assisted by Artificial Intelligence", HORIZON EUROPE RIA, 2022-2025. (Principal Investigator) |
| Online disinformation and fake media content have emerged as a serious threat to democracy, economy and society. Recent advances in AI have enabled the creation of highly realistic synthetic content and its artificial amplification through AI-powered bot networks. Consequently, it is extremely challenging for researchers and media professionals to assess the veracity/credibility of online content and to uncover the highly complex disinformation campaigns. vera.ai seeks to build professional trustworthy AI solutions against advanced disinformation techniques, co-created with and for media professionals & researchers and to also set the foundation for future research in the area of AI against disinformation. Key novel characteristics of the AI models will be fairness, transparency (incl. explainability), robustness against concept drifts, continuous adaptation and ability to handle multimodal and multilingual content. [Project Web site] |
| 2021 - present | "CRiTERIA: Comprehensive Data-driven Risk and Threat Assessment Methods for the Early and Reliable Identification, Validation and Analysis of migration-related Risks", H2020 RIA, 2021-2024. (Project's Research Manager & Principal Investigator) |
| EU borders are constantly faced with a multiplicity of challenges, from increased waves of illegal migration to human trafficking, document fraud, terrorism, smuggling, and public health threats. In the CRiTERIA project we will develop a novel risk analysis methodology, which will be backed by effective intelligent analysis technologies. Building upon state-of-the-art text, media, data and network analysis methods, we will develop and evaluate advanced analysis technologies and tools that are tailored to the new comprehensive threat indicators of the CRiTERIA methodology. In this process, ethical, legal and societal aspects will be considered from the very beginning, in close collaboration with practitioners from border agencies, which will also validate the developed technologies in piloting activities. [Project Web site] |
| 2020 - present | "AI4Media: A European Excellence Centre for Media, Society and Democracy", H2020 RIA, 2020-2024. |
| Motivated by the challenges, risks and opportunities that the wide use of AI brings to media, society and politics, AI4Media aspires to become a centre of excellence and a wide network of researchers across Europe and beyond, with a focus on delivering the next generation of core AI advances to serve the key sector of Media, to make sure that the European values of ethical and trustworthy AI are embedded in future AI deployments, and to reimagine AI. AI4Media will establish the networking infrastructure to bring together the European AI landscape in the field of media; will shape a research agenda for media AI research; and will implement research and innovation both with respect to cutting-edge technologies at the core of AI research, and within specific fields of media-related AI. [Project Web site] |
|
COMPLETED RESEARCH PROJECTS | |
| 2020 - 2023 | "QuaLiSID: Quality of Life Support System for People with Intellectual Disability", Greek national project, 2020-2023. (Principal Investigator) |
| People with intellectual disabilities encounter several problems regarding the interaction with their environment in terms of their daily needs, activities and communication. QuaLiSID will contribute to optimizing the opportunities provided to the people with intellectual impairment in order to cope with particular everyday issues, by developing an appropriate, fully functional, interactive support system. The integrated system will provide various stimuli, facilitate information, serve entertainment, creative activities and training through specialized learning programs, and, on the other hand, it will allow the recognition of emergency situations along with relevant notices towards the responsible care givers. [Project Web site] |
| 2019 - 2022 | "MIRROR: Migration-Related Risks caused by misconceptions of Opportunities and Requirement", H2020 RIA, 2019-2022. (Project's Research Manager & Principal Investigator) |
| The goal of the MIRROR project is to develop an integrated platform, a set of tools on top of this platform, as well as a systematic methodology for the comprehensive intermedia analysis of the perception of Europe (and individual countries in Europe), the detection of discrepancies between perception of and reality in Europe, and the creation of awareness for the impact of such misconceptions and potentially resulting threats. For achieving this goal the MIRROR project will bring together a highly interdisciplinary team of experts and three border authorities, and will combine methods of automated media analysis considering different types of media with empirical studies for creating a substantiated picture of the perception of Europe. [Project Web site] |
| 2018 - 2021 | "ReTV: Enhancing and Re-Purposing TV Content for TransVector Engagement", H2020 RIA, 2018-2021. (Principal Investigator) |
| ReTV will advance the state of the art in video analysis, video augmentation and annotation, content and audience metrics, prediction and recommendation models, and visual analytics. The results of this research will be tested and validated together with a regional public broadcaster, a national TV archive and an OTT TV distributor operating in multiple EU markets. ReTV will offer them a better match between content and viewers across vectors, time and different EU languages. Automated re-purposing and more accurate targeting in terms of relevance and appropriate representation, tailored to upcoming events and specific vector audiences, will drive growth, lower costs, and increase the competitiveness of broadcasters and other professional stakeholders in European media value chains. [Project Web site] |
| 2016 - 2019 | "MOVING: Training towards a society of data-savvy information professionals to enable open leadership innovation", H2020 RIA, 2016-2019. (Project's Coordinator & Principal Investigator) |
| MOVING is an innovative training platform that enables users from all societal sectors to fundamentally improve their information literacy by training how to use, choose, reflect and evaluate data mining methods in connection with their daily research tasks and to become data-savvy information professionals. The platform provides users with technical support as well as social advice and learning input to organise, filter and exploit information in a more efficient and sustainable way. Thus, it tackles the core challenges of the knowledge society: managing large amounts of information in a professional way, and training users to understand, use and develop data mining strategies. [Project Web site] |
| 2016 - 2018 | "InVID: In Video Veritas - Verification of Social Media Video Content for the News Industry", H2020 ICT IA, 2016-2018. (Project's Coordinator & Principal Investigator) |
| The digital media revolution is bringing breaking news to online video platforms; and, news organisations delivering information by Web streams and TV broadcast often rely on user-generated recordings of breaking and developing news events shared by social media to illustrate the story. However, in video there is also deception. Access to increasingly sophisticated editing and content management tools, and the ease in which fake information spreads in electronic networks requires reputable news outlets to carefully verify third-party content before publishing it. InVID will build a platform providing services to detect, authenticate and check the reliability and accuracy of newsworthy video files and video content spread via social media. [Project Web site] |
| 2017 - 2018 | "EMMA: Enriching market solutions for content management and publishing with state of the art multimedia analysis techniques", H2020 IA, 2017-2018. (Principal Investigator) |
| EMMA will transfer state-of-the-art technology in multimedia analysis from the labs to creative industry SMEs, more specifically to solution providers for the media management, branding, marketing and communication. This new technology will enhance existing commercial services, helping SMEs that are active in these sectors to solve current needs of their customers, and thus become more competitive in their market. EMMA focuses on two application areas, tourism and events, addressing the needs of destinations, and events to better drive, connect and engage with audiences. The impact in these vertical markets is huge, since both are among the key industries in Europe. [Project Web site] |
| 2013 - 2016 | "ForgetIT: Concise Preservation by combining Managed Forgetting and Contextualized Remembering", FP7 ICT IP, 2013-2016. (Project's Research Manager & Principal Investigator) |
| ForgetIT addresses current challenges in the area of multimedia preservation, in the personal and organizational context, by introducing three new concepts: i) Managed Forgetting, which is inspired by the important role of forgetting in human memory; ii) Synergetic Preservation, which crosses the chasm between active information use and preservation management; iii) Contextualized Remembering, which aims at keeping preserved content meaningful and useful along time. To achieve these goals, ForgetIT brings together a truly interdisciplinary team of experts. [Project Web site] |
| 2011 - 2015 | "LinkedTV: Television Linked To The Web", FP7 ICT IP, 2011-2015. (Principal Investigator) |
| TV and the Internet are going through an exciting phase of convergence, with TV being delivered on-demand via the Web while access to Web content is ever more a part of the TV experience. The LinkedTV project will bring this convergence to its fulfillment, neatly interweaving TV and Web content into a single, integrated experience. To achieve this ambitious goal, LinkedTV will develop several technologies and tools to analyze and annotate audio-visual content, interlink parts of the content with other content, deliver this enriched audio-visual content via different networks to the end user and provide intuitive user interfaces on the end device to allow easy access to and browsing of related content within the program. [Project Web site] |
| 2012 - 2014 | "MediaMixer: Community set-up and networking for the remixing of online media fragments", FP7 ICT CSA, 2012-2014. (Principal Investigator) |
| MediaMixer will set up and sustain a community of video producers, hosters and redistributors who will be supported in the adoption of semantic multimedia technology in order to build an European market for media fragment re-purposing and re-selling. It will demonstrate the achievable benefits enabled by the creation, repurposing and reuse of digital contents across borders on the Web, where media fragments are intelligent digital objects, identified and classified at a highly granular degree, integrated with knowledge management, and connected at Web-scale. [Project Web site] |
| 2009 - 2012 | "GLOCAL: Event-based Retrieval of Networked Media", FP7 ICT IP, 2009-2012. (Principal Investigator) |
| The key idea underlying GLOCAL is to use events as the primary means to organize and index media, e.g., photos, videos, journal articles. Instead of starting from media and seeing, a posteriori, how we can meaningfully understand their contents (e.g., by tagging them), we organize a priori our data and knowledge in terms of events and use media to populate them, thus providing their experiential dimension. Events provide the common framework inside which the local experience-driven contextual information can be not only coded, but also shared and reduced to a common denominator. |
| 2007 - 2010 | "Vidi-video: Interactive semantic video search with a large thesaurus of machine-learned audio-visual concepts", FP6 IST STREP, 2007-2010. |
| The VIDI-Video project aims to integrate and develop state of the art components from machine learning, audio event detection, video processing, interaction and visualization into a fully implemented audio-visual search engine combining large number of categories and exploiting the interclass similarities as well as using the information from different sources: metadata, keyword annotations, audio visual data, speech, and explicit knowledge. |
| 2007 - 2008 | "K-Space: Knowledge Space of Semantic Inference for Automatic Annotation and Retrieval of Multimedia Content", FP6 IST NoE, 2006-2008. |
| 2006 - 2009 | "MESH: Multimedia Semantic Syndication for Enhanced News Services", FP6 IST IP, 2006-2009. |
| 2006 - 2008 | "DELTIO: Analysis of Multimedia Content using Evolutionary Ontologies and Application to Television News Bulletins", GSRT 2006-2008. |
| 2006 - 2008 | "COST292: Semantic Multimodal Analysis of Digital Media", European Cooperation in the Field of Scientific and Technical Research, 2004-2008. |
| 2005 - 2007 | "Knowledge-assisted analysis of medical image and video for doctor decision support applications", GSRT, Slovenia - Greece, 2005-2007. |
| 2004 - 2006 | "aceMedia: Integrating knowledge, semantics and content for user centred intelligent media services", FP6 IST IP, 2004-2007. |
| 2004 - 2006 | "CIRCE: Content-Based and Semantic Multimedia Indexing and Retrieval in Collaborative Environments", GSRT, Hungary - Greece, 2004-2006. |
| 2003 - 2004 | "COST 276: Information and Knowledge Management for Integrated Media Communication", 2001-2005. |
| 2002 - 2005 | "SCHEMA: Network of Excellence in Content-Based Semantic Scene Analysis and Information Retrieval", DG XIII, IST, 2002-2005. |
| 2001 - 2002 | "COST 211 quat: Coding of video signals in multimedia services", 1998-2002. |
| 2001 | "ISTORAMA: Content-Based Image Search over the Internet", GSRT-PAVET, 1999-2001. |