Sven Helmer 
University of Zurich, Switzerland

​

Show, Don't Tell - Retrieving Information via Gestures

​

Abstract: Currently, many information retrieval systems utilize a textual interface for users to express their information needs. While this works perfectly well for searching text document collections, there are domains in which textualizing a query or context is much harder. Among these are domains involving cultural practices, such as the performing arts or traditional crafts. Here we need to capture and represent intangible assets, such as human motion, gestures, or facial expressions. We report on our work in the areas of preserving cultural heritage, making accessible museum collections, and visualizing dance choreography, illustrating some of the challenges and potential solutions.

 

Bio: Sven Helmer is a (titular) professor in the Department of Informatics at the University of Zurich, Switzerland, after holding positions as Associate Professor in the Faculty of Computer Science at the Free University of Bozen-Bolzano, Italy, and as Senior Lecturer at Birkbeck, University of London, United Kingdom. He acquired a PhD from the University of Mannheim, Germany, an MSc in Computer Science from the University of Karlsruhe, Germany, and also spent some time as a visiting professor at the University of Heidelberg. He has taught and is teaching courses on data science, databases, and information security; his research interests include database systems, Raspberry Pis, time series, and graph data management, as well as interdisciplinary research in the areas of information systems and ethnography. He has published close to 120 peer-reviewed papers and book chapters.

​

​

Gianfranco Messina
Hitachi Rail, Italy

​

What’s Next in Smart Factory: the Digital Transformation Journey in Hitachi Rail​

​

Abstract: TBA

Bio:

Gianfranco Messina is a professional with over 20 years of experience in strategic problem-solving, leadership, and project management within the realms of Digital Transformation and Digital Innovation. His career has been marked by the development of numerous successful projects that have significantly enhanced operational efficiency and reduced costs, leveraging digital transformation technologies such as IT, OT, IoT, and, in particular, AI/GenAI. His professional path has led him through various roles in multinational companies including Leonardo (formerly Finmeccanica), Boeing, Italcementi, and Hitachi, where he has managed complex innovation projects across the globe. His primary objective has always been to drive innovation, reduce costs, and improve processes, ensuring that each phase of the company's value chain, from design to procurement and manufacturing, operates at its highest potential.

​

In particular, Gianfranco has led advanced digital transformation and optimization projects at Hitachi Rail, including the Italian Lighthouse Industry 4.0 project, applying the most innovative AI and Industry 4.0 in all Italian Factories. He has also directed a global project for applying AI in operational business processes, achieving significant cost savings and improvements in operational efficiency. His leadership in digital transformation has led to investments of multi-million dollars in global digitalization projects, promoting operational efficiency in business processes through solutions such as Smart Factory, Supply Chain Control Tower, Predictive Maintenance and Quality, Manufacturing Operations Management, and Digital Twin.

​

Recently, Gianfranco has led the design and creation of an advanced digital and Green factory in the United States, a flagship project that integrated cutting-edge technologies to improve production efficiency, quality, safety and reduce operational costs. This project represented a significant step forward in the adoption of all digital technologies and set new standards for digital manufacturing operations.

Additionally, he has recently led a global project for knowledge management and lessons learned using Generative AI tools. This project has enabled the efficient capture, organization, and sharing of corporate knowledge, enhancing the organization's ability to learn from past experiences and apply these lessons to optimize future processes.

​

​

Vincenzo Moscato 
University of Naples Federico II, Italy

 

Visual Language Models in Medicine: Opportunities, Challenges, and Emerging Research Directions

​

Abstract: The advent of Visual Language Models (VLMs) -- AI systems capable of jointly processing medical images and natural language -- provides new opportunities in clinical practice and biomedical research. These multimodal models are increasingly being applied to tasks such as automated image interpretation, radiology report generation, clinical decision support, offering promising avenues for improving diagnostic accuracy, workflow efficiency, and healthcare accessibility. This keynote will provide a comprehensive overview of: i) current applications of VLMs in some medical domains; ii) open challenges, such as performances with respect to Computer Vision/Deep Learning aided systems, model interpretability, clinical validation, regulatory compliance, and integration into real-world healthcare systems; iii) emerging research directions, including model fine-tuning, domain-specific foundation models and multimodal prompt engineering Eventually, the talk will conclude with a forward-looking perspective on how VLMs may evolve to become trustworthy, transparent, and clinically robust tools, fostering a new paradigm of AI-augmented medicine.

 

Bio:

Vincenzo Moscato is a Full Professor at the Electrical Engineering and Information Technology Department of University of Naples Federico II, where he is the owner of Database Systems and Big Data Engineering teachings for the bachelor and master’s degree programs in Computer Engineering, respectively. Currently, he is one of the leaders of PICUS (Pattern and Intelligence Computation for mUltimedia Systems) departmental research group and his research activities lay in the area of Big Multimedia Data Analytics, Artificial Intelligence and Social Network Analysis. In addition, He is the Director of CINI (Consorzio Interuniversitario Nazionale per l'Informatica) ITEM Research Lab, where he carries out several research activities on Intelligent Multimedia Systems.

​

He managed as Principal Investigator several national and international projects and he won various awards for his research, including one granted by Oracle for the “Knowledge graphs for next-generation health science applications” project). He was in the Program Committee (PC) of a plethora of international and top-ranked conferences and served as reviewer of numerous international journals, including some of the most important journals concerning Multimedia, Knowledge and Data Engineering and Artificial Intelligence topics. He is in the editorial boards of several international journals (such as Expert Systems with Applications , Journal of Intelligent Information Systems and IEEE Trans. On Neural Networks and Learning Systems) and has managed as Guest Editor different Special Issues for a lot of journals. Finally, he was an author of about 250 publications in international journals, conference proceedings and book chapters. About 100 of such publications are available on top-ranked journals (Q1 and Q2 from SCIMAGO ranking) or included in Proceedings of top-ranked conferences (A++, A+, A). In particular, the paper published in IEEE Intelligent Systems "An Emotional Recommender System for Music" was awarded the runner up for best paper award related to 2021 by the IEEE Computer Society (https://www.computer.org/publications/best-paper-award-winners.

​

 

​

​

​