32nd International Conference on Multimedia Modeling

Jiri Matas is the head of the Visual Recognition Group at the Center for Machine Perception, Department of Cybernetics, Czech Technical University in Prague. He holds a PhD degree from the University of Surrey, UK (1995). He has published more than 300 papers that have been cited about 74000 in Google Scholar (h-index = 99). He received the best paper prize at the British Machine Vision Conference in 2002, 2005 and 2022, at the Asian Conference on Computer Vision in 2007 and at Int. Conf. on Document analysis and Recognition in 2015. J. Matas served as a programme or general chair at ECCV 2004, 2016, 2022 and CVPR 2007 and 2022. He is an Editor-in-Chief of the International Journal of Computer Vision was an Associate Editor-in-Chief of IEEE T. Pattern Analysis and Machine Intelligence. He is on the computer science panel of the ERC.
His research interests include visual tracking, object recognition, image matching and retrieval, sequential pattern recognition, and RANSAC-type optimization metods. He has co-founded two companies, Eyedea Recognition (computer vision) and Locksley (combinatorial optimization).

Marcel Worring: Multimedia Analytics in the Foundation Model Era

Abstract: Multimedia Analytics was introduced in 2010 by Chinchor et.al. as the combination of multimedia analysis and visual analytics. In 2014 Zahalka et.al. developed a model for Multimedia Analytics, while at the same time Sacha et.al. developed a visual analytics model connecting interactive processes with human cognition. Up to recently, these two fields have developed more or less is parallel. Foundation models have changed the playing field completely. They combine multimedia analysis with reasoning and generation capabilities. Still for a lot of tasks, humans outperform AI and Human-AI teaming is the best way forward. Yet, the main communication channel between humans and AI is via a textual prompt. Clearly Visual Analytics could yield significant improvements here. In this talk, we will consider the historical developments in multimedia analysis and visual analytics and present a new multimedia / visual analytics model suited for the foundation model era. We show the value of the model by taking a number of existing systems as case studies and use the model to describe them and suggest improvements based on the model characteristics.

Bio: Marcel Worring is a full professor in the Informatics Institute of the University of Amsterdam. He is leading the MultiX group which is doing research on multimedia analytics techniques for getting the richest information possible from the data through AI algorithms, interactions, and interfaces; surpassing human and machine intelligence for applications and social impact in public health, forensics and law enforcement, cultural heritage, and data-driven business. He has been associate editor of ACM TOMCCAP, IEEE Transactions on Multimedia, and IEEE Multimedia, and organized ACM Multimedia 2016, MMM2024, and will organize ICMR2026. He is a fellow of ELLIS, the European Laboratory for Learning and Intelligent Systems, and co-founder of the Innovation Center for Artificial Intelligence.

Giuseppe Amato: Synergy between Extended Reality and Artificial Intelligence

Abstract: Extended Reality (XR) builds on Augmented Reality (AR) and Mixed Reality (MR), which themselves extend the foundations of Virtual Reality (VR). VR immerses users in fully digital environments through headsets, smart devices, or computer screens, but it isolates them from the physical world. AR and MR, instead, overlay digital content onto the real environment. Virtual objects are aligned, fused, and synchronized with physical surroundings, and in MR users can interact with both physical and virtual elements in a unified space.

XR goes even further. It is not limited to visual augmentation; it enhances the realism of interactions across multiple sensory dimensions. With XR, users can feel virtual objects—their weight, their temperature, even their texture and consistency—bringing the physical and digital worlds into deeper, more natural continuity.

Artificial Intelligence plays a crucial role in enabling this integration. AI can enrich virtual scenes with semantic information, reconstruct and interpret 3D environments, correct and enhance data during 3D digitization, support the creation of virtual worlds from physical ones, and facilitate seamless interaction across both realms.

In this keynote, we will explore how these challenges have been addressed within the SUN project (Social and hUman ceNtered XR – https://www.sun-xr-project.eu/) and discuss the current limitations and emerging opportunities in this rapidly evolving field.

Bio: Dr. Giuseppe Amato is a research director at CNR-ISTI in Pisa, where he leads the "Artificial Intelligence for Multimedia and Humanities" laboratory (AIMH - http://aimh.isti.cnr.it/ ). He was awarded a PhD in Computer Science at the University of Dortmund, Germany, in 2002. His main research interests are artificial intelligence, extended reality, content-based retrieval of multimedia documents, access methods for similarity search, smart camera networks. He has published more than 200 papers in peer reviews international journals and conferences in the areas of artificial intelligence and multimedia information retrieval. He has participated in several EC and national funded research actions in the areas of Artificial Intelligence, Multimedia Information Retrieval, Computer Vision, Extended Reality, Robotics, and Cultural Heritage, and he currently coordinates the Social and hUman ceNtered XR (SUN) project (https://www.sun-xr-project.eu/) funded by the Horizon Europe Research & Innovation Programme. More at http://aimh.isti.cnr.it/giuseppeamato/