Bio: Thomas Wiegand is a professor in the department of Electrical Engineering and Computer Science at the Technical University of Berlin and is jointly heading the Fraunhofer Heinrich Hertz Institute, Berlin, Germany. He received the Dipl.-Ing. degree in Electrical Engineering from the Technical University of Hamburg-Harburg, Germany, in 1995 and the Dr.-Ing. degree from the University of Erlangen-Nuremberg, Germany, in 2000.
As a student, he was a Visiting Researcher at Kobe University, Japan, the University of California at Santa Barbara and Stanford University, USA, where he also returned as a visiting professor. He has been a co-founder and consultant for various start-up companies.
Since 1995, he has been an active participant in standardization for multimedia with many successful submissions to ITU-T and ISO/IEC. In 2000, he was appointed as the Associated Rapporteur of ITU-T VCEG and from 2005-2009, he was Co-Chair of ISO/IEC MPEG Video. From 2018-2023, he has been the chair of the ITU/WHO Focus Group on Artificial Intelligence for Health.
The projects that he co-chaired for the development of the H.264/MPEG-AVC standard have been recognized by an ATAS Primetime Emmy Engineering Award. He was also a recipient of a ATAS Primetime Emmy Engineering Award for the development of H.265/MPEG-HEVC and a pair of NATAS Technology & Engineering Emmy Awards. For his research in video coding and transmission, he received numerous awards including the Vodafone Innovations Award, the EURASIP Group Technical Achievement Award, the Eduard Rhein Technology Award, the Karl Heinz Beckurts Award, the IEEE Masaru Ibuka Technical Field Award, and the IMTC Leadership Award. He received multiple best paper awards for his publications. Since 2014, Thomson Reuters named him in their list of "The World's Most Influential Scientific Minds" as one of the most cited researchers in his field. He is a recipient of the ITU150 Award.
He is an IEEE Fellow and has been elected to the German National Academy of Engineering (Acatech) and the National Academy of Science (Leopoldina).
Abstract: In recent years, advancements in artificial intelligence have led to a remarkable surge in the quality and realism of AI-generated images, video, audio, and speech. This rapid evolution has raised significant challenges in distinguishing between content created by AI and that captured through traditional sources such as cameras and microphones. As the capabilities of generative AI continue to improve, the difficulty in detecting the origins of multimedia content intensifies, creating a weapons race between AI content generators and detection algorithms. It can be forecasted that in some not-so-distant future, it might become impossible to distinguish between AI-generated and natural content.
Another approach to addressing this the fake media challenge is to enable end-to-end authentication for original multimedia content sourced from natural origins, such as cameras and microphones. By utilizing digital signatures, the integrity of compressed content can be guaranteed. Moreover, embedding essential provenance information such as date, time, location, and other relevant metadata into the digital signature increases robustness. This keynote will explore the mechanics of digital signatures for multimedia, emphasizing their critical role in verifying content authenticity. We will also discuss cascading authentications within content production and distribution chains, as well as the potential implications of failures of the authentication method. The integration of authenticity signalling into video (H.26x) and audio (MPEG-x) coding standards is currently being worked on in ITU/ISO/IEC.
Bio: Dan Schien is a Senior Lecturer in Computer Science at the University of Bristol, UK. His research focuses on the environmental impact of information technology and its role in the decarbonisation of society. He is particularly interested in sustainable consumption of digital media and the complex system of interactions between consumption of digital media, the ICT infrastructure and design of media services. Dan applies multidisciplinary methods from software engineering, human computer interaction and environmental science.
Abstract: The way how visual signals are generated, processed, transmitted, and interpreted is changing: from video compression over automated scene understanding to generating media. Yet, as performance improves its environmental footprint evolves in complex and often counterintuitive ways.
This keynote explores the dynamic interplay between the changing direct impacts of media technology (through energy and hardware), and the indirect effects that emerge through shifts in demand, behaviour, and value chains. Drawing on recent research in sustainability assessment of digital services, it highlights how current energy and carbon accounting frameworks fail to capture these interactions, and points to ways they can be extended to reflect the broader systemic consequences of the co-evolution of technology and its adoption.
Bio: Silvia Miksch is a University Professor and head of the research unit "Visual Analytics" (Centre for Visual Analytics Science and Technology (CVAST)), which is part of Vienna University of Technology (TU Wien), Faculty of Informatics, Institute of Visual Computing and Human-Centered Technology. She served on various program committees of international scientific conferences (paper co-chair of the IEEE VAST 2010, 2011, 2020, EG EuroVis 2012, etc.), belong(ed) to the editorial board of IEEE TVCG, CGF, etc., and she act(ed) in various strategic and guiding committees, such as the VAST steering committee and the VIS Executive Committee (VEC). Currently, she is chairing the EuroVis steering committee. In 2020, she was inducted into the IEEE Visualization Academy (or in short, Vis Academy). The Vis Academy was established in 2018 by the IEEE VGTC Executive Committee. Induction into the Vis Academy is the highest and most prestigious honor in the field of visualization. In 2023 she was honored for my outstanding technical contributions to VA of time-varying data with the prestigious IEEE VGTC Visualization Technical Achievement Award.
She has more than 300 scientific publications, and her main research interests are visualization and visual analytics over time and space, with a particular focus on interaction techniques, network-based, knowledge-assisted, and guidance-enriched methods. Her cross-cutting application fields are healthcare, digital humanities/arts, financial fraud detection, etc. More information can be found at: https://www.cvast.tuwien.ac.at/team/silvia-miksch
Abstract: Visual Analytics—“the science of analytical reasoning facilitated by interactive visual interfaces”—seeks to help users explore and understand large, heterogeneous, and complex data sets by tightly integrating interactive visualization, data analysis, human–computer interaction, and cognitive and perceptual science. Central to this field are human capabilities, as well as user needs and tasks, especially when navigating complex decision-making processes. A mixed-initiative process, in which both humans and systems can take the lead, offers a powerful framework for richer problem-solving and deeper insight. In this talk, I will outline guidance-enriched and knowledge-assisted Visual Analytics through the lens of mixed-initiative interaction. I will address three key questions: “what” is visualized, “why” it is visualized, and “how” it is visualized. Examples from healthcare and medicine, cultural heritage, art history, and finance will demonstrate current achievements and point toward future opportunities and challenges. While data and information are broad domains, I will focus on temporal, spatial, spatio-temporal, network, and uncertainty dimensions.
