Keynote Speakers

Juan Wachs

Purdue University, United States

Dr. Juan Wachs is the James H. and Barbara H. Greene Professor in the Edwardson School of Industrial Engineering at Purdue University, Professor of Biomedical Engineering (by courtesy) and an Adjunct Professor of Surgery at Indiana University School of Medicine. He is also the Director of the Intelligent Systems and Assistive Technologies (ISAT) Lab at Purdue, and he is affiliated with the Regenstrief Center for Healthcare Engineering. He completed his postdoctoral training at the Naval Postgraduate School’s MOVES Institute under a National Research Council Fellowship from the National Academies of Sciences. He is the recipient of the 2013 Air Force Young Investigator Award, and the 2015 Helmsley Senior Scientist Fellow, and 2016 Fulbright U.S. Scholar, the James A. and Sharon M. Tompkins Rising Star Associate Professor, 2017, the ACM Distinguished Speaker 2018, and the James H. and Barbara H. Greene Enodwed Professorship, 2024. He is also the Associate Editor of IEEE Transactions in Human-Machine Systems, Frontiers in Robotics and AI.

Keynote Title: Bridging the Algorithm Abyss: Where Surgical Intelligence Meets Computer Vision

Abstract: Robots can already solve sophisticated problems ranging from playing games, autonomous driving, and dancing—given enough observational of data for training. The core of such success resides in efficient algorithms, compliant hardware and robust computing, all implemented using carefully curated data collected before the training phase. Thus, robots learn in a “sterile” domain, under clean, controlled and to some extent supervised environments. As the target domain changes, however, moving to more constrained, resource limited, and austere settings, robots struggle to perform well. To be able to meet the future needs in emergency medicine, a new form of intelligence, involving both physical and perceptive aspects is needed, referred as to shared intelligence. In this talk, I will present my trajectory in the pursue of shared intelligence along the continuum of care, focusing in the operating room as the main setting to highlight new challenges and discoveries in the field of interventional AI. Specifically, I will discuss work related to telesurgery, skill augmentation and training. Progress in these directions will contribute to the public purpose of creating truly applied machine vision that is more accessible, effective and sensitive to social needs.

Leo Dorst

University of Amsterdam

Leo Dorst is with the Informatics Institute at the University of Amsterdam. He received his MSc and PhD in the applied physics of computer vision from Delft University, and started his work on geometrical issues in robotics at Philips Laboratories, NY, USA, where he developed robot path planning algorithms (cast into 12 patents). His passion since 1997 is geometric algebra; he is coauthor of the introductory book "Geometric Algebra for Computer Science" (2009) and co-editor of several topical collections.

Keynote Title: Let Geometric Algebra Shape Your Thinking

Abstract: This keynote briefly presents the basics of geometric algebra, and explains what features make it such a powerful framework for computational geometry in vision, graphics, robotics and physics. Essentially, GA structurally expands the geometric use of linear algebra in a representation that makes geometric primitives, their combinations, and their transformations automatically universal and structure-preserving. We illustrate the payoff of this practical principle in some applications: orders of magnitude reduction in data and size for equivariant networks, expansion of linear algebra techniques to seemingly nonlinear domains in parameter estimation, and compact dimension-agnostic software for physics-based computer vision and graphics.

Marco Diani

iMAGE S S.p.A.

Marco Diani has more than 40 years of experience in Imaging and Computer Vision. He developed a keen interest in Machine Vision in 1983 while he was a student at the University of Pavia, where he received his degree in Electronic Engineering in 1986. His thesis was in Machine Vision and he continued his education, ultimately receiving his PhD in Machine Vision in 1989. He also authored and co-authored nearly 30 national and international scientific publications during his studies. Marco has spent his entire carrier in the Machine Vision industry. In 1987 he established a system integration company that developed industrial vision systems that is still in business. Among the company’s many achievements, he is most proud of the company’s design and manufacture of the first blister pack inspection system made in Italy for the pharmaceutical industry. In 1994, he was one of the founding partners of iMAGE S, a leading distributor of machine vision components in Italy and one of the original members of the EMVA. Over the last 30+ years he was instrumental in leading the company, together with his partners, to become the reference point for all the Italian system integrators and OEM’s that are working in vision.

Keynote Title: The Rise of Computer Vision: History, Acceleration, and the Road Ahead

Abstract: During the last decades Imaging and machine visions evolved tremendously also the first studies of machine vision technology started in early 40’s of last century. During this talk I would like to make a little history of machine vision technologies looking to the fast evolution over the last years with specific attention to the applications but starting from the first “expert systems” the predecessor of actual AI. In the last part we will analize the latest news hardware/software/ai technologies with a look forward to new applications and sectors.

Alexandru Telea

Utrecht University

Alexandru Telea is Professor of Visual Data Analytics at the Department of Information and Computing Sciences, Utrecht University. He holds a PhD from Eindhoven University and has been active in the visualization field for over 25 years. He has been the program co-chair, general chair, or steering committee member of several conferences and workshops in visualization, including EuroVis, VISSOFT, SoftVis, EGPGV, IVAPP, and SIBGRAPI. His main research interests cover unifying information visualization and scientific visualization, high-dimensional visualization, and visual analytics for machine learning. He is the author of the textbook “Data Visualization: Principles and Practice” (CRC Press, 2014).

Keynote Title: Seeing is Learning in High Dimensions: How Dimensionality Reduction Bridges Machine Learning and Data Visualization

Abstract: Computer vision and machine learning (ML) applications are one of the most prominent generators of large, high-dimensional, and complex datasets. Multidimensional projections (MPs) are the techniques of choice for visually exploring such high-dimensional data. Yet, for a long while, the ML and data visualization fields have developed largely independently of each other. In this talk, I will explore the connections, challenges, and potential synergies between these two fields, showing that they share many unexplored commonalities revolving around MPs. These involve “seeing to learn”, or how to deploy MP techniques to open the black box of ML models, and “learning to see”, or how to use ML to create better MP techniques for visualizing high-dimensional data. Examples will cover how to use ML to measure the quality of MPs, using ML to create significantly faster MPs, and extending MPs to create dense representations of ML models.