Keynote Speakers
Meike Ramon (University of Lausanne): Natural and synthetic face recognition research: fundament and societal benefits
Recent technological advances and related societal issues have led to a surge of attention towards the concept of “face recognition”. I argue that the most important facet of face recognition — identity processing — is not a solved problem. On the contrary, it is a typically underestimated, highly complex skill that our brains have developed to efficiently master. Moreover, generative AI and the ability to create synthetic identities at scale have given rise to entirely novel questions in this field of research. Using examples of ongoing work in my group, I argue that studying face identity processing can do more than advance our understanding of human cognition and its neural basis. It can support the development of human-machine interactions, and facilitate an inter-stakeholder exchange necessary to maintain trust in institutions, and enable innovative research opportunities. Synthetic identities in particular can play a major role in enhancing trust, privacy and fairness across a range of applications.
Bio: Professor Meike Ramon is a Swiss National Science Foundation PRIMA (Promoting Women in Academia) Fellow. She founded and leads the Applied Face Cognition Lab at the University of Lausanne. From March 2025 onwards she will hold a Professorship for Applied Data Science at the Bern University of Applied Sciences. After studying at the Ruhr-University in Bochum (DE), funded by Belgian National Science Foundation she received a PhD from the Université catholique de Louvain (BE), and was a Visiting Postdoctoral at the University of Glasgow (UK). Meike’s research focus is on cognitive neuroscience and its translation into application and policy. She studies face recognition, the neurofunctional basis of differences in this ability, and its implications for society - from face-blindness to so-called Super-Recognizers. Other things Meike is involved in: Expert Panel Member for Innosuisse, the Swiss Federal Innovation Agency - Board Member Association for Independent Research - Advisory Board Member for the multi-centric project "Increasing eyewitness identification accuracy in lineups using 3D interactive virtual reality (3DIL)” - Member of the European Association for Biometrics (EAB) - Member of the Europol Platform for Experts (EPE) and Europol Data Protection Experts Network (EDEN). As a Scientific Advisor for the Berlin Police, Meike co-developed the Berlin Test for Super-Recognizer Identification (beSure®), a bespoke tool involving authentic police material.
Xiaoming Liu (MSU): Person Recognition at a Far Distance
In recent years we have witnessed increasingly diverse application scenarios of biometrics systems in our daily life, one of which is person recognition at a (far) distance. In this talk, I will cover a number of key problems that are recently being addressed at the Computer Vision Lab of MSU, including: how to address the various training sample quality in learning large-scale face recognition systems; how to integrate identity information from an image set or video sequences; how to estimate the 3D body shape from an image of clothed human body; how to use AIGC to generate a complete synthetic database for training face recognition systems; how to leverage foundation models for person recognition; and how to build our own foundation models for unified face and body recognition.
Bio: Dr. Xiaoming Liu is the MSU Foundation Professor, and Anil and Nandita Jain Endowed Professor at the Department of Computer Science and Engineering of Michigan State University (MSU). He is also a visiting scientist at Google Research. He received Ph.D. degree from Carnegie Mellon University in 2004. Before joining MSU in 2012 he was a research scientist at General Electric (GE) Global Research. He works on computer vision, machine learning, and biometrics especially on face related analysis and 3D vision. Since 2012 he helps to develop a strong computer vision area in MSU who is ranked top 15 in US according to the 5-year statistics at csrankings.org. He is an Associate Editor of IEEE Transactions on Pattern Analysis and Machine Intelligence. He has authored more than 200 scientific publications, and has filed 35 U.S. patents. His work has been cited over 28000 times according to Google Scholar, with an H-index of 79. He received the 2018 and 2023 Withrow Distinguished Scholar Awards from MSU. He is a fellow of The Institute of Electrical and Electronics Engineers (IEEE) and International Association for Pattern Recognition (IAPR).