Title: Beyond Pixels: Continuous Neural Representations for Biometrics
Speaker: Prof. Dr. Vishal Patel, Johns Hopkins University, USA
When: September 24, 2026 at 9:00 AM US Eastern Time (3:00 pm CEST, 9:00 PM Beijing Time)
Where: Online (Zoom)
Registration (free but required): https://us06web.zoom.us/webinar/register/WN_UodgWsTBTaGuNgPPNphlQg
Abstract
Biometrics has traditionally relied on discrete pixel representations and, more recently, learned feature embeddings for recognition and analysis. This talk explores an emerging alternative based on Implicit Neural Representations (INRs), which model biometric traits as continuous functions rather than discrete images. The talk will introduce the principles of INRs and demonstrate their applications to deepfake and presentation attack detection, biometric quality assessment, and function-space metric learning. Our speaker will conclude by discussing future opportunities for INRs in biometric recognition, continuous biometric templates, morph attack analysis, privacy-preserving biometrics, and multimodal biometric systems, arguing that continuous neural representations may provide a new foundation for the next generation of biometric technologies.
About The Speaker
Vishal M. Patel is a Professor in the Department of Electrical and Computer Engineering (ECE) at Johns Hopkins University. His research focuses on computer vision, machine learning, image processing, medical image analysis, and biometrics. He has received a number of awards including the 2021 IEEE Signal Processing Society (SPS) Pierre-Simon Laplace Early Career Technical Achievement Award, the 2021 NSF CAREER Award, the 2021 IAPR Young Biometrics Investigator Award (YBIA), the 2016 ONR Young Investigator Award, and the 2016 Jimmy Lin Award for Invention. Patel serves as an associate editor for the IEEE Transactions on Pattern Analysis and Machine Intelligence journal and IEEE Transactions on Biometrics, Behavior, and Identity Science. He is a Fellow of the IEEE and IAPR.
