ECCV 2026 Workshop on Foundation and Generative Models in Biometrics

September 9, 2026, Malmö, Sweden

Introduction

Foundation models (such as CLIP, GPT, etc.) are extensively studied in different domains, including natural language processing (NLP), computer vision, etc. Given the performance and capabilities of these models, many researchers are focused on the development and applications of these models such that we can observe extremely rapid advancements, especially in the last three years. In fact, foundation models have demonstrated great potential in learning feature representations in various learning tasks. Particularly, foundation models have been shown to achieve superior performance for training on multiple tasks with large-scale data and then fine-tuning it to small-scale data for specific tasks or zero-shot generalization. Biometrics is also an active field of research in computer vision community. Given various problems in biometric systems, several researchers are focused on improving the recognition accuracy of biometric systems as well as enhancing security and privacy in such systems.

The Third Workshop on Foundation and Generative Models in Biometrics at ECCV 2026 aims to bring together researchers to discuss state-of-the-art advancements, applications, and challenges at the applications of foundation and generative models for biometrics. The workshop will foster discussions that inspire innovation and address challenges in real-world applications of these advanced models.

Invited Speakers

Jiankang Deng

Imperial College London

Wen-Sheng Chu

Google

Organizers

Hatef Otroshi

Idiap Research Institute, Switzerland

Vitomir Štruc

University of Ljubljana, Slovania

Luisa Verdoliva

University Federico II of Naples, Italy

Zhen Lei

Institute of Automation, CASIA, China

Arun Ross

Michigan State University, USA

Sébastien Marcel

Idiap Research Institute, Switzerland

Technical Program Committee

Contact

If you have any questions, please contact hatef.otroshi@idiap.ch.