IEEE International Joint Conference on Biometrics (IJCB 2023)

Keynote Talks

Keynote 1, Tuesday 26 September 2023, 9am-10am

Keynote speaker: Gouying Zhao, Academy professor, University of Oulu

Keynote Title: What can machines read from human faces?

Abstract: The face is very special for us humans. Most people spend more time looking at faces than at any other type of objects. Given a face image/video, technology has been able to get the information regarding people’s age, gender, ethnicity, identity, facial expressions, etc. Recent years’ efforts have been put on reading concealed and imperceptible visual cues from faces, such as facial micro-expressions, subtle facial color changes, and physiological signals, like the heart rate. This talk focuses on research developments from reading well-seen facial cues to hidden micro and imperceptible cues with the discussion about the technology, applications and ethical concerns.

Speaker Bio: Guoying Zhao received the Ph.D. degree in computer science from the Chinese Academy of Sciences, Beijing, China, in 2005. She is currently an Academy Professor and full Professor (tenured in 2017) with University of Oulu. She is/was also a visiting professor with Aalto University and Stanford University. She is a member of Academia Europaea, a member of Finnish Academy of Sciences and Letters, IEEE Fellow, IAPR Fellow and AAIA Fellow. She was panel chair for IEEE conference on Automatic Face and Gesture (FG 2023), publicity chair of 22nd Scandinavian Conference on Image Analysis (SCIA 2023), co-program chair for ACM International Conference on Multimodal Interaction (ICMI 2021), and co-publicity chair for FG2018, and has served as associate editor for IEEE Trans. on Multimedia, Pattern Recognition, IEEE Trans. on Circuits and Systems for Video Technology, Image and Vision Computing and Frontiers in Psychology Journals. Her current research interests include image and video descriptors, facial-expression and micro-expression recognition, emotional gesture analysis, affective computing, and biometrics. Her research has been reported by Finnish TV programs, newspapers and MIT Technology Review.

Keynote 2, Wednesday 27 September 2023, 9am – 10am

Keynote speaker: Xiangyu Zhu, Institute of Automation, Chinese Academy of Sciences (CASIA)

Winner of the IAPR Young Biometrics Investigator Award

Keynote title: Building 3D Representations for Face Recognition

Abstract: One of the most promsing idea in computer vision is that object recognition relies on 3D representations. In this talk, he will discuss the application of this concept to biometric recognition, specifically focusing on the building of 3D representations for face recognition. He will introduce this works on 3D face reconstruction, 3D-aided face recognition, and 3D description-based face analysis. Finally, he will provide a personal look into future work on how to build hierarchical 3D representation unsupervisedly.

Speaker Bio: Xiangyu Zhu is an associate professor at the Center for Biometrics and Security Research (CBSR) & the State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences. His research interest includes 3D face reconstruction and face recognition. He has published over 70 papers including top journals like IEEE T-PAMI, IJCV etc. He has won a number of academic awards and competitions by the developed face algorithms, including the FG2017 facial micro-expression recognition competition, the champion of light weight face recognition challenge in ICCV 2019, the best student paper award in Chinese Conference on Biometrics (CCBR) 2017, the best student paper award runner-up in ICME 2018, the best poster paper award in CCBR 2022. He also serves as a secretary at the Pattern Recognition and Machine Intelligence Committee (PRMI) of the Chinese Association of Automation (CAA), IAPR.

Keynote 3, Thursday 28 September 2023, 9am – 10am

Keynote speaker: Manoj Aggarwal, Director of Applied Science, Amazon One

Keynote Title: Amazon One: A Peek under the Hood

Abstract: Amazon One is a fast, convenient, contactless way for people to use their palm to enter, identify, and pay. The service is highly secure and uses custom-built algorithms and hardware to create a person’s unique palm signature. In this talk, I will discuss pieces of the technology behind Amazon One, including the image acquisition system and the recognition engine. I will also share insights into components beyond recognition such as generative AI, image quality estimation and liveness detection that are key to achieving a good customer experience.

Speaker Bio: Manoj Aggarwal is a technologist with over 20 years of experience in computer vision, biometrics and AI. He is currently a Director of Applied Science at Amazon where he is leading the science teams that built the palm recognition engine powering Amazon One. Before Amazon, he founded two startups to build computer vision-based systems for wide area surveillance, iris recognition and automated sports production. He received his Ph.D. degree in Electrical Engineering from the University of Illinois at Urbana-Champaign in 2001.