CVPR 2023 Biometrics Workshop

With a very security conscious society, biometrics based authentication and identification have become center of focus for many important applications as it is believed that biometrics can provide accurate and reliable identification. Biometrics research and technology continue to mature rapidly, driven by pressing industrial and government needs and supported by industrial and government funding. As the number and types of biometrics architectures and sensors increases, the need to disseminate research results increases as well. This workshop is intended to be positioned at the frontier of biometrics research and showcase the most excellent and advanced work underway at academic and private research organizations as well as government labs.

Many of the applications require higher level of accuracy performance not feasible with a single biometrics today. Additionally, it is also believed that fusing multiple biometrics will also improve wider coverage of population who may not be able to provide a single biometrics and also improve security of the systems in terms of spoof attacks. This workshop will address all aspects of research issues in different modes and levels of fusion of biometrics samples, sensing modes and modalities with a sole goal of improving performance of biometrics. Theoretical studies on sensor fusion techniques applied to biometrics authentication, recognition and performance are encouraged. The topics of interest are:

Overall Meeting Sponsors

General Chair: Bir Bhanu (University of California, Riverside, bbhanu@ucr.edu)

Program Chair: Ajay Kumar (The Hong Kong Polytechnic University, Ajay.Kumar@polyu.edu.hk)

• Aythami Morales, Universidad Autónoma de Madrid, Spain
• Christoph Busch, Fraunhofer Institute, Germany
• Elias Zois, University of West Attica, Greece
• Hazim Ekenel, Istanbul Technical University, Turkey
• Hugo J. Escalante, INAOE, Puebla, Mexico
• Hugo Proença, University of Beira Interior, Portugal
• Jiankun Hu, University of New South Wales, Australia
• Jonathon Phillips, NIST, USA
• Kar-Ann Toh, Yonsei University, South Korea
• Karthik Nandakumar, MBZUAI, United Arab Emirates
• Kevin Ho Man Cheng, Huawei Technologies, Finland
• Kevin Bowyer, Notre Dame University, USA
• Koichi Ito, Tohuku University, Japan
• Mark Nixon, University of Southampton, UK
• Matteo Ferrara, University of Bologna, Italy
• Maneet Singh, AI Garage, Master Card, India
• Massimo Tistarelli, Università di Sassari, Italy
• Naser Damer, Fraunhofer IGD, Germany
• Pong C Yuen, Hong Kong Baptist University, Hong Kong
• Raghavendra Ramachandra, NTNU, Norway
• Shiqi Yu, Southern University of Science and Technology, China
• Stephanie Schuckers, Clarkson University, USA
• Terrance E Boult, University of Colorado at Colorado Springs, USA
• Vikram M. Gadre, IIT Bombay, India
• Vishal Patel, Johns Hopkins University, USA
• Yasushi Makihara, Osaka University, Japan

Paper submission: March 3, 2023 (11:59pm PST) Decisions: April 6, 2023 Camera ready papers due: April 12, 2023

Workshop Date: June 18, 2023

Title of the Talk: Harnessing Generative Priors for Image Super-Resolution Speaker: Chen Change Loy, Nanyang Technological University, Singapore Abstract: In this talk, I will present an overview of recent advancements in harnessing generative priors for image super-resolution, particularly focusing on blind face restoration and real-world applications. We discuss how leveraging learned discrete codebook priors, and robust diffusion priors can significantly improve restoration quality and robustness under complex and unknown degradations. In particular, I will discuss CodeFormer, a Transformer-based prediction network that uses a codebook prior to tackling the inherent uncertainty in blind face restoration, and the DifFace, an approach that exploits a pre-trained diffusion model to cope with unseen degradations without complicated loss designs.

Title of the Talk: Unlocking the Secrets of Human Movement: A Look at the Cutting-Edge Progress in Gait Recognition Speaker: Yasushi Yagi, Osaka University, Japan Abstract: The way we walk, or our gait, can reveal a lot about our personal information, such as our identity, gender, age, emotions, intentions, and even our health. This has led to extensive research on gait recognition not just in biometrics, but also in fields like biomechatronics and healthcare. However, applying gait recognition to real-world problems presents a challenge due to various fluctuating factors that need to be taken into account. In this presentation, I will discuss recent progress in gait recognition research by our group, which focuses on the diversity of observations, including cross-view and occlusion, as well as the uncertainty of annotation. Additionally, I will touch on video-based gait analysis, which can play a critical role in medical and wellness fields if time permits.

Title of the Talk: The Art of Non-Verbal Communication: Decoding Facial Expressions and Gestures for Seamless Human-Robot Interaction Speaker: Xilin Chen, Chinese Academy of Sciences, China Abstract: As robots become more prevalent in our daily lives, their ability to understand and respond to human communication is becoming increasingly important. While natural language processing (NLP) has enabled robots to capture human intentions from verbal communication, understanding non-verbal cues such as facial expressions and gestures remains a challenge. However, these non-verbal channels are crucial for conveying user intention to robots, especially for human-centered robotics. In this talk, I will explore the roles of non-verbal channels in human communication, which provide additional information to emphasize key points and express attitudes. I will also discuss recent efforts in understanding facial expressions and gestures, both conscious and unconscious, to improve the interaction efficiency between humans and robots.

1. All the submissions will be subjected to double-blind review process. Therefore author names, affiliations, email addresses, personal acknowledgements, etc. should be removed from the paper. Please use the submission template [Latex] [MS-Word].
2. The submissions can be up to 8 pages (excluding references) during the review process.
3. All the papers must be submitted in IEEE format using the templates provided. Submitted papers should not have been published, accepted or under review elsewhere.
4. All the papers accepted for the biometrics workshop must be presented by one of the authors, and at least one of the authors must register at the standard registration rate before the paper registration deadline. If any accepted paper is not presented by any of the registered co-authors of this paper, it will be recommended for withdrawal from the IEEE Xplore proceedings and no communication will be sent to any of the co-authors.
5. Authors are required by the IEEE to transfer copyrights for any papers to be published in the conference proceedings. This is performed at the time when the camera ready version is submitted for production. If a paper is withdrawn from the proceedings, copyright gets reverted to the authors.
6. All the papers should be submitted using CMT at https://cmt3.research.microsoft.com/BIOMETRICS2023

CVPR 2023 Biometrics Workshop Best Paper Award

• Chih-Jung Chang, Yaw-Chern Lee, Shih-Hsuan Yao, Min-Hung Chen, Chien-Yi Wang, Shang-Hong Lai, Trista Pei-Chun Chen for the paper “A Closer Look at Geometric Temporal Dynamics for Face Anti-Spoofing,” Presented at CVPR 2023 Biometrics Workshop

CVPR 2023 Biometrics Workshop Highest Impact Paper Award

• Javier Hernandez-Ortega, Julian Fierrez, Aythami Morales, Pedro Tome for the paper “A Time Analysis of Pulse-based Face Anti-Spoofing in Visible and NIR” Presented at CVPR 2018 Biometrics Workshop

Vancouver, Canada

Bir Bhanu Email: bbhanu@ucr.edu

Ajay Kumar Email: Ajay.Kumar@polyu.edu.hk