Special Session · IEEE FG 2027

TRUST-XR

Trustworthy Face and Gesture Recognition in Extended Reality

Held in conjunction with the 21st IEEE International Conference on Automatic Face and Gesture Recognition (FG 2027).

When
26–30 April 2027
Where
Marrakesh, Morocco
Abstract due
9 Oct 202623 Oct 2026 AoE
Papers due
16 Oct 202630 Oct 2026 AoE
Read the Call for Papers IEEE FG 2027 website

News

    About the session

    Face and gesture recognition have become core interaction modalities in consumer VR/AR platforms, collectively known as extended reality (XR) environments in the form of photorealistic talking head-based avatar animation, hands-free authentication, social presence, and accessibility. Delivering these experiences requires continuous capture of high-resolution facial imagery, eye-gaze, hand-skeletal, and body-motion data streams.

    Recent studies show that these streams are independently sufficient to re-identify users with high confidence for reliable authentication. But at the same time, correlation between data streams (e.g., gaze and head motion) resists anonymization and is prone to security attacks by adversaries. Further, they can also leak sensitive inferences pertaining to age, health indicators, emotional and cognitive state that compromise user privacy. These risks present challenging problems for on-device capture, differential privacy for behavioral biometrics, liveness detection for gesture-based authentication, and cross-platform data governance.

    FG is the principal venue for face and gesture algorithmic research, yet the privacy and security implications specific to immersive capture remain underrepresented. This session extends FG's core expertise into this fast-growing application domain in XR. The proposed special session will foster collaboration between researchers, practitioners, policy stakeholders and industry experts to encourage novel methodologies, explore new applications, and identify challenges associated with improving trustworthiness in extended reality.

    Topics of interest

    Topics of interest include but are not limited to the following list.

    • Face, gaze, gesture, and behavior-based recognition and authentication in XR environments
    • Multimodal behavioral biometrics and cross-modal fusion of face, gaze, voice, hand, head, and body-motion signals
    • Liveness detection, presentation attack detection, and spoofing resilience for XR biometric systems
    • Deepfakes, synthetic avatars, avatar impersonation, and identity manipulation in immersive environments
    • Threat modeling and adversarial attacks for biometric capture in headsets, smart glasses, and other XR devices
    • Re-identification and de-anonymization from gaze, hand, head, and body-motion data
    • Robustness and scalable generalization across users, sessions, devices, and XR platforms
    • Deducing health cues from data in XR settings
    • Privacy-preserving, federated, differential-privacy, and signal-degradation approaches for XR biometrics
    • On-device and resource-efficient recognition, authentication, and privacy protection
    • Datasets, benchmarks, evaluation protocols, and bias analysis for XR biometrics and security
    • Regulatory and standards perspectives, including GDPR, BIPA, EU AI Act, and ISO/IEC
    • Usable privacy, consent, transparency, and user control in immersive interfaces

    Important dates

    All deadlines are 23:59 Anywhere on Earth (UTC−12).

    1. Special session paper abstract submission
    2. Special session paper submission
    3. Notification to authors
    4. Camera-ready submission
    5. IEEE FG 2027Marrakesh, Morocco

    Submission

    Special session papers go through the IEEE FG 2027 submission process. See the FG 2027 call for papers for full author guidelines.

    How to submit

    Submit via the official FG 2027 CMT system at cmt3.research.microsoft.com/FG2027, choosing the TRUST-XR special session track. Select TRUST-XR as the Primary Subject Area in CMT.

    Format and review

    Use the official FG 2027 author kit and follow its formatting, anonymization, page-limit and supplementary-material requirements — identical to the main conference.

    Publication

    Accepted papers are published and presented according to FG 2027 special session policies.

    Call for Papers

    CALL FOR PAPERS TRUST-XR: Trustworthy Face and Gesture Recognition in Extended Reality Special Session held in conjunction with IEEE FG 2027 21st IEEE International Conference on Automatic Face and Gesture Recognition 26-30 April 2027 | Marrakesh, Morocco Face and gesture recognition have become core interaction modalities in extended reality (XR), powering photorealistic avatar animation, hands-free authentication, social presence and accessibility. These experiences require continuous capture of facial imagery, eye-gaze, hand-skeletal and body-motion data. Each stream alone can re-identify users with high confidence, correlations between streams (e.g., gaze and head motion) resist anonymization and invite security attacks, and the data can leak sensitive inferences about age, health, and emotional and cognitive state. FG is the principal venue for face and gesture research, yet the privacy and security implications of immersive capture remain underrepresented. This special session extends FG's core expertise into XR, bringing together researchers, practitioners, policy stakeholders and industry experts to advance trustworthiness in extended reality. TOPICS OF INTEREST include but are not limited to: * Face, gaze, gesture, and behavior-based recognition and authentication in XR environments * Multimodal behavioral biometrics and cross-modal fusion of face, gaze, voice, hand, head, and body-motion signals * Liveness detection, presentation attack detection, and spoofing resilience for XR biometric systems * Deepfakes, synthetic avatars, avatar impersonation, and identity manipulation in immersive environments * Threat modeling and adversarial attacks for biometric capture in headsets, smart glasses, and other XR devices * Re-identification and de-anonymization from gaze, hand, head, and body-motion data * Robustness and scalable generalization across users, sessions, devices, and XR platforms * Deducing health cues from data in XR settings * Privacy-preserving, federated, differential-privacy, and signal-degradation approaches for XR biometrics * On-device and resource-efficient recognition, authentication, and privacy protection * Datasets, benchmarks, evaluation protocols, and bias analysis for XR biometrics and security * Regulatory and standards perspectives, including GDPR, BIPA, EU AI Act, and ISO/IEC * Usable privacy, consent, transparency, and user control in immersive interfaces IMPORTANT DATES (23:59 AoE) * Paper abstract submission: 9 October 202623 October 2026 * Paper submission: 16 October 202630 October 2026 * Notification to authors: 20 December 2026 * Camera-ready submission: 26 January 2027 * IEEE FG 2027: 26-30 April 2027 SUBMISSION Special Session papers must follow the same formatting and page-limit requirements as regular FG 2027 submissions. Authors should use the official FG 2027 author kit and carefully follow the formatting, anonymization, supplementary-material, and submission requirements specified in the FG 2027 Call for Papers. Special Session papers must be submitted via CMT and follow the same procedure as Main Conference papers, choosing the special session track within the main FG 2027 CMT system: https://cmt3.research.microsoft.com/FG2027. Papers submitted to any Special Session must select the name of the Special Session (TRUST-XR) as the Primary Subject Area in CMT. Accepted papers are published and presented according to FG 2027 special session policies. Refer to FG 2027 Special Session website for details.

    Organizers

    TRUST-XR is organized by researchers in biometrics, computer vision, security and machine learning.

    Dr. Sudipta Banerjee

    Dr. Sudipta Banerjee

    Assistant Professor, Electrical Engineering and Computer Science
    University of Wyoming, USA

    Dr. Sudipta Banerjee is currently appointed as an Assistant Professor in the Department of Electrical Engineering and Computer Science at University of Wyoming, United States. Prior to that she was affiliated with New York University Tandon School of Engineering as a Research Assistant Professor in Computer Science and Engineering. She received her doctoral degree in Computer Science from Michigan State University. Her research focuses on biometrics, generative models and image forensics.

    She has served as an Area Chair in IEEE FG 2026 and Program Chair in the 11th International Conference on Computer Vision and Image Processing (CVIP 2026). Dr. Banerjee has organized the Special Session on Generative AI for Futuristic Biometrics at IEEE/IAPR International Joint Conference in Biometrics (IJCB) 2024. She has (co)-authored multiple research papers for peer-reviewed journals and presented her work at international conferences. She has received Best Paper Awards at IEEE International Conf. on Biometrics: Theory, Applications and Systems (BTAS) 2019, IAPR/IEEE-IWBF 2018 and IEEE-ISBA 2019.

    Dr. Marija Ivanovska

    Dr. Marija Ivanovska

    Assistant, Faculty of Electrical Engineering
    University of Ljubljana, Slovenia

    Dr. Marija Ivanovska is an Assistant at the Faculty of Electrical Engineering, University of Ljubljana, Slovenia, and a member of the Laboratory for Machine Intelligence. Her research focuses on biometric security, computer vision, and trustworthy artificial intelligence, with particular emphasis on face-based attacks on biometric systems and the use of foundation models and multimodal large language models for robust biometric security.

    She has held international research appointments as a Visiting Scholar at Johns Hopkins University and as a Visiting Researcher at Queensland University of Technology, fostering collaborations in biometrics and trustworthy AI. She has authored numerous publications in peer-reviewed journals and conferences in computer vision, biometrics, and information forensics. Marija is actively involved in the international research community through editorial, organizational, and reviewing roles. She is a member of the IEEE Information Forensics and Security Technical Committee and the IAPR Technical Committee on Biometrics, and serves on the Webinar Committee of the IEEE Biometrics Council.

    Dr. Emanuela Marasco

    Dr. Emanuela Marasco

    Senior Research Scientist, Department of Computer Science
    Virginia Commonwealth University, USA

    Dr. Emanuela Marasco currently serves as a Senior Research Scientist in the Department of Computer Science, College of Engineering, at Virginia Commonwealth University (VCU). Previously, she was an Assistant Professor in the Department of Information Sciences and Technology at George Mason University. Her research focuses on artificial intelligence, machine learning, biometrics, cybersecurity, trustworthy identity technologies. She has published in leading conferences and journals, including WACV, ECML-PKDD, EMNLP, IEEE TBIOM, IMAVIS, and IEEE Access, and has led NSF-funded research projects. She is also an inventor on U.S. patents related to biometric MFA and hyperspectral technologies.

    Dr. Marasco has extensive experience organizing technical workshops, conferences, and research events. She is Lead Co-Organizer of the DL-HSA Workshops at IEEE ICIP 2025 and 2026, Co-Organizer of the GenXR-ID Workshop at IEEE CVPR 2026, Doctoral Consortium Co-Chair of IEEE IJCB 2026, and Demo/Exhibits Co-Chair and Industry-Panel Co-Chair of IEEE WACV 2026.

    Dr. İnci M. Baytaş

    Dr. İnci M. Baytaş

    Associate Professor, Department of Computer Engineering
    Boğaziçi University, Türkiye

    Dr. İnci M. Baytaş is an Associate Professor at the Department of Computer Engineering at Boğaziçi University. Her research interests include machine learning, deep learning, adversarial robustness, temporal analysis, graph neural networks, and their applications to biomedical informatics. She serves as the communication officer for Technical Committee 20 of the International Association of Pattern Recognition, titled Pattern Recognition for Bioinformatics and Digital Health.

    Dr. Baytaş co-organized the International Workshop on Pattern Recognition in Healthcare Analytics at ICPR 2022, 2024, 2026, and ACML 2023. She co-organized special issues, Pattern Recognition for Healthcare Analytics for Frontiers in Digital Health in 2022 and Pattern Recognition for Healthcare Analytics for the Journal of Computational Biology in 2023. She served as a program committee member at NeurIPS 2026, AAAI 2021-2026, FG 2026, KDD 2024 and KDD 2025.

    Contact us

    For questions about the special session, topics or submissions, email the organizers.