<html xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:m="http://schemas.microsoft.com/office/2004/12/omml" xmlns="http://www.w3.org/TR/REC-html40"> <head> <meta http-equiv="Content-Type" content="text/html; charset=us-ascii"> <meta name="Generator" content="Microsoft Word 15 (filtered medium)"> <style></style> </head> <body lang="EN-US" link="#0563C1" vlink="#954F72"> <div class="WordSection1"> IEEE VR 2023 Workshop on Multi-modal Affective and Social Behavior Analysis and Synthesis in Extended Reality (MASSXR)<o:p></o:p> Location and date<o:p></o:p> The workshop IEEE-MASSXR will take place during the 30th IEEE Conference on Virtual Reality and 3D User Interfaces (IEEE VR 2023) conference, which will be held from March 25-29, 2023, in Shanghai, China.<o:p></o:p> IEEE-MASSXR is a half-day workshop, and it will be held online on 25th March. For more information, please visit the workshop’s website:<o:p></o:p> <a href="https://sites.google.com/view/massxrworkshop2023">https://sites.google.com/view/massxrworkshop2023</a> <o:p></o:p> Description<o:p></o:p> With the recent advances in immersive technologies such as realistic digital humans, off-the-shelf XR devices with capabilities to capture users’ speech, faces, hands, and bodies, and the development of sophisticated data-driven AI algorithms, there is a great potential for automatic analysis and synthesis of social and affective cues in XR. Although affective and social signal understanding and synthesis are studied in other fields (e.g., for human-robot interaction, intelligent virtual agents, or computer vision), it has not yet been explored adequately in Virtual and Augmented Reality. This demands extended-reality-specific theoretical and methodological foundations. Particularly, this workshop focuses on the following research questions:<o:p></o:p> <ul style="margin-top:0in;padding-inline-start:48px" type="disc"> <li class="MsoNormal" style="color:black;margin-top:11.0pt;text-align:justify;mso-list:l3 level1 lfo1;vertical-align:baseline"> How can we sense the user’s affective and social states using sensors available in XR?<o:p></o:p></li><li class="MsoNormal" style="color:black;text-align:justify;mso-list:l3 level1 lfo1;vertical-align:baseline"> How can we collect users’ interaction data in immersive situations?<o:p></o:p></li><li class="MsoNormal" style="color:black;text-align:justify;mso-list:l3 level1 lfo1;vertical-align:baseline"> How can we generate affective and social cues for digital humans/avatars in immersive interactions enabled by dialogue, voice, and non-verbal behaviors?<o:p></o:p></li><li class="MsoNormal" style="color:black;margin-bottom:11.0pt;text-align:justify;mso-list:l3 level1 lfo1;vertical-align:baseline"> How can we develop systematic methodologies and techniques to develop plausible, trustable, personalized behaviors for social and affective interaction in XR?<o:p></o:p></li></ul> The objective of this workshop on Multi-modal Affective and Social Behavior Analysis and Synthesis in Extended Reality is to bring together researchers and practitioners working in the field of social and affective computing with the ones on 3D computer vision and computer graphics/animation and discuss the current state and future directions, opportunities, and challenges. The workshop aims to establish a new platform for the development of immersive embodied intelligence at the intersection of Artificial intelligence (AI) and Extended Reality (XR). We expect that the workshop will provide an opportunity for researchers to develop new techniques and will lead to new collaboration among the participants. <o:p></o:p> Scope<o:p></o:p> This workshop invites researchers to submit original, high-quality research papers related to multi-modal affective and social behavior analysis and synthesis in XR. Relevant topics include, but are not limited to:<o:p></o:p> <ul style="margin-top:0in;padding-inline-start:48px" type="disc"> <li class="MsoNormal" style="color:black;margin-top:11.0pt;text-align:justify;mso-list:l4 level1 lfo2;vertical-align:baseline"> Analysis and synthesis of multi-modal social and affective cues in XR<o:p></o:p></li><li class="MsoNormal" style="color:black;text-align:justify;mso-list:l4 level1 lfo2;vertical-align:baseline"> Data-driven expressive character animation (e.g., face, gaze, gestures, ...)<o:p></o:p></li><li class="MsoNormal" style="color:black;text-align:justify;mso-list:l4 level1 lfo2;vertical-align:baseline"> AI algorithms for modeling social interactions with human- and AI-driven virtual humans<o:p></o:p></li><li class="MsoNormal" style="color:black;text-align:justify;mso-list:l4 level1 lfo2;vertical-align:baseline"> Machine learning for dyadic and multi-party interactions<o:p></o:p></li><li class="MsoNormal" style="color:black;text-align:justify;mso-list:l4 level1 lfo2;vertical-align:baseline"> Generating diverse, personalized, and style-based body motions<o:p></o:p></li><li class="MsoNormal" style="color:black;text-align:justify;mso-list:l4 level1 lfo2;vertical-align:baseline"> Music-driven animation (e.g., dance, instrument playing)<o:p></o:p></li><li class="MsoNormal" style="color:black;text-align:justify;mso-list:l4 level1 lfo2;vertical-align:baseline"> Multi-modal data collection and annotation in and for XR (e.g., using VR/AR headsets, microphones, motion capture devices, and 4D scanners)<o:p></o:p></li><li class="MsoNormal" style="color:black;text-align:justify;mso-list:l4 level1 lfo2;vertical-align:baseline"> Efficient and novel machine learning methods (e.g., transfer learning, self-supervised and few-shot learning, generative and graph models)<o:p></o:p></li><li class="MsoNormal" style="color:black;text-align:justify;mso-list:l4 level1 lfo2;vertical-align:baseline"> Subjective and objective analysis of data-driven algorithms for XR<o:p></o:p></li><li class="MsoNormal" style="color:black;margin-bottom:12.0pt;text-align:justify;mso-list:l4 level1 lfo2;vertical-align:baseline"> Applications in healthcare, education, and entertainment (e.g., sign language)<o:p></o:p></li></ul> Important Dates<o:p></o:p> <ul style="margin-top:0in;padding-inline-start:48px" type="disc"> <li class="MsoNormal" style="color:black;margin-top:11.0pt;text-align:justify;mso-list:l2 level1 lfo3;vertical-align:baseline"> Submission deadline: January 9, 2023 (Anywhere on Earth)<o:p></o:p></li><li class="MsoNormal" style="color:black;text-align:justify;mso-list:l2 level1 lfo3;vertical-align:baseline"> Notifications: January 20, 2023<o:p></o:p></li><li class="MsoNormal" style="color:black;text-align:justify;mso-list:l2 level1 lfo3;vertical-align:baseline"> Camera-ready deadline: January 27, 2023<o:p></o:p></li><li class="MsoNormal" style="color:black;text-align:justify;mso-list:l2 level1 lfo3;vertical-align:baseline"> Conference date: March 25-29, 2023<o:p></o:p></li><li class="MsoNormal" style="color:black;margin-bottom:11.0pt;text-align:justify;mso-list:l2 level1 lfo3;vertical-align:baseline"> Workshop date: March 25, 2023 (Shanghai time TBD)<o:p></o:p></li></ul> Instructions for Submissions<o:p></o:p> Authors are invited to submit a:<o:p></o:p> <ul style="margin-top:0in;padding-inline-start:48px" type="disc"> <li class="MsoNormal" style="color:black;text-align:justify;mso-list:l0 level1 lfo4;vertical-align:baseline"> Research paper: 4-6 pages + references<o:p></o:p></li><li class="MsoNormal" style="color:black;text-align:justify;mso-list:l0 level1 lfo4;vertical-align:baseline"> Work-in-progress paper: 2-3 pages + references<o:p></o:p></li></ul> Organizers:<o:p></o:p> <ul style="margin-top:0in" type="disc"> <li class="MsoNormal" style="color:black;margin-top:11.0pt;text-align:justify;mso-list:l1 level1 lfo5;vertical-align:baseline"> Zerrin Yumak (Utrecht University, The Netherlands)<o:p></o:p></li><li class="MsoNormal" style="color:black;text-align:justify;mso-list:l1 level1 lfo5;vertical-align:baseline"> Funda Durupinar (University of Massachusetts Boston, USA)<o:p></o:p></li><li class="MsoNormal" style="color:black;text-align:justify;mso-list:l1 level1 lfo5;vertical-align:baseline"> Oya Celiktutan (King’s College London, UK)<o:p></o:p></li><li class="MsoNormal" style="color:black;text-align:justify;mso-list:l1 level1 lfo5;vertical-align:baseline"> Pablo Cesar (CWI and TU Delft, The Netherlands)<o:p></o:p></li><li class="MsoNormal" style="color:black;text-align:justify;mso-list:l1 level1 lfo5;vertical-align:baseline"> Aniket Bera (Purdue University, USA)<o:p></o:p></li><li class="MsoNormal" style="color:black;text-align:justify;mso-list:l1 level1 lfo5;vertical-align:baseline"> Mar Gonzalez-Franco (Google Labs, USA)<o:p></o:p></li></ul> <o:p> </o:p> <o:p> </o:p> -- Dr. Zerrin Yumak | Assistant Professor of Human-Centered Computing, Founding member of the Departmental Diversity Committee,<o:p></o:p> Director of the Motion Capture and Virtual Reality Lab | <o:p> </o:p> Utrecht University | Department of Information and Computing Sciences | Princetonplein 5, 3584 CC Utrecht | Buys Ballot Building room 4.20 <o:p> </o:p> |+31 30 253 7578 | <a href="mailto:z.yumak@uu.nl">z.yumak@uu.nl</a> |www.zerrinyumak.com | Twitter: @zerrinyumak<o:p></o:p> <o:p> </o:p> </div> </body> </html>