Title: Learning to synthesize 3D face and human interactions
30 May 2024
Abstract
This talk summarizes a number of aspects of 3D human face generation and body motion generation. I will first present our recent results on 3D and 4D face synthesis. We propose a new model that generates transitions between different expressions, and synthesizes long and composed 4D expressions. Second, I will present results on two-person interactions synthesis, a crucial element for designing 3D human motion synthesis frameworks. it can open up a wide variety of new applications in entertainment media, interactive mixed and augmented reality, human-AI interaction, and social robotics.
Biography
Mohamed Daoudi is a Full Professor of Computer Science at IMT Nord Europe and the Head of Image group at CRIStAL Laboratory (UMR CNRS 9189). His research interests include computer vision and machine learning for human behavior understanding. He has published over 150 papers in some of the most distinguished scientific journals and international conferences. He is/was Associate Editor of Image and Vision Computing, IEEE Transactions on Multimedia, IEEE Trans. on Affective Computing and Computer Vision and Image Understanding, Computers & Graphics, Guest Editor for Computer Vision and Image Understanding Special Issue on “Special Issue-Eyes on People Recent Trends on Human Analysis, Perception and Generation-CVIU”, Guest Editor for Image and Vision Computing On “Learning with Manifolds in Computer Vision”, Guest Editor for Sensors “Computer Vision in Human Analysis: From Face and Body to Clothes”, and Guest Editor for IEEE Transactions on Biometrics, Behavior and Identity Science on “Selected Best Works From Automated Face and Gesture Recognition 2019”. He was General Chair of IEEE International Conference on Automatic Face and Gesture Recognition IEEE FG 2019 in Lille (France), 3D Object Retrieval Symposium (2010, 2022, 2023), Shape Modeling International Conference (2015), has organized successful workshops in Face and Gesture Analysis for Health Informatics (FGAHI at CVPR 2023, ICMI 2020, CVPR 2019, FG 2018), Learning with few or without annotated face, body and gesture data (LFA at WACV 2023, IEEE FG 2024), Generation of Human Face and Body Behavior (GHB at WACV 2021, ICIAP 2023), Towards a Complete Analysis of People: From Face and Body to Clothes (T-CAP at ICIAP 2022, ICPR 2022, ECCV 2022), Manifold Learning, From Euclid to Riemann (ManLearn at ICPR 2021, ICCV 2017), and has served as area chair at 3DV 2021, IEEE FG 2024, ACM Multimedia (2021, 2022, 2023, 2024), EUSIPCO (2013, 2015), and he will serve as General Chair for IEEE FG 2025. He is a Fellow of the International Association for Pattern Recognition, IEEE Senior member, ACM member.