The 3rd Vision-based Remote Physiological Signal Sensing (RePSS) Challenge & Workshop

Title: Towards Practical Remote Photoplethysmography Detector 

Abstract: Remote photoplethysmography (rPPG) is a promising enabling technology for many non-contact and non-invasive computer vision and healthcare applications, such as face presentation attack detection, heart rate and respiration rate estimation, and sleep disorder detection. While rPPG research has been performed for almost 20 years, there has been great success in the past few years. To develop such applications, one of the key factors is to develop a robust and accurate rPPG detector that is insensitive to illumination and human motion. In this talk, I will first review the development of rPPG detection and its applications. Then, I will share two recent research works on rPPG detection from my group. Finally, some future directions will be discussed. 

Bio: Pong C. Yuen received his B.Sc. in Electronic Engineering with first-class honours in 1989 from the City Polytechnic of Hong Kong and his Ph.D. in Electrical and Electronic Engineering in 1993 from The University of Hong Kong. He joined the Hong Kong Baptist University in 1993 and served as Head of the Department of Computer Science from 2011 to 2017. Currently, he is a Chair Professor in the Department of Computer Science and Associate Dean of the Science Faculty. Dr. Yuen has held key roles in international conferences and professional communities, including serving as Associate Editor of IEEE Transactions on Information Forensics and Security and Senior Editor of the SPIE Journal of Electronic Imaging. He is a Fellow of IAPR and has received prestigious awards such as the Natural Science Awards from Guangdong Province and the Ministry of Education, China. His research interests include biometric security and privacy, video surveillance, and medical informatics.

Title: InternVideo: A Multimodal Foundation Model for Video Understanding 

Abstract: How to build a foundation model for video understanding has become a very challenging task. This talk mainly introduces a multimodal foundation model InternVideo and the key technologies behind it, including the unimodal video self-supervised pre-training method of VideoMAE, the multimodal video weakly supervised pre-training method of UMT, and the video-centric chat model of VideoChat. At the same time, the multimodal video dataset InternVid and the multimodal video evaluation benchmark MVBench will also be introduced. Finally, we will discuss the future trend of multimodal video understanding foundation model. 

Bio: Limin Wang received the B.Sc. degree from Nanjing University, Nanjing, China, in 2011, and the Ph.D. degree from The Chinese University of Hong Kong, Hong Kong, in 2015. From 2015 to 2018, he was a Postdoctoral Researcher with the Computer Vision Laboratory, ETH Zürich. He is currently a Professor with the Department of Computer Science and Technology, Nanjing University. His research interests include computer vision and deep learning. He was the first runner-up at the ImageNet Large Scale Visual Recognition Challenge 2015 in scene recognition and the winner at the ActivityNet Large Scale Activity Recognition Challenge 2016 in video classification. He served as the Area Chair for CVPR, ICCV, and NeurIPS. He is on the Editorial Board of IJCV.

Title: Fine Grained 3D Face Reconstruction from a Single Image 

Abstract: 3D information is important in many computer vision tasks. This talk introduces the progress of 3D face recovery from a single image. We present a solution to capture the personalized shape so that the reconstructed shape looks identical to the corresponding person, including the data augmentation method, the many-to-one network and visual effect loss function. Furthermore, we show a method that reconstructs faces with extreme expressions. The facial part segmentation information is incorporated and a Part Re-projection Distance Loss (PRDL) is proposed to improve the reconstruction results. Experiments demonstrate good quantitative and qualitative performance in several databases. 

Bio: Zhen Lei received the B.S. degree in automation from the University of Science and Technology of China, in 2005, and the Ph.D. degree from the Institute of Automation, Chinese Academy of Sciences, in 2010, where he is currently a professor. He is IEEE/IAPR/AAIA Fellow. He has published over 200 papers in international journals and conferences with 31000+ citations in Google Scholar and h-index 82. He was the program co-chair of IJCB2023, was competition co-chair of IJCB2022 and has served as area chairs for several conferences and is associate editor for IEEE Transactions on Information Forensics and Security, IEEE Transactions on Biometrics, Behavior, and Identity Science, Pattern Recognition, Neurocomputing and IET Computer Vision journals. His research interests are in computer vision, pattern recognition, image processing, and face recognition in particular. He is the winner of 2019 IAPR Young Biometrics Investigator Award.