I C I V I S
K E Y N O T E _ S P E A K E R S
Prof. Zhen Lei
Institute of Automation, Chinese Academy of Sciences


                                                                                                

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 29000+ citations in Google Scholar and h-index 81. 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.

Keynote Title: 3D Face Recovery and its Applications in Biometrics

Abstract
3D information is important in many computer vision tasks. This talk will firstly introduce the progress of 3D face recovery from a single image, including the traditional analysis-by-synthesis method and the deep learning based method. After that, it will describe how to generate fidelity face images with the help of 3D models, which can be used in many face analysis tasks, like face recognition, face anti-spoofing etc. Finally, it simply introduces the physical and digital face attack detection task and reports recent progress of fake face detection with 3D image decomposition, which provides new clues in this direction.

Prof. Junwei Han
Northwestern Polytechnical University


                                                                                                

Junwei Han is currently the Dean and a Professor in School of Automation, Northwestern Polytechnical University. His research interests include artificial intelligence, remote sensing image analysis, and brain pattern recognition. He has published more than 150 papers in top journals such as IEEE TPAMI, IJCV and so on and more than 30 papers in top conferences such as CVPR, ICCV, ACM Multimedia, MICCAI, IJCAI, etc. He is an Associate Editor for several international journals including IEEE TPAMI, IEEE TMM, and so on. He is a Fellow of IEEE and IAPR.

Keynote Title: Visual object detection in earth observation system: challenges and solutions

Abstract
With the rapid development of remote sensing technologies, more and more remote sensing images with high spatial resolution are available. How to achieve the detection of objects of interest is one of central issues for earth observation systems. In this talk, by analyzing the characteristics of high-spatial-resolution remote sensing images (e.g., data massiveness, object diversity, and environmental complexity) and the applications, we first summarize several key challenges needed to be solved for visual object detection techniques, including the automatic labeling of large number of training samples, the extraction of rotation-invariant and high-level image features and so on. Then, focusing on the above-mentioned problems, we introduce a series of solutions by our research group.