授课教师：Stefano Berretti

国籍：意大利

职称：副教授

教师简介（中英文）：

Stefano Berretti，1997年在意大利佛罗伦萨大学获得电子工程硕士学位，2001年在佛罗伦萨大学获得信息与通信工程博士学位，2000年到2002年在佛罗伦萨大学获得博士后职位，2002年至2011年担任佛罗伦萨大学助理教授，自2011年以来，担任佛罗伦萨大学副教授，也是该校智能计算博士研究生学院的院长。Stefano Berretti于2019年担任里尔大学客座教授，2019年、2020年、2021和2022年担任阿尔伯塔大学客座研究员，还是喀拉拉邦数字科学、创新与技术大学计算机科学与工程学院的副教授（2021-2023年）。现在是 IEEE Trans. on Circuits and Systems and Video Technology和ACM Trans. on Multimedia Computing, Communications, and Applications 的副编辑。Stefano Berretti的研究兴趣集中在人脸和面部表情识别的3D计算机视觉方法、人类行为理解、3D和4D人脸重建和生成、形状分析的几何方法和建模，在国际期刊和会议发表了200多篇文章。

Stefano Berretti received the Master (Laurea) degree in Electronic Engineering in 1997 from University of Florence Italy, and the post-laurea Master in Multimedia Content Design, organized by the University of Florence, Radiotelevisione Italiana (RAI) and Tuscany Region, in 1998. He obtained his Ph.D. in Informatics and Telecommunication Engineering from the University of Florence in 2001 for his thesis on content-based image retrieval based on color and spatial arrangement. From 2000 to 2002 he got a postdoctoral position at the University of Florence, where his research focused on image retrieval and indexing. From 2002 to 2011 he was Assistant Professor at the University of Florence. Since 2011 he is an Associate Professor at the same University, where he is also the head of the Ph.D. School in Smart Computing. Stefano Berretti has been Visiting Professor at the University of Lille in 2019, and at the University of Alberta in 2019, 2020, 2021, and 2022. He is also Adjunct Professor at the School of Computer Science and Engineering (SoCSE), Kerala University of Digital Sciences, Innovation and Technology (2021-2023).

From 2016 to 2021, he was the Information Director of the ACM Trans. on Multimedia Computing, Communications, and Applications (ACM TOMM). He is now an associate editor of ACM TOMM, of the IEEE Trans. on Circuits and Systems and Video Technology, and the IeT Computer Vision journal.

The research interests of Stefano Berretti focus on 3D computer vision methods for face and facial expression recognition, human behavior understanding, face reconstruction and generation in 3D and 4D, geometric methods for shape analysis, and modeling. On these themes he has published over 200 articles in peer reviewed international journals and conference proceedings.

课程简介（中英文）：

本课程旨提供关于3D数据采集、处理和分析的当前技术、方法和算法。除此之外，还将介绍一些最新的3D数据深度学习解决方案，包括处理和分析用低分辨率相机获取的深度图像的方法，应用场景包括基于人脸、身体和人类行为理解的3D生物识别领域。主要涵盖以下主题：

（1）三维数据采集和处理基础。（2）用于三维形状和骨架分析的经典方法。（3）3D数据的深度学习。（3）三维数据的生成方法。

The idea of this course provide the students with a view on the current techniques, methods and algorithm for 3D data acquisition, processing, and analysis. In addition to this, it will cover some recent deep learning solutions for 3D data also including methods for processing and analyzing depth images acquired with low resolution cameras. The targeted applications will be in the area of 3D biometrics based on face and body and human behavior understanding. More in detail, we propose the following title for the course “Geometric Deep Learning for 3D Humans Behavior” with the aim to cover the following topics:

-Fundamentals of 3D data acquisition, and processing.

-Classical methods for 3D shape and skeleton analysis.

-Deep learning for 3D dataa.

-Generative methods for 3D data