Guosheng Hu, Yandong Guo, Lei Zhang
Face recognition is a task that humans perform routinely and effortlessly in our daily lives. Wide availability of computer systems (powerful cloud or low-cost edge devices) has created an enormous interest in automatic processing of face images in a variety of applications, including biometric authentication, surveillance, human-computer interaction, and multimedia management. In this tutorial, we will present the research interests and milestone works of face recognition in different periods, including the traditional solutions (e.g. handcrafted features), state of the art methods (e.g. deep learning) and the future research directions in this field. Apart from the advances of face recognition in academia, the tutorial will introduce the industrial progressions and the open questions of face recognition in industry. First, Dr. Guosheng Hu will introduce the research advances of a fully automatic face recognition pipeline, including face detection, face alignment and face feature extraction. Then Dr. Yandong Guo will present how to improve driving experience based on facial analysis, including recognition, expression analysis, gaze detection, etc. Dr. Lei Zhang will demonstrate how to leverage the public dataset (MS-Celeb-1M) to train powerful face recognition models and cutting-edge technologies to transfer the learnings from public datasets to industrial applications. Finally, the open questions of face recognition from industry will be proposed for discussion. The major topics are:
- Face recognition pipeline
- Face recognition and analysis in the driving scenario
- MS-Celeb-1M: A large scale public dataset for face
Guosheng Hu is a senior research scientist in AnyVision and an honorary assistant professor at Queens University of Belfast, UK. Before he joined AnyVision, he was a research fellow in the THOTH team, Inria Grenoble Rhone-Alpes, France. He finished his PhD under the supervision of Prof. Josef Kittler in Centre for Vision, Speech and Signal Processing, University of Surrey, UK. His research interests include deep learning, pattern recognition, and biometrics (mainly face recognition). In particular, he has worked on 2D and 3D face recognition for around 10 years in academia and industry. He has published many face recognition related papers in mainstream conferences (ICCV, ECCV, AAAI, ICASSP, BMVC, ICB, IJCB, etc) and journals (TIP, PR, etc). He served as a program committee member of CVPR, ECCV, AAAI, IJCAI, BMVC, FG, etc. He works as a regular reviewer for journals TPAMI, IJCV, TIP, etc.
Yandong Guo is the chief scientist of XPeng Motors (Xiaopeng Qiche) and the vice president leading the artificial intelligent center. Currently, his mission is to improve the driving experience based-on the intelligent system including vision recognition, speech recognition, and natural language processing. Before he joined XPeng Motors, he was a researcher at Microsoft AI & Research, Redmond WA in the United States. His research interests were mainly in the machine intelligence areas including computer vision and deep learning. He was one of the key contributors to the Microsoft cognitive service, connected car project, Microsoft image search, and Microsoft Knowledge graph. Yandong Guo earned his Ph.D. in electrical and computer engineering at Purdue University at West Lafayette, under the supervision of Prof. Charles Bouman and Prof. Jan Allebach. Before that, he received his B.S. and M.S. degree in ECE from Beijing University of Posts and Telecommunications, China, in 2005 and 2008, receptively. He serves as reviewer/committee member for conferences including ICML, NIPS, CVPR, ACM MM, ICIP, ICASSP, ICME, TIP, TCI, TMM, SPIE EI, IJCAI, etc.
Lei Zhang is a principal researcher and research manager in Microsoft AI & Research, leading a team working on visual recognition and computer vision. Prior to this, he has worked with Microsoft Research Asia for 12 years as a senior researcher, leading a research team working on visual recognition, image analysis, and large-scale data mining. His years of work on large-scale, search-based image annotation has generated many practical impacts in multimedia search, including a highly scalable solution of duplicate image clustering for billions of images. From 2013 to 2015, he moved to Bing Multimedia Search as a principal development manager, helping develop cutting-edge solutions for web-scale image analysis and recognition problems, including image caption generation and high precision image entity linking. Lei is a senior IEEE member and a senior ACM member, and has served as editorial board members for Multimedia System Journal, as program co-chairs, area chairs, or committee members for many top conferences. He is the author or co-author of 100+ published papers in fields such as multimedia, computer vision, web search and information retrieval, and holds 40+ U.S. patents for his innovation in these fields. Lei earned all his degrees (B.E., M.E., and Ph.D) in Computer Science from Tsinghua University, and currently also holds an adjunct professor position in Tianjin University