Title: A Machine Learning Approach to Visual Information Processing

Speaker: C.-C. Jay Kuo

University of Southern California

Time: December 18 (Wednesday), 3-4pm

Venue: 海韵科研一号楼310

Abstract: Machine learning has a long history, including techniques developed in the context of pattern recognition, neural nets, fuzzy logic, etc. It has blossomed in the last decade. There are two key ingredients for the success of the machine learning approach: 1) a sufficient amount of training data and 2) an efficient learning mechanism. Since this methodology heavily relies on training data, it is also called the data-driven approach. Due to the availability of a large amount of speech corpses and text data, we have witnessed a great progress in speech understanding and text data mining & search based on machine learning in recent years. There are quite a few image and video files available over the Internet nowadays, and they continue to grow in an amazing rate. Will we observe the same success in “data-driven visual information processing” in the coming decade? The future appears to be bright. In this talk, after a brief introduction, I will use two examples to explain the data-driven visual information processing methodology; namely, perceptual visual quality assessment and indoor/outdoor scene classification. Then, I will point out three major research problems in the near future: 1) information representation, 2) pedagogical development, and 3) context decision.

Research in US Universities: Overview and My Own Experience

December 18 (Wednesday), 4-5pm

I have often encountered questions such as “How to guide graduate students in their research?” “How do you run such a large research group at USC?” It is not easy to give simple answers to these questions since the success in graduate research depends on many factors, including motivation, ambition, problem selection, research environment, advisor’s guidance and feedback, dynamics of faculty-student interaction, paper writing and research presentation. Furthermore, many graduate students did not pay attention to effective management of their resource such as time, peers, professors, network resources, etc. If a graduate student can be more sensitive to his/her resource management, it is likely that he/she will do more solid research and graduate in a timely manner. The management skills become even more important, when a student starts to work after graduation. I received very little training in management myself in my graduate study. However, in my career path, I have gradually learned more management skills to meet several challenges. This knowledge will be very beneficial to all faculty members and graduate students, if they are sensitive to such a need in an early stage. In this talk, I will provide an overview on research in US high education systems, an introduction to the University of Southern California and, then, share my own experience at MIT and USC and my experience of running a large research group at USC. Quite a few learned lessons should be beneficial to faculty members as well as graduate students.

Biography of Speaker

 Dr. C.-C. Jay Kuo received the Ph.D. degree from the Massachusetts Institute of Technology in 1987. He is now with the University of Southern California (USC) as Professor of EE, CS and Mathematics. His research interests are in the areas of digital media processing, multimedia compression, communication and networking technologies, and embedded multimedia system design. Dr. Kuo is a Fellow of AAAS, IEEE and SPIE. Dr. Kuo has guided about 115 students to their Ph.D. degrees and supervised 20 postdoctoral research fellows. Currently, his research group at USC consists of around 30 Ph.D. students (see website http://viola.usc.edu), which is one of the largest academic research groups in multimedia technologies. He is a co-author of about 200 journal papers, 850 conference papers and 10 books. Dr. Kuo is a Fellow of AAAS, IEEE and SPIE. He is Editor-in-Chief for the IEEE Transactions on Information Forensics and Security and Editor Emeritus for the Journal of Visual Communication and Image Representation (an Elsevier journal). Dr. Kuo received the National Science Foundation Young Investigator Award (NYI) and Presidential Faculty Fellow (PFF) Award in 1992 and 1993, respectively. He received the best paper awards from the Multimedia Communication Technical Committee of the IEEE Communication Society in 2005, from the IEEE Vehicular Technology Fall Conference (VTC-Fall) in 2006, and from IEEE Conference on Intelligent Information Hiding and Multimedia Signal Processing (IIH-MSP) in 2006. He was an IEEE Signal Processing Society Distinguished Lecturer in 2006, a recipient of the Okawa Foundation Research Award in 2007, the recipient of the Electronic Imaging Scientist of the Year Award in 2010, and the holder of the Fulbright-Nokia Distinguished Chair in Information and Communications Technologies from 2010-2011.

主办：信息科学与技术学院

协办：软件学院