(tentative, in alphabetical order)
C.-C. Jay Kuo
University of Southern California, USA
Title: Resolving the Gap between Image Pixels and Semantics: Yesterday, Today and Tomorrow
Abstract: How to resolve the gap between low-level signals and high-level semantics has been a long-standing problem for several decades. For example, earlier image retrieval work focused on similarities of low-level features such as color, shape and texture, which can be derived from image pixels easily, with limited success since they do not capture semantic meaning of images well. We have witnessed breakthrough in narrowing down the gap between signals and semantics in recent years due to the rapid development of deep learning technologies. Deep neural networks provide a mapping from the image pixel domain to the semantic domain (e.g. object recognition, semantic segmentation, etc.) through a large number of training samples with human labels. It is proper to say that it is human labeling effort that narrows down the semantic gap. Most deep learning systems are heavily supervised. Yet, a powerful AI system should be able to learn under the weak supervision setting with much fewer training samples. The capability of a pure data-driven solution is limited. It is time to revisit the idea of integrating the traditional knowledge-driven (or rule-based) and the modern data-driven approaches so as to benefit from both. New research directions along this line will be presented.
Bio: Dr. C.-C. Jay Kuo received his Ph.D. degree from the Massachusetts Institute of Technology in 1987. He is now with the University of Southern California (USC) as Director of the Media Communications Laboratory and Distinguished Professor of Electrical Engineering and Computer Science. His research interests are in the areas of visual computing and communication. He is a Fellow of AAAS, IEEE and SPIE. Dr. Kuo’s research interests are in the areas of multimedia computing and data science and engineering. He has received numerous awards for his outstanding research contributions, including the 2010 Electronic Imaging Scientist of the Year Award, the 2010-11 Fulbright-Nokia Distinguished Chair in Information and Communications Technologies, the 2011 Pan Wen-Yuan Outstanding Research Award, the 2019 IEEE Computer Society Edward J. McCluskey Technical Achievement Award, the 2019 IEEE Signal Processing Society Claude Shannon-Harry Nyquist Technical Achievement Award and the 2020 IEEE TCMC Impact Award. Dr. Kuo has guided 155 students to their PhD degrees and supervised 30 postdoctoral research fellows. His educational achievements have won a wide array of recognitions such as the 2016 IEEE Computer Society Taylor L. Booth Education Award, the 2016 IEEE Circuits and Systems Society John Choma Education Award, the 2016 IS&T Raymond C. Bowman Award, the 2017 IEEE Leon K. Kirchmayer Graduate Teaching Award, the 2017 IEEE Signal Processing Society Carl Friedrich Gauss Education Award, and the 2018 USC Provost’s Mentoring Award.
University of California, Los Angeles, USA