Embedded Files
C.-C. Jay Kuo 郭宗杰
C.-C. Jay Kuo 郭宗杰
William M. Hogue Professor, University of Southern California, U.S.A.
r. 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 William M. Hogue Professor, Distinguished Professor of Electrical and Computer Engineering and Computer Science, and Director of the Media Communications Laboratory. His research interests are in visual computing and communication. He is a Fellow of AAAS, NAI, IEEE, and SPIE and an Academician of Academia Sinica.
Dr. Kuo’s research activities lie in multimedia and green computing. He is a co-author of 330 journal papers, 980 conference papers, 30 patents, and 15 books. He delivered 40 keynote speeches and 750 invited lectures at conferences, research institutes, universities, and companies. Dr. Kuo has received a few awards for his 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 2019 IEEE Computer Society Edward J. McCluskey Technical Achievement Award, the 2019 IEEE Signal Processing Society Claude Shannon-Harry Nyquist Technical Achievement Award, the 72nd annual Technology and Engineering Emmy Award (2020), and the 2021 IEEE Circuits and Systems Society Charles A. Desoer Technical Achievement Award.
Dr. Kuo was Editor-in-Chief for the IEEE Transactions on Information Forensics and Security (2012-2014) and the Journal of Visual Communication and Image Representation (1997-2011). He is currently the Editor-in-Chief for the APSIPA Trans. on Signal and Information Processing (2022-2023). He has guided 164 students to their Ph.D. degrees and supervised 31 postdoctoral research fellows.
Interpretable and Low-Power 3D Point
Cloud Computing
Interpretable and Low-Power 3D Point
Cloud Computing
3D point cloud processing finds rich applications in future computing, such as computer-aided design, 3D printing, autonomous driving, etc. Most state-of-the-art point cloud processing methods are based on deep learning. Although they outperform traditional methods in accuracy, they demand higher training complexity. Besides, they lack mathematical transparency. I will present interpretable and low-power computing methods for point cloud registration, classification, and segmentation. First, an unsupervised registration method that extracts salient points for matching is presented. Second, an unambiguous way to order points sequentially in a point cloud set is developed. Then, their spatial coordinates can be treated as geometric attributes of a 1D data array. This idea facilitates the classification task. Third, we show how to leverage prior knowledge of point clouds to derive an intuitive and effective method for the segmentation task. Extensive experiments are conducted to demonstrate the performance of the three new methods.
Page updated
Report abuse