摘要:Convolutional neural networks (CNNs) trained with deep learning have been widely used in various classification, localization, detection, segmentation, as well as for data synthesis and characteristics transform, etc.

In this talk, I will review the recent evolutions of these CNNs, from classification driven CNNs (such as AlexNet, VGG), to their extended version of localization regression CNNs, then detection CNNs (such as R-CNN, Fast R-CNN, Faster R-CNN, SSD and Yolo), to segmentation CNNs (such as fully CNN U-Net), and eventually to synthesis CNNs (such as GAN) as well as transfer CNN (such as Cycle-GAN). I will then discuss what are the main features enable these CNNs to be able to successfully and effectively serve as the universal functional approximation tools for so many applications.

该讲座为前沿讲座，欢迎全校师生踊跃参加。

Normal0false7.8 磅02falsefalsefalseEN-USZH-CNX-NONE附主讲人简介：

Dr. Jenq-Neng Hwang received the BS and MS degrees, both in electrical engineering from the National Taiwan University, Taipei, Taiwan, in 1981 and 1983 separately. He then received his Ph.D. degree from the University of Southern California. In the summer of 1989, Dr. Hwang joined the Department of Electrical Engineering of the University of Washington in Seattle, where he has been promoted to Full Professor since 1999. He served as the Associate Chair for Research from 2003 to 2005, and from 2011-2015. He is currently the Associate Chair for Global Affairs and International Development in the EE Department. He has written more than 330 journal, conference papers and book chapters in the areas of machine learning, multimedia signal processing, and multimedia system integration and networking, including an authored textbook on "Multimedia Networking: from Theory to Practice," published by Cambridge University Press. Dr. Hwang has close working relationship with the industry on multimedia signal processing and multimedia networking.

Dr. Hwang received the 1995 IEEE Signal Processing Society's Best Journal Paper Award. He is a founding member of Multimedia Signal Processing Technical Committee of IEEE Signal Processing Society and was the Society's representative to IEEE Neural Network Council from 1996 to 2000. He is currently a member of Multimedia Technical Committee (MMTC) of IEEE Communication Society and also a member of Multimedia Signal Processing Technical Committee (MMSP TC) of IEEE Signal Processing Society. He served as associate editors for IEEE T-SP, T-NN and T-CSVT, T-IP and Signal Processing Magazine (SPM). He is currently on the editorial board of ZTE Communications, ETRI, IJDMB and JSPS journals. He served as the Program Co-Chair of IEEE ICME 2016 and was the Program Co-Chairs of ICASSP 1998 and ISCAS 2009. Dr. Hwang is a fellow of IEEE since 2001.

Normal07.8 磅02falsefalsefalseEN-USZH-CNX-NONE