Institute of Information Science, Academia Sinica

Acknowledging the tremendous contributions deep learning (DL) made to a broad range of image, video and multimedia processing tasks, further optimizing quality of the DL-based features has consistently presented a challenge, especially when working with multi-view data, arguably the most natural data format. Though DL models have been hotly pursued to address this issue, no clear breakthroughs at the foundational level have been witnessed. In this talk, we present recent development from a significantly different perspective, mathematics-inspired models with a lightweight neural network (NN) twist; an approach clearly goes beyond deep learning paradigm. Particularly, we call upon a natural multi-view processing architecture, discriminant correlation analysis, setting the stage for the development of an innovative platform. Due to its power to handle information with multiple views, the platform is termed as discriminant multiple correlation (DMC) analysis. Depending on the nature of the data sources to work with, DMC features two distinct designs, one with a perceptron-style NN (PNN), and the other with a convolution-style NN (CNN). Statistics collected from experiments of numerous multi-view analysis and recognition benchmarks evidently show that the MI models not only generate impressive (sometimes unprecedented) performance accuracies, but much faster processing speed comparing with contemporary DL-based fusion models.

Dr. Ling Guan received his Ph.D. Degree from University of British Columbia, Canada. From 1992 to 2001, he was on the Faculty of Engineering, University of Sydney, Australia. Dr. Guan served as a Tier I Canada Research Chair in Multimedia and Computer Technology and a Professor of Electrical and Computer Engineering at Ryerson University/Toronto Metropolitan University, Toronto, Canada. He is the founding director of Ryerson/TMU Multimedia Research Lab and Centre for Interactive Multimedia Information Mining. Dr. Guan has been working on image, video and multimedia signal processing, human-computer interaction, pattern recognition and machine intelligence, and published extensively in the field. He has served on half a dozen editorial boards of IEEE Transactions and Magazines and chaired the 2006 IEEE International Conference on Multimedia and Expo in Toronto. He played the leading role in the inauguration of IEEE Pacific-Rim Conference on Multimedia in 2000 and served as the Founding General Chair. Dr. Guan is a Life Fellow of the IEEE, a Fellow of the Canadian Academy of Engineering and the Engineering Institute of Canada. He is an IEEE Circuits and System Society Distinguished Lecturer and a recipient of the 2005 IEEE Transactions on Circuits and Systems for Video Technology Best Paper Award. Dr. Guan is the awardee of the 2014 IEEE Canada C.C. Gotlieb Medel for his contributions to computer science and engineering.