Katsaggelos Delivers Plenary Talk at 2016 IEEE Southwest Symposium on Image Analysis and Interpretation
He lectured on "Learning for Future Video."
Prof. Aggelos K. Katsaggelos gave a Plenary Talk at the 2016 IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI), held March 7, 2016 on "Learning for Future Video."
Abstract: Learning has made it possible to unleash the power of data. We have moved away from the detailed modeling of a system or a phenomenon of interest thanks to the abundance of data as well as the huge improvements in processing power. With approaches like dictionary learning we can discover linear relationships between the input and output. On the other hand, recent advancements in deep learning have made it possible to discover non-linear relationships. As one of the examples in this talk we discuss the application of dictionary and deep learning to the video super-resolution problem. We describe a multiple-frame algorithm based on dictionary learning and motion estimation. We further describe the use of a convolutional neural network that is trained on both the spatial and temporal dimensions of videos to enhance their resolution. We demonstrate experimentally the effectiveness of these approaches. We finally discuss future research directions on the topic of learning.
The Southwest Symposium on Image Analysis and Interpretation (SSIAI) is a biennial conference dedicated to all aspects of computational analysis and interpretation of images and video. SSIAI brings together researchers and practitioners in academia, industry, and government to share and discuss the latest advances in this field. SSIAI 2016 will be held at the historic La Fonda Hotel in Santa Fe, New Mexico, USA. The symposium seeks original contributions reporting novel research directions, results, and applications.