Visualizing Analyzing and Learning from Large-Scale Data
René Vidal, Johns Hopkins University
The past few years have witnessed an explosion in the availability of data from multiple sources and modalities. For example, millions of cameras have been installed in buildings, streets, airports and cities around the world, and people are using billions of handheld devices equipped with high-resolution cameras. This digital revolution has generated extraordinary advances on how to acquire, compress, store, share, transmit and process massive amounts of complex high-dimensional data. However, the automatic interpretation of such data has proven exceedingly difficult. For example, the human visual system is exquisitely sensitive to an enormous variety of shapes and motions. However, there is currently no computer vision system that can recognize objects and actions nearly as well as humans do. In this talk, I will briefly overview some of the recent advances in learning from large-scale data, such as images and videos.