Towards Scalable Analysis of Images and Videos

Eric Xing, Carnegie Mellon University
Host: Suchi Saria

With the prevalence of mobile and wearable cameras and video-recorders, and global deployment of surveillance systems in space, air, sea, ground, and social network, the amount of unprocessed images and videos is massive, calling for a need for effective computational means for automatic analysis, understanding, summarization, and organization of visual data. In this talk, I will present some of our recent work on scalable machine learning approaches to image and video understanding. Specifically, I will focus on structured multitask methods for large-scale image classification, and online latent space methods for video analysis and summarization.

This is joint work with Bin Zhao.

Speaker Biography

Dr. Eric Xing is a Professor of Machine Learning in the School of Computer Science at Carnegie Mellon University. His principal research interests lie in the development of machine learning and statistical methodology; especially for solving problems involving automated learning, reasoning, and decision-making in high-dimensional, multimodal, and dynamic possible worlds in social and biological systems. Professor Xing received his Ph.D. in Computer Science from UC Berkeley. He is an associate editor of the Annals of Applied Statistics (AOAS), the Journal of American Statistical Association (JASA), the IEEE Transaction of Pattern Analysis and Machine Intelligence (PAMI), the PLoS Journal of Computational Biology, and an Action Editor of the Machine Learning Journal (MLJ), the Journal of Machine Learning Research (JMLR). He is a member of the DARPA Information Science and Technology (ISAT) Advisory Group, and a Program Chair of ICML 2014.