Event Location: NSH 1507
Bio: Jia Li is a research scientist at Yahoo! Research. She leads the Visual Computing and Learning Group. Her research interests are computer vision, machine learning，social network analysis and multimedia analysis. She received her Ph.D. degree from the Computer Science Department at Stanford University. She is the leader of the OPTIMOL team, which won the first prize in the Semantic Robotics Vision Challenge in 2007. She served as the volunteers chair in CVPR 2010， travel funding committee for ACM Multimedia Systems 2014 and area chair for WACV 2015. She has been serving as the associate editor of the Visual Computer: International Journal of Computer Graphics. In 2014, she is selected as the Super Star winner at Yahoo!, the highest award at the company.

Abstract: One of the most exciting revolutions in recent human history is the information revolution. The largest component of the digital universe is images, captured by more than billions of devices in the world, from digital cameras and camera phones to medical scanners and security cameras. With this exponential growth of image data, an important question that faces today’s computer engineers and scientists is how to take advantage of this resource to further human knowledge and advance human society. Such research has applications for inferring social interaction through seamless sharing photos, automatic multimedia library indexing, retrieval and organization, educational, and clinical assistive technology, and security systems. In this talk, I am going to talk about the large scale visual recognition research and efforts on real-world image understanding. I will give a brief review of the research on modeling real world images for a number of fundamental tasks related to object detection, image classification and social network analysis to extract the useful information from images. The algorithms have been well tested both on large scale academic research dataset as well as real-world data such as user photos, celebrity images and product data. I show striking performance of our approaches on large scale visual recognition problems. The fundamental research algorithms also demonstrate significant impact on real-world products and user experience.