Visit ShanghaiTech University | 中文 | How to find us
HOME > News and Events > Seminars
Limited-Data Driven Inference for Computer Vision
Date: 2016/8/19             Browse: 466

Limited-Data Driven Inference for Computer Vision

Speaker: Mei Chen

Time: Aug 19, 3:30pm - 4:30pm.

Location: Room 410, Teaching Building


The past fifteen years have seen a revolution in computer vision which has come from embracing data as a primary source of information in solving complex inference problems. The spatio-temporal structure of a class of images can be implicitly constrained and defined by a well-chosen annotated dataset. This paradigm has led to impressive gains in a number of key areas, due in part to the power of modern machine learning methods when applied to big data. However, often times it is not only tedious but impracticable to annotate large numbers of training examples in necessary detail, as is the case for biomedical imaging. Working with minimalistic annotations on limited data may be a more plausible solution. These observations have motivated my work on data-driven inference, where a consistent thread is the incorporation of key insights from the problem domain which constrain and bias the learning problem, and lead to effective performance given limited training data and minimal annotation.


Mei Chen is an Associate Professor in the Computer Engineering Department at the State University of New York, Albany. Between 2011 and 2014, she built and led the Intel Science & Technology Center on Embedded Computing that sponsored more than sixty faculty and students from Carnegie Mellon, Cornell, Georgia Tech, Penn State, UC Berkeley, UIUC, UPenn, and University of Washington for research in perception, machine learning, robotics, and embedded architecture. Previously she held research lead positions at Intel Labs, HP Labs, and SRI Sarnoff. Mei’s work in computer vision and biomedical imaging were nominated finalists for 6 Best Paper Awards and won 3. While at HP Labs, she successfully transferred her research in computational photography to 5 hardware and software products. She earned a Ph.D. in Robotics from the School of Computer Science at Carnegie Mellon University, and a M.S. and B.S. from Tsinghua University in Beijing, China.


SIST-Seminar 16062