Hilton San Francisco
San Francisco, California, United States
8 - 12 February 2015
Plenary Events
Plenary Session and Society Award Presentations
Date: Tuesday 10 February 2015
Time: 8:30 AM - 9:50 AM
Analyzing Social Interactions through Behavioral Imaging

James M. Rehg, Georgia Institute of Technology (United States)

Abstract: Beginning in infancy, individuals acquire the social and communication skills that are vital for a healthy and productive life. Children with developmental delays face great challenges in acquiring these skills, resulting in substantial lifetime risks. Children with an Autism Spectrum Disorder (ASD) represent a particularly significant risk category, due both to the increasing rate of diagnosis of ASD and its consequences. Since the genetic basis for ASD is unclear, the diagnosis, treatment, and study of the disorder depends fundamentally on the observation of behavior. In this talk, I will describe our research agenda in Behavioral Imaging, which targets the capture, modeling, and analysis of social and communicative behaviors between children and their caregivers and peers. We are developing computational methods and statistical models for the analysis of vision, audio, and wearable sensor data. Our goal is to develop a new set of capabilities for the large-scale collection and interpretation of behavioral data. I will describe several research challenges in multi-modal sensor fusion and statistical modeling which arise in this area, and present illustrative results from the analysis of social interactions with children and adults.

Biography: James M. Rehg is a Professor in the School of Interactive Computing at the Georgia Institute of Technology, where he is co-Director of the Computational Perception Lab and is the Associate Director for Research in the Center for Robotics and Intelligent Machines. He received his Ph.D. from CMU in 1995 and worked at the Cambridge Research Lab of DEC (and then Compaq) from 1995-2001, where he managed the computer vision research group. He received an NSF CAREER award in 2001 and a Raytheon Faculty Fellowship from Georgia Tech in 2005. He and his students have received a number of best paper awards, including best student paper awards at ICML 2005 and BMVC 2010. Dr. Rehg serves on the Editorial Board of the International Journal of Computer Vision, and he served as the General co-Chair for CVPR 2009. He has authored more than 100 peer-reviewed scientific papers and holds 23 issued U.S. patents. His research interests include computer vision, medical imaging, robot perception, machine learning, and pattern recognition. Dr. Rehg is currently leading a multi-institution effort to develop the science and technology of Behavior Imaging— the capture and analysis of social and communicative behavior using multi-modal sensing, to support the study and treatment of developmental disorders such as autism.
Plenary Session and Conference Award Presentations
Date: Wednesday 11 February 2015
Time: 8:30 AM - 9:50 AM
What Makes Big Visual Data Hard?

Alexei (Alyosha) Efros, University of California, Berkeley (United States)

Abstract: There are an estimated 3.5 trillion photographs in the world, of which 10% have been taken in the past 12 months. Facebook alone reports 6 billion photo uploads per month. Every minute, 72 hours of video are uploaded to YouTube. Cisco estimates that in the next few years, visual data (photos and video) will account for over 85% of total internet traffic. Yet, we currently lack effective computational methods for making sense of all this mass of visual data. Unlike easily indexed content, such as text, visual content is not routinely searched or mined; it's not even hyperlinked. Visual data is Internet's "digital dark matter" [Perona,2010] -- it's just sitting there! In this talk, I will first discuss some of the unique challenges that make Big Visual Data difficult compared to other types of content. In particular, I will argue that the central problem is the lack a good measure of similarity for visual data. I will then present some of our recent work that aims to address this challenge in the context of visual matching, image retrieval, visual data mining, and interactive visual data exploration.

Biography: Alexei (Alyosha) Efros joined UC Berkeley in 2013 as associate professor of Electrical Engineering and Computer Science. Prior to that, he was nine years on the faculty of Carnegie Mellon University, and has also been affiliated with École Normale Supérieure/INRIA and University of Oxford. His research is in the area of computer vision and computer graphics, especially at the intersection of the two. He is particularly interested in using data-driven techniques to tackle problems which are very hard to model parametrically but where large quantities of data are readily available. Alyosha received his PhD in 2003 from UC Berkeley. He is a recipient of CVPR Best Paper Award (2006), NSF CAREER award (2006), Sloan Fellowship (2008), Guggenheim Fellowship (2008), Okawa Grant (2008), Finmeccanica Career Development Chair (2010), SIGGRAPH Significant New Researcher Award (2010), ECCV Best Paper Honorable Mention (2010), and the Helmholtz Test-of-Time Prize (2013).
Back to Top