Time+Place: Monday 28/03/2016 14:30 Room NOTE CHANGE OF ROOM Auditorium 2 Taub Bld.
Title: Your phone can and should do all the image/video processing and machine learning you need: Child Development Screening for Everybody
Speaker: Prof. Guillermo Sapiro - DISTINGUISHED POLLAK LECTURE SERIES http://ece.duke.edu/faculty/guillermo-sapiro
Affiliation: Edmund T. Pratt, Jr. School Professor of Electrical and Computer Engineering, Duke University
Host: Prof. Ron Kimmel, Prof. Michael Elad and Prof. Alfred M. Bruckstein


Pollak Distinguished Lecture Series 2016

1st Lecture -  March 28, 2016, 14:30,  Auditorium 2, Taub

Your phone can and should do all the image/video processing and machine 
learning you need: Child Development Screening for Everybody


Let us start with some incredible and very sad numbers:

- 1 in 9 children have the need for intervention due to developmental 

- The waiting time for an autism expert in top hospitals in the US is 
about 1 year.

- Autism is diagnosed on average 4 years later than what is possible.

- In Africa there are 50 experts to attend 1/2 billion children.

Then we ask ourselves, how can we solve this? In this talk we will 
describe how we are using technology to develop fast and reliable 
screening methods for child development and mental health, in particular 
autism. We use the fact that phones have screes, cameras, and a small 
super-computer, all integrated in one device.

We will share our technology, experience, and results. These come from 
extensive testing in a pediatric clinic in Duke Hospital as well as with 
the internationally deployed Autism&Beyond iOS app.

The lecture is self-contained and dedicated to all that have an interest 
in helping humanity, in revolutionizing child health care, and also 
maybe in technology for health-care.

This work is the result of close collaboration with a large 
interdisciplinary team to be described in the talk.


2nd Lecture -  March 30, 2016, 14:30, Taub 337  

Your phone can and should do all the image/video processing and machine 
learning you need: Video Enhancement and Face Recognition


We live in the era of big data, and while big data is helping to address 
very important challenges, it comes at a significant cost. For example, 
the leading results in face recognition report using hundreds of 
millions of labeled data (yes, hundreds of millions) and training in 
some of the largest supercomputers for several hundred hours. Then, the 
trained systems are so big that they need special computers to store 
their parameters. While these aspects are not of concern for very 
important applications, they are for many of our daily tasks.

Intellectually, if we decide to operate under limited resources, we open 
the door to new technologies and developments.

We will illustrate an approach to do face recognition on your mobile 
device, achieving state-of-the-art results while using several orders of 
magnitude less data (only in the thousands) and training (only minutes 
on a desktop) than current state-of-the-art. We will also show how to 
solve the problem of camera shake via a trivial algorithm (FFT is 
back!). Both examples illustrate that a bit of thinking can save several 
tera bytes of data and programming.

The work is the result of close collaborations with Qiang Qiu, Mauricio 
Delbracio, and Alex Bronstein.


Short Bio:

Guillermo Sapiro received his B.Sc. (summa cum laude), M.Sc., and Ph.D. from 
the Department of Electrical Engineering at the Technion, Israel Institute of
Technology, in 1989, 1991, and 1993 respectively. After post-doctoral research 
at MIT, Dr. Sapiro became Member of Technical Staff at the research facilities of
HP Labs in Palo Alto, California. He was with the Department of Electrical and 
Computer Engineering at the University of Minnesota, where he held the position of
Distinguished McKnight University Professor and Vincentine Hermes-Luh Chair in 
Electrical and Computer Engineering. Currently he is the Edmund T. Pratt, Jr.
School Professor with Duke University.

G. Sapiro works on theory and applications in computer vision, computer graphics, 
medical imaging, image analysis, and machine learning. He has authored and
co-authored over 300 papers in these areas and has written a book published by 
Cambridge University Press, January 2001.

G. Sapiro was awarded the Gutwirth Scholarship for Special Excellence in Graduate 
Studies in 1991,  the Ollendorff Fellowship for Excellence in Vision and Image
Understanding Work in 1992,  the Rothschild Fellowship for Post-Doctoral Studies in 
1993, the Office of Naval Research Young Investigator Award in 1998, the Presidential 
Early Career Awards for Scientist and Engineers (PECASE) in 1998, the National Science 
Foundation Career Award in 1999, and the National Security Science and Engineering 
Faculty Fellowship in 2010. He received the test of time award at ICCV 2011.
G. Sapiro is a Fellow of IEEE and SIAM.
G. Sapiro was the founding Editor-in-Chief of the SIAM Journal on Imaging Sciences.

Refreshments will be served from 14:00
Lecture starts at 14:30