Plenary Speakers

Monday, September 18
9:00-10:00

Michael Elad
Professor of Computer Science at the Technion

Sparse Modeling in Image Processing and Deep Learning 
Sparse approximation is a well-established theory, with a profound impact on the fields of signal and image processing. In this talk we start by presenting this model and its features, and then turn to describe two special cases of it – the convolutional sparse coding (CSC) and its multi-layered version (ML-CSC).  Amazingly, as we will carefully show, ML-CSC provides a solid theoretical foundation to … deep-learning. Alongside this main message of bringing a theoretical backbone to deep-learning, another central message that will accompany us throughout the talk: Generative models for describing data sources enable a systematic way to design algorithms, while also providing a complete mechanism for a theoretical analysis of these algorithms' performance. This talk is meant for newcomers to this field - no prior knowledge on sparse approximation is assumed.

Michael Elad

Michael Elad holds a B.Sc. (1986), M.Sc. (1988) and D.Sc. (1997) in Electrical engineering from the Technion, Israel Institute of Technology. After several years in industrial research, Michael served as a research associate at Stanford University during 2001-2003, working closely with Prof. Gene Golub (CS), Prof. Peyman Milanfar (EE-UCSC), and Prof. David L. Donoho (Statistics). Since 2003 he holds a permanent faculty position in the Computer Science Department at the Technion. Michael works in the field of signal and image processing, specializing in particular on inverse problems and sparse representations. He has authored hundreds of technical publications in leading venues, many of which have led to exceptional impact. He is the author of the 2010's book "Sparse and Redundant Representations: From Theory to Applications in Signal and Image Processing", which is a leading publication in this field. He has served as an Associate Editor for IEEE-TIP (2007-2011), IEEE-TIT (2011-2014), ACHA (2012-2015), and SIAM Imaging Sciences - SIIMS (2010-2015). He held a senior editorial role for IEEE-SPL (2012-2014), and since January 2016, he is serving as the Editor-in-Chief for SIIMS. Michael received numerous teaching and research awards and grants. He was awarded an ERC advanced grant in 2013. He is the recipient of the 2008 and 2015 Henri Taub Prizes for academic excellence, and the 2010 Hershel-Rich prize for innovation. Michael is an IEEE Fellow since 2012.


Tuesday, September 19
9:00-10:00

Song-Chun Zhu 
Professor of Statistics and Computer Science at UCLA
 
A Tale of Three Families: Descriptive, Generative and Discriminative Models
Representations of images, in general, belong to three probabilistic families, developed for different regimes of data and tasks. (i) Descriptive models, originated from statistical physics, reproduce certain statistical regularities in data, and are often suitable for patterns in the high entropy regime, such as MRF, Gibbs and FRAME. (ii) Generative models, originated from harmonic analysis, seek latent variables and dictionaries to explain data in parsimonious representations, and are often more effective for the low entropy regime, such as sparse models and auto-encoders. (iii) Discriminative models are often trained by statistical regression for classification tasks. This talk will start with the Julesz quest on texture and texton representations in the 1960s, and then review the developments, interactions and integration of these model families in the recent deep learning era, such as the adversary and cooperative models. Then the talk will draw a unification of these models in a continuous entropy spectrum in terms of information scaling. Finally, the talk will discuss future directions in developing cognitive models for representations beyond deep learning, i.e. modeling the task-oriented cognitive aspects, such as functionality, physics, intents and causality, which are the invisible “dark matter”, by analogy to cosmology, in human intelligence.

Song-Chun Zhu

 

Song-Chun Zhu received a Ph.D. degree from Harvard University in 1996. He is Professor of Statistics and Computer Science at UCLA, and Director of the UCLA Center for Vision, Learning, Cognition and Autonomy (VCLA@UCLA).  His work in computer vision received a number of honors, including the Marr Prize in 2003 for image parsing with Tu et al, the Marr Prize honorary nominations in 1999 for texture modeling and in 2007 for object modeling with Y. Wu et al.  He received the Aggarwal prize from the International Association of Pattern Recognition in 2008 for “contributions to a unified foundation for visual pattern conceptualization, modeling, learning, and inference”. He received the Helmholtz Test-of-time prize at ICCV 2013. As a junior faculty he received the Sloan Fellow in Computer Science, NSF Career Award, and ONR Young Investigator Award in 2001.  He is a Fellow of the IEEE since 2011. In recent years, he is also interested in situated dialogues and cognitive robots with the support of some DARPA projects. He is the Principal Investigator leading two consecutive ONR MURI projects on Scene/Event Understanding and Commonsense Reasoning, respectively. He serves the IEEE community as a General Chair for CVPR 2012 and 2019.


Wednesday, September 20
9:00-10:00

Kari Pulli
CTO at Meta

Immersive Optical-See-Through Augmented Reality
Augmented Reality has been getting ready for the last 20 years, and is finally becoming real, powered by progress in enabling technologies such as graphics, vision, sensors, and displays. In this talk I’ll provide a personal retrospective on my journey, working on all those enablers, getting ready for the coming AR revolution. At Meta, we are working on immersive optical-see-through AR headset, as well as the full software stack. We’ll discuss the differences of optical vs. video see-through displays, immersion, Meta 2 optics, and the key computer vision enablers for AR. We will finish with discussing the many possible applications that are enabled by wearable and immersive Augmented Reality.

Kari Pulli

 

Kari Pulli is CTO at Meta. Before joining Meta, Kari worked as CTO of the Imaging and Camera Technologies Group at Intel influencing the architecture of future IPUs. He was VP of Computational Imaging at Light and before that he led research teams at NVIDIA Research (Senior Director) and at Nokia Research (Nokia Fellow) on Computational Photography, Computer Vision, and Augmented Reality. He headed Nokia's graphics technology, and contributed to many Khronos and JCP mobile graphics and media standards, and wrote a book on mobile 3D graphics. Kari holds CS degrees from University of Minnesota (BSc), University of Oulu (MSc, Lic. Tech.), University of Washington (PhD); and an MBA from University of Oulu. He has taught and worked as a researcher at Stanford University, University of Oulu, and MIT.