Program 2016

08:00-09:00 Registration and Refreshments
09:00-09:10 Welcome
09:10-09:35 Computer Vision Now and Then: A Personal Journey
Prof. Gerard Medioni, USC
09:35-10:00 Wearable AI: What if Our Digital Assistants had Eyes and Ears?
Prof. Amnon Shashua, Hebrew University | Mobileye | OrCam
10:00-10:25 Computer Vision from Academia to ATAP
Prof. David Frakes, Google ATAP
10:25-10:50 FoodTech, New Frontier for Technology
Prof. Eyal Shimoni, Strauss Group
10:50-11:15 On the Way to Visual Understanding…
Dr. Gershom Kutlirof, Intel
11:15-11:45 Coffe Break & Visit the Exhibition 
  Automotive
Chair: Dr. Sharon Duvdevani
Elbit System Elop
New Frontiers:
Medical Imaging and the Ocean

Chair: Dr. Ron Maron, BIRD Foundation
Innovision
11:45-12:05 NVIDIA Deep Learning Platform
Carlo Nardone, NVIDIA
New Frontiers in Sensory Substitution and Sensory Recovery
Prof. Amir Amedi, The Hebrew University
The Israeli Machine Vision Industry Overview
Koby Simana, IVC Research Center
12:05-12:25 Giving Sight to Embedded Systems
Noam Babayof, Synopsys
Analysis of High-throughput Microscopy Videos: Catching Up with Cell Dynamics 
Dr. Tammy Riklin Raviv, Ben Gurion University

Investors Panel
Moderator: Dror Gill , Beamr

Eden Shochat, Aleph
Rutie Adar, Samsung Ventures
Alex Tepper, GE Ventures

12:25-12:45 StixelNet: A Deep Convolutional Network for Obstacle Detection and Road Segmentation
Dr. Dan Levi, GM
From Idea to Patient Care in 8 Months - DEXA T-Score Prediction Based on CT
Orna Bregman Amitai, Zebra Medical Vision
12:45-13:05 Advanced Regularization for Estimating Dense LIDAR Measurements in Autonomous Vehicles
Dr. Guy Gilboa, Technion 
How Can Computer Vision Advance Ocean Exploration?
Dr. Tali Treibitz, Marine Imaging Center, University of Haifa
13:05-14:10 Lunch Break
  Deep Vision
Chair: Dr. Doron Shaked, HP Lab
3D models & AR 
Chair: Ziv Aviv, Intel
Innovision Speed Startups 
14:10-14:30 Joint Embeddings of Shapes and Images via CNN Image Purification
Dr. Yangyan Li, Stanford & TAU
The OMEK Consortium
Erez NurFlare Vision
InnoVision: the final 5 startup companies to present their technology
Judges:

Uri Arazy, Intel Capital
Itamar Friedman, Visualead & mentor at the Microsoft Accelerator Program
Dr. Nimrod Koslovski
, JVP Media Labs
David Stark, OurCrowd
Koby Simana, IVC Research Center
14:30-14:50 Deep Neural Networks Challenges in Embedded and Real Time Systems
Erez NatanCEVA
Approach for Evaluating Point Cloud Quality in SLAM
Riki Sheinin & Yehonatan Sela, Intel
14:50-15:10 What from Where. In 3D! Learning Semantic Segmentation from 3D Models
Avram Golbert, Rafael 
Practical 3D Recognition for Augmented Reality
Dr. Leonid Karlinsky, IBM Research
15:10-15:30 Convolutional Neural Networks – from Theory to Practice
Ziv Mhabary, Trax
3D Time-of-Flight Sensing: Challenges and Solutions
Daniël Van NieuwenhoveSoftKinetic
15:30-16:10 Happy Hour sponsored by GE & Visit the Exhibition
16:10-16:20 Winners of Startups and Students competitions
16:20-16:35 Live Interactive Holography – From Medical Imaging to Augmented Reality
Shaul Gelman, RealView
16:35-16:50 Gear VR
Aviv Hod, Samsung
16:50-17:15 Deep Learning for Autonomous Driving
Prof. Shai Shalev Shwartz, The Hebrew University of Jerusalem
17:15-17:40 When Sensors are Out of Line! Deep Learning on Manifolds – Theory and Applications
Prof. Shai Dekel, GE

 

Companies Track

11:45-12:05

How to Manage a Project in Computer Vision
Ron Soferman, Ron Soferman Image Processing & Computer Vision

12:05-12:25

From $100,000 Pilot Helmets to $500 Augmented Reality Glasses

Matan ProtterInfinityAR

12:25-12:45

Mantis Vision

14:10-14:30

Volume Elements

14:30-14:50

SoftKinetic DepthSense®: 3D Time-of-Flight Depth-Sensing Opening the Way for Machine Vision
Daniël Van Nieuwenhove, SoftKinetic

 

 

 

 

 

 

 

 

 

The diverse list of keynote speakers brings the latest technology developed for computer vision along with the vision to pave the road for future developments. 

An interesting theme that characterizes IMVC 2016 speakers is the collaboration and fertilization between academy and industry. 

Keynote Speakers

Prof. Gerard Medioni

Professor at the University of South California, now on leave at Amazon, who also acted as a consultant to a number of companies: OptiCopy, Geometrix, Poseidon, DXO, Bigstage and PrimeSense. Prof. Medioni will review some of the technology developed along the way, and the lessons learned.

Prof. Amnon Shashua 

Professor at the Hebrew University of Jerusalem and also a co-founder of Mobileye and OrCam. 

Prof. David Frakes 

The Technical Project Lead of Mobile Imaging at Google ATAP. Prior to that, he was the Principal Investigator at the Arizona State University Image Processing Applications Laboratory.

Prof. Eyal Shimoni 

VP of Technology, responsible for the future business development of the Strauss Group. He received his doctorate in Food Engineering and Biotechnology from the Technion and is a professor at the Food Engineering faculty. His research mainly addresses the issues of improving the health qualities of food products by mastering the ingredients from the molecular level to the manufacturing level. In IMVC 2016 Prof. Shimoni will address the computer vision challenges in the food industry. 

Dr. Gershom Kutliroff

Served as co-founder and CTO of Omek Interactive that developed gesture recognition and body tracking software. He is now at Intel and will address recent work done on computer vision and machine learning. 

Shaul Gelman

President, Founder and VP of R&D of RealView Imaging, presented RealView's technology in IMVC 2014. IMVC 2016 will conclude with an updated by Shaul Gelman on RealView's digital holography visualization solutions for the medical field. 

Sessions

IMVC 2016 focuses on the following topics this year:

  • Medical imaging encompasses different imaging modalities and processes to image the human body for diagnostic and treatment purposes and therefore plays an important role in initiatives to improve public health for all population groups.  Medical image computing (MIC) is an interdisciplinary field at the intersection of computer science, data science, electrical engineering, physics, mathematics and medicine.  This field focuses on the computational analysis of the images, not their acquisition. The methods can be grouped into several broad categories: image segmentation, image registration, image-based physiological modeling, and others. 
  • Automotive The automotive industry is a wide range of companies and organizations involved in the design, development, manufacturing, marketing, and selling of motor vehicles.It is one of the world's most important economic sectors by revenue.  The term automotive was created from Greek autos (self), and Latin motivus (of motion) to represent any form of self-powered vehicle. 
  • 3D modeling is the process of developing a mathematical representation of any three-dimensional surface of an object via specialized software. The product is called a 3D model. It can be displayed as a two-dimensional image through a process called 3D rendering or used in a computer simulation of physical phenomena. The model can also be physically created using 3D printing devices.
  • Augmented reality (AR) is a live direct or indirect view of a physical, real-world environment whose elements are augmented (or supplemented) by computer-generated sensory input such as sound, video, graphics or GPS data. 
  • Deep Vision (Deep Learning for computer vision).  With the increase of acceleration of digital photography and the advances in storage devices over the last decade, we have seen explosive growth in the available amount of visual data and equally explosive growth in the computational capacities for image understanding. Instead of hand crafting features, recent advancement in deep learning suggests an emerging approach to extracting useful representations for many computer vision tasks.  Deep Learning involves the use of complex, multi-level “deep” neural networks for both supervised and unsupervised machine learning tasks. For example, voice recognition (speech to text) in mobile devices today is accomplished via Deep Learning networks. It is also the technology behind most image search engines today and at the front of current research both in the academy and in the giant corporations.