The Race For AI: Video object segmentation and representation with Deep Learning

Agenda:

18:30-19:00: Gathering (food and drinks)

19:00 –20:30- "The Race For AI: Video object segmentation and representation with Deep Learning"

Eddie Smolyansky, Visualead's Head of Research and Gilad Sharir, Visualead's Senior CV researcher will present their work on video object segmentation using convolutional neural networks.

Abstract:

In this talk we will cover the following topics:

• What is semantic segmentation in images?
• How can it be extended to any object segmentation in video?
• A discussion on some of their experiments (as well as failure cases)
• Present other leading methods for video object segmentation: this is a hot field with new state of the art results almost monthly.

More formally:

The task of category independent foreground segmentation in images is challenging for a machine learning system, because it needs to learn the general concept of an object, even for object categories that it hasn't seen during training. In the case of foreground segmentation in videos, the problem is compounded by the fact that the object as well as the background change appearance throughout the video. We propose a method for learning the general concept of object appearance in videos, based on deep neural networks. Apart from learning the object appearance for each frame, our system learns the temporal changes between frames in a video, which represent the object motion, and thus leverages the temporal information available in videos. By learning a category-independent object segmentation, we are able to perform unsupervised video object segmentation. In addition, in the case of semi-supervised video segmentation (where one frame from the video is annotated) we further train our system to recognize a specific object which appears in the video. In both scenarios, our system compares favorably against the state of the art.Furthermore, we demonstrate a novel use case for video object segmentation, by implementing a mobile application where a user captures a video of an object, and our system is able to segment the object and display it in an AR setting.

Bios:

Eddie Smolyansky:

Eddie joined Visualead as an accomplished computer vision engineer and quickly grew to lead Visualead's Research vision and efforts. Always working on the Next Big Thing, the highly academic research team is responsible for the company's innovation and next generation of disruptive technologies. Prior to Visualead, Eddie worked in the smartphone dual-lens company CorePhotonics. In the IDF, he took part in the prestigious Psagot program and later served as an academic officer in the unit 8200, where his team won the Israel Defense Award (among others). He holds two B.Sc. degrees from the Technion in EE and Physics.

Gilad Sharir:

Gilad is Visualead's Senior Computer Vision Researcher, where he applies deep learning research on innovative scenarios. Gilad holds a B.Sc. in Electrical Engineering and Physics, and an M.Sc. in EE from Tel Aviv University. He specialised as a computer vision researcher in VISICS lab at KUL university, where he worked on implementing advanced algorithms for action recognition from videos. Gilad published several research-papers in leading computer vision conferences on the topics of image segmentation and action recognition.