I am currently the computer vision and deep learning technical lead at Video-AI technologies group, in IBM - Haifa Research lab, at Israel. Prior to this position I was a researcher in Medical Imaging Analytics group at IBM and Computer Vision researcher at several companies.
I hold a BSc. and MSc. in Aerospace Engineering from Technion-Israel Institute of Technology and PhD. in Applied Mathematics from Tel-Aviv University (specialized in computer vision).
My research area is in Computer Vision, with background in Stereo vision, Shape from X, Optical flow, Visual tracking and Segmentation. More recently my research was focused on applications of deep learning in medical imaging.
In Video-AI technologies we strive to reach automatic video understanding, to recognize objects, and enrich video with extracted metadata.
The team have developed novel assets in:
* Text recognition in natural scene images (deployed in Watson Extend image-based recognition machine).
* Video scene segmentation using multi-modal video analysis
* Deep learning based summarization and content representation in video
* Action recognition in video
Our goal is to advance AI capabilities through cutting edge research that learn dynamic temporal content of videos and contextual data for video semantic summarization. We target learning from less labeling such as weakly supervised and noisy label approaches.