Text recognition with limited computational resources
Bio: Michalis Raptis is a Senior Software Engineer at Google in Los Angeles, working on computer vision and more specifically on text detection. He received his M.Sc. and Ph.D. degrees from the University of California, Los Angeles, USA, in 2008 and 2011 under the supervision of Prof. Stefano Soatto, where his main focus of research was human action recognition in videos. Before joining Google, he was a Senior Researcher at Comcast Labs in Washington D.C working on text recognition on sports videos and a postdoctoral associate at Disney Research in Pittsburgh.
Prof. C. V. Jawahar International Institute of Information Technology, India
Beyond Text Detection and Recognition: Emerging Opportunities in Scene Understanding
Bio: Prof. C.V. Jawahar holds the Amazon Chair at the IIIT Hyderabad, India, where he leads a group focusing on computer vision, machine learning and multimedia systems. In the recent years, he has been looking into a set of problems that overlap with vision, language and text, as well as large scale multimedia retrieval systems. He has numerous publications in top-tier computer vision, robotics and document image processing conferences, with contributions in the areas of scene text understanding and handwritten text recognition among others.
Dr. Sezer Karaoglu University of Amsterdam, Netherlands
Object Reading: Seeing Beyond Visual Cues
Bio: Sezer Karaoglu is Co-Founder and CTO of 3DUniversum, technology spin-off of UvA providing state-of-the art 2D\3D computer vision solutions. Sezer received his Ph.D. degree at Computer Vision Group, Informatics Institute, UvA. During his Ph.D. he has numerous publications in top-tier Computer Vision Journals and Conferences in the domain of scene text detection. Sezer is also part-time postdoctoral researcher at UvA and founder of two other startups (ScanM and 3DHealthScan). He passionately combines research and practice of computer vision technologies.