Jul 2, 2014 · 5:00 PM
This location is shown only to members
Inside Visual Search Engine - By Superfish
Information retrieval approach to text analysis proved extremely efficient, ranging from simple text retrieval by Google through speech recognition by Siri and to answering tricky Jeopardy questions by IBM. Visual search became not only another way to browse images around us, but the answer to many visual recognition tasks, such as classification of objects into categories, annotation etc.
Superfish's visual search technology is in the heart of such an engine. We will share from our experience in building such an engine.
Inside Visual Search Engine. Part I - Algorithms July 2nd 2014
Prof. Lior Wolf, Tel-Aviv University. Deep learning - the final frontier in visual understanding?
I will discuss the recent successes that deep learning has shown in visual understanding, object detection and recognition, face identification, and action recognition. I will cover the reasons for the marked improvement in performance obtained in all of these domains and discuss practical strategies for employing such methods.
Michael Chertok, Founder & CTO of Superfish. From Deep Learning to Visual Search: Where are the gaps and how to bridge them
I’ll present the notion of Visual Synonyms, which are in the heart Superfish’s visual search engine and their relation to deep learning.