Deep Learning in Retail & Advertising Summit
London

The Web is a multi-model space. It is flooded with visual and textual information. The ability to natively organize and mine its heterogeneous content is crucial for a seamless user experience. This is true in e-commerce search, where product images and textual descriptions play key roles, because it is not feasible to physically inspect the goods.

Caroline Walerud wants you to forget your shoe size. Or, at least, to forget that number you've been reeling off to salespeople for years, like a U.S. 9, or a European 40. It's likely that it isn't quite right anyway, given the complex anatomical structure of our feet and the inconsistent sizing used by footwear brands.

ASOS can make a couple of interesting technology boasts. It is now the largest UK user of Microsoft cloud services, for example, while in the DevOps world, it claims to be the largest contributor of open source code to leading deployment automation technologies.

Wide Eyes Technologies has developed cutting-edge software that uses image recognition to find items similar to what you’re looking for in a store’s database. Not only that, it can also recommend items to go with the ones you’ve chosen and complete your look.

In the fashion industry there are many tasks that require human-level cognitive skills, such as detecting similar products or identifying facets in products (e.g. sleeve length or silhouette types in dresses).

In GILT we are building automated cognitive systems to detect dresses based on their silhouette, neckline, sleeve type and occasion.