“Scientists at Amazon describe a GAN that generates clothing examples to match product descriptions, which they say could be used to refine customer text queries. For instance, if a shopper searched for “women’s black pants” and then add the word “petite” and then the word “capri,” the on-screen images would adjust accordingly with each new word.
In experiments, the team reports that ReStGAN improved product classification by type up to 22% and gender up to 27%, compared with the previous best-performing models based on the StackGAN architecture. Color improved 100%.”
“In an internal study, the company claims that online shoppers spent upwards of 72 minutes on websites where its software was deployed, compared with 25 minutes on sites without it
VueTag, an AI-powered object recognition service that tags and categorizes up to 30,000 product images per hour across over 250 attributes including color, pattern, length, neckline, and more.
Another feature on tap is VueStyle, an “AI stylist” that surfaces outfits which match shoppers’ style preferences and tastes, recommends products in a range of categories, and optionally automates things like subscription box curation.
VueCommerce, VueFind, and VueMail, Vue.ai provides an omnichannel personalization solution that sends millions of personalized emails to shoppers, leverages computer vision and natural language processing to deliver contextual product search results, and delivers real-time style recommendations.
Perhaps the most technically impressive tool in Vue.ai’s retail arsenal is VueModel, which employs a sophisticated model to generate on-model fashion imagery.
Vue.ai has competition in startups like Trendage, which uses AI and crowdfunded fashion expertise to help retailers make the right recommendations for shoppers, and Singapore-based ViSenze, which recently raised $20 million for its ecommerce-tailored computer vision platform. “