Sponsored Link

eBay Applies Tech Resources to Identifying Brands in Photos

eBay

eBay logoeBay is devoting tech resources to using Artificial Intelligence to identify brands in product photos. In a post on the eBay corporate blog, it wrote, “By understanding brand characteristics, we can further cater the shopping experience to individuals and serve them up a truly tailored experience where everything they see is personalized to them.”

Two eBay research scientists in the field of computer vision, Hadi Kiapour and Robinson Piramuthu, wrote today’s post:

“We’re researching how to recognize brands using computer vision by training our AI to look beyond logos and iconic patterns.”

“Think of your favorite brands: How do you recognize them when you are shopping? Maybe it’s that iconic swoosh on your favorite sneakers or that distinctive plaid on your handbag or that apple on your phone. Brands express themselves in various visual forms.

“At eBay, we’re researching how to recognize brands using computer vision. We’re training our AI to look beyond logos and iconic patterns to dial in on the unique monakers that brands use to create specific items. We’ve compared our deep learning model to human understanding in an experiment to validate visual perceptions of brands.”

You can find the complete post on the eBay corporate blog.

Ina Steiner on EmailIna Steiner on LinkedinIna Steiner on Twitter
Ina Steiner
Ina Steiner
Ina Steiner is co-founder and Editor of EcommerceBytes and has been reporting on ecommerce since 1999. She's a widely cited authority on marketplace selling and is author of "Turn eBay Data Into Dollars" (McGraw-Hill 2006). Her blog was featured in the book, "Blogging Heroes" (Wiley 2008). She is a member of the Online News Association (Sep 2005 - present) and Investigative Reporters and Editors (Mar 2006 - present). Follow her on Twitter at @ecommercebytes and send news tips to ina@ecommercebytes.com. See disclosure at EcommerceBytes.com/disclosure/.

Written by 

Ina Steiner is co-founder and Editor of EcommerceBytes and has been reporting on ecommerce since 1999. She's a widely cited authority on marketplace selling and is author of "Turn eBay Data Into Dollars" (McGraw-Hill 2006). Her blog was featured in the book, "Blogging Heroes" (Wiley 2008). She is a member of the Online News Association (Sep 2005 - present) and Investigative Reporters and Editors (Mar 2006 - present). Follow her on Twitter at @ecommercebytes and send news tips to ina@ecommercebytes.com. See disclosure at EcommerceBytes.com/disclosure/.

7 thoughts on “eBay Applies Tech Resources to Identifying Brands in Photos”

  1. fleecebay still keeps losing sellers pics, can not get correct information in the catalo, has a hard time loading pages…

    yea, this is really going to work..morons

  2. Will it go on a new version of the app, “ebay beta–the app for restless experimentation”?

  3. Do these people work in the Department of Redundancy Department?

    We put make and model in the headline AND the item details section.
    Does these people have a picture of Wenig and a goat?

  4. This is not for the buyers’ benefit. It’s a thinly disguised tool for rooting out branded products not being sold by authorized sellers (VERO). Very efficient way for eBay to search by a protected brand and see who is selling it without permission, even if their titles do not give it away. I’m not usually a conspiracy theorist, but how is a buyer supposed to search by the image?? They would have to find the image, copy it, paste it into eBay’s new tool and hit Search. Wouldn’t it be simpler to for the buyer to type in “Galaxy s8”?

    The only way the new tool would be faster and easier is if it could read the buyer’s mind, “see” the image through a brain scan, and then provide a matching search result. Not going to happen. That’s why the “eBay police theory” holds more weight.

  5. I’ve read that article three times and I still don’t know what they’re attempting to accomplish. It doesn’t even appear to be a way to search for items. It seems more like busy work for their programmers while serious issues on the site go unaddressed.

Comments are closed.