Google ties with Microsoft in Microsoft’s own contest for generating image captions


Products You May Like

Machines can't always generate captions as well as humans yet, but Microsoft and Google are making progress.

Twisted Agile: We’re taking elements Agile dev and shaking it up with savvy best practices for better, faster outcomes. Sign up for our free webinar on June 11 at 10 a.m. PST/11 p.m. EST.

Google and Microsoft have come out in a dead tie for first place in the Microsoft Common Objects in Context (COCO) Captioning Challenge for automatically coming up with captions for images. The results will be formally announced on Friday at the CVPR computer-vision conference in Boston.

The technology from Google, described in a recent paper entitled “Show and Tell: A Neural Image Caption Generator,” performed just as well as two separate Microsoft systems — one described in the paper “From Captions to Visual Concepts and Back” and the other in the paper “Language Models for Image Captioning: The Quirks and What Works”. Technology from researchers at the University of Montreal and the University of Toronto also tied for first place in the competition, which involved categorizing several objects in hundreds of thousands of images and then writing multiple captions for every single image.

Researchers from Baidu who worked with people at the University of California, Los Angeles received a lower ranking in the competition.

Judges came up with the rankings based on the percentage of captions that were at least as good as, if not better than, human captions, and the percentage of captions that passed the Turing Test.

The competition is one of many for people working on image recognition systems. But this is the latest opportunity for Google to boast about its capabilities when it comes to analyzing both words and images at scale.

To perform so well in the competition, Google and Microsoft researchers employed a type of artificial intelligence called deep learning. It involves training systems called artificial neural networks on lots of data, like pictures, and then giving them a new piece of data to receive an inference about it in response. Deep learning works behind the scenes for many consumer-facing web applications, including the new Google Photos service.

But Google and Microsoft are constantly improving their deep learning technology, as are several other companies, like Facebook and Baidu.

Impressing talent is key at this point, with deep learning en vogue, so if nothing else, Google and Microsoft have succeeded in not looking like they lag behind other companies or academic teams.

To get a sense of what Microsoft’s cutting-edge image-captioning technology can do, check out this demo. It isn’t perfect — as is the case with Microsoft’s face-recognition technology — but it isn’t all that bad.

More information:

Powered by VBProfiles

VentureBeat’s VB Insight team is studying marketing and personalization… Chime in here, and we’ll share the results.

More information:

Powered by VBProfiles


Products You May Like

Articles You May Like

The Final Cut Reviews; Deet n Bax Save th’ World – A Stoner Comedy Starring Jason Mewes, Craig Michaelson and Weston Cage.
Deet n Bax Save the World Movie Starring Jason Mewes Premier on 4/20/2015 in Portland
Feature Film “Deet n Bax Save the World” Starring Jason Mewes to be Released on 4/20/2015 ”Deet n Bax Save the World” an Action Stoner Comedy starring Jason Mewes produced by TruEarth Entertainment.
TruEarth Entertainment to Deliver First Feature Film Starring Jason Mewes
Deet n Bax Save the World Movie – Sex, Guns & Weed!
Deet n Bax Save the World wrapped on November 4th!
Deet n Bax Save the World resumes filming this Monday in Portland Oregon!
Deet and Bax Save The World Movie Resumes Filming Soon!

Leave a Reply

Your email address will not be published. Required fields are marked *