News

June 18, 2019

A Picture From a Dozen Words – A Drawing Bot for Realizing Everyday Scenes—and Even Stories

New AI technology being developed at Microsoft Research AI can understand and respond to a natural language description of an image.

June 14, 2019

Adobe AI Can Detect Manipulated Photos

The company worked with UC Berkeley scientists to develop a neural network that can spot fake photos and restore their original appearance.

June 14, 2019

IBM’s AI Creates New Labeled Image Sets Using Semantic Content

Researchers at IBM describe in a newly published paper an AI system that can synthesize image labels from only a few examples.

June 14, 2019

Pinterest Details Complete the Look, a Context-aware Visual Search Tool

Complete the Look, a visual search AI, considers a person's body type or the season to make fashion recommendations.

June 14, 2019

How Amazon Cloned a Neighborhood to Test Its Delivery Robots

Amazon used cameras, lidar, and aerial photography to build a highly detailed digital map of a Seattle suburb, where it is testing Scout.

June 14, 2019

Facebook is Creating Photorealistic Homes for AIs to Work and Learn In

If AI-powered robots are ever going to help us out around the house, they’re going to need experience navigating human environments.

June 14, 2019

Applying AutoML to Transformer Architectures

In the computer vision domain, AutoML approaches have found state-of-the-art models that outperform those that are designed by hand.

June 13, 2019

Envisioning Privacy Preserving Image-based Localization for Augmented Reality

New camera localization technology for sensitive environments can keep images and map data confidential.

June 13, 2019

Bridging the Domain Gap for Neural Models

Deep neural networks, a milestone technique in the advancement of modern machine perception systems, still suffer from poor transferability.

June 12, 2019

16-Year-Old Engineer Works to Improve Spinal Surgery Using Machine Learning and Computer Vision

PHOENIX, May 17, 2019 – Krithik Ramesh, 16, of Greenwood Village, Colorado, was awarded first place for developing a machine learning technology for orthopedic surgeons at this year’s Intel International Science and Engineering Fair (ISEF), a program of Society for Science & the Public. Intel ISEF is the world’s largest international pre-college science competition. The competition featured over 1,800 young scientists selected from 423 affiliate fairs in more than 80 countries, regions and territories.