Microsoft Research

See an example of 3D hand tracking research from Microsoft, in proceedings at SIGGRAPH 2016.

Many real-world tasks require understanding interactions between a set of entities.

Presenting fingertip haptics: touch feedback on flat keyboards and touchscreens.

Anomaly detection is important for data cleaning, cybersecurity, and robust AI systems.

They are tiny. They are tall. They are gray. They are green. They survey our world with enormous glowing eyes.

Chris Bishop shared the vision for how AI for science will leverage AI to model and predict natural phenomena, including the exciting real-world progress being made by the team.

We live in a world of great and increasing complexity, where even the most expert professionals struggle to master the tasks they face.

Microsoft's Scott Evans and Kareem Choudhry show off the brains of the new Xbox One Kinect.

The app is designed to build a digital 3-D model based on imagery gathered from panning a mobile phone around an object.

TED talks have redefined the elements of a successful presentation and become the gold standard for public speaking around the world.

Writing papers and giving talks are key skills for any researcher, but they aren’t easy.

In 1982, Richard Feynman first proposed using a quantum computer founded on the laws of quantum physics to simulate physical systems and achieve exponential computational speed-ups over conventional

Project Zanzibar, a completely new sensing platform in the form of a flexible, portable mat that has the ability to locate, sense and communicate with objects as well as sense a user’s touch.

See how Kinect's sign language translation capabilities help the hearing and the deaf communicate. For more information on Microsoft Translator, visit microsoft.com/translator

I will talk about recent results from a number of people in the group on Riemannian manifolds in computer vision. In many Vision problems Riemannian manifolds come up as a natural model.

Our research shows: Steerable AutoStereo 3-D Display: We use a special, flat optical lens (Wedge) behind an LCD monitor to direct a narrow beam of light into each of a viewer's eyes.

Got an email you can’t read? No problem. Want to respond even though you don’t know the language? You can do that too.

This presentation introduces participants to what a graph database is and how Neo4j is used in many enterprises to implement key use cases.

Mobile video is quickly becoming a mass consumer phenomenon. More and more people are using their smartphones to search and browse video content while on the move.

We present KinectFusion, a system that takes live depth data from a moving depth camera and in real-time creates high-quality 3D models.

The Microsoft Translator live feature transforms your favorite device into your own personal universal translator where you can have real conversations with people across different languages.

This video is a short demonstration of our research efforts to make Holoportation truly mobile.

One of the main challenges for AI remains unsupervised learning, at which humans are much better than machines, and which we link to another challenge: bringing deep learning to higher-level

One of the key problems in human-computer interactions is the ability of the computer to understand what a person wants, yet with LUIS, it’s no longer a problem.

Microsoft Cognitive Toolkit (formerly known as CNTK) version 2.0 is now available to Developers and Data Scientists.

This video provides a comprehensive but brief overview of Microsoft Azure for research scientists.

We contribute a new pipeline for live multi-view performance capture, generating temporally coherent high-quality reconstructions in real-time.

Fetch! is an iPhone app that can identify breeds from photos of dogs. In addition to identifying the breed, Fetch!