Computer Vision
Enabling computers and devices to understand what they see.
Project
From Captions to Visual Concepts and Back
We introduce a novel approach for automatically generating image descriptions. Visual detectors, language models, and deep multimodal similarity models are learned directly from a dataset of image captions. Our system is state-of-the-art on the official…
Video
Accurate, Robust, and Flexible Real-time Hand Tracking
We present a new real-time hand tracking system based on a single depth camera. The system can accurately reconstruct complex hand poses across a variety of subjects. It also allows for robust tracking, rapidly recovering…
Project
Presenter Camera
Presenter Camera is a desktop application designed to improve the quality of video seen by remote attendees of a presentation. The Problem Remote meetings are becoming more prolific in the modern workplace. A common…
Video
Microsoft Research Internships
Microsoft Research interns describe the distinct advantages of having an intern experience at Microsoft, including direct interaction with product groups and invaluable impact on their PhD studies. Microsoft Research mentors also weigh in on what…
Project
Hands-Free Keyboard
The Hands-Free keyboard is a project to enable people who are unable to speak or use a physical keyboard to communicate using only their eyes.