Computer vision
Teaching machines to interpret and reason about the visual world, from object recognition to medical imaging.
Video
Opening Keynote: Faculty Summit 2014
Harry Shum, executive vice president of Microsoft’s Technology and Research group, opens the Faculty Summit by highlighting major efforts at Microsoft Research. Two of significance are the integration of Microsoft Academic Search into Bing with…
Video
Deep learning enables large-scale computer image recognition
Trishul Chilimbi, Partner Research Manager for Microsoft Research, discusses Project Adam, and how deep neural networks have enabled large-scale computer image recognition with astounding accuracy.
Video
Introducing Project Adam: a new deep-learning system
Project Adam is a new deep-learning system modeled after the human brain that has greater image classification accuracy and is 50 times faster than other systems in the industry.
Project
Sparse Reflections Analysis
We present Sparse Reflections Analysis (SRA), an algorithm for removing multipath interference from Time of Flight sensors. SRA allows for very general forms of multipath, including interference with three or more paths, diffuse multipath resulting…
Publication