Computer Vision
Enabling computers and devices to understand what they see.
Project
Human activity detection in RGBD videos
The ability to detect human actions in real-time is fundamental to several applications such as surveillance, gaming, and sign language detection. These applications demand accurate and robust localization of actions at low latencies which remains…
Tool
MSR Demosaicing Dataset
The Microsoft Research Cambridge demosaicing data set consists of set of raw images, and their downscaled versions which can be used for learning and evaluating demosaicing (and possibly other tasks like denoising), both in linear-space…
Microsoft Research Blog
Machine Learning Gets Big Boost from Ultra-Efficient Convolutional Neural Network Accelerator
Posted by Doug Burger Editor’s note: Doug Burger, a processor architect by training, is a Microsoft researcher focused on disrupting the very fabric of datacenter processing power in a mobile-first, cloud-first world. I’m excited to…
Microsoft Research Blog
Microsoft Researchers’ Algorithm Sets ImageNet Challenge Milestone
Posted by Richard Eckel The race among computer scientists to build the world’s most accurate computer vision system is more of a marathon than a sprint. The race’s new leader is a team of Microsoft…