Microsoft Research

Team Project Meeting

This talk will discuss small image sensor designs and big visual data parsing and their applications.

90% of the US population lives in a shared dwelling with at least one other person.

Distributed software development poses many challenges.

I will describe a new method for recovering the blur in motion-blurred images based on statistical irregularities their power spectrum exhibits.

Simulation of physical quantum systems is potentially the most important application of quantum computers, and is Feynman's original motivation for proposing quantum computers.

The use of interactive technologies to improve health and wellbeing has grown dramatically over the last two decades.

This talk describes an approach to quantitatively evaluate the quality and maturity of open source software. and hence its suitability for use in business-critical settings.

Future graphics and imaging applications�from photorealistic real-time rendering, to 4D light field cameras and pervasive sensing, to multi-material 3D printing�demand orders of magnitude more

The future of computation will be characterized by real-time interaction with multiple screens and multiple devices.

We survey some of the important and classical facts concerning integers that can be written as the sum of (two, three, or four) squares, as well as the number of such representations, emphasizing

Deep learning is quickly becoming a popular subject in machine learning. A lot of this success is due to the advances done in how these models are trained.

In the d-dimensional vector bin packing problem (VBP), one is given d-dimensional real vectors x_1,x_2, � ,x_n and the goal is to find a partition into a minimum number of feasible sets.

Abstract interpretation (AI) is one of the most scalable automated program verification techniques.

Through an intuitive drag and drop interface that resembles snapping together LEGO blocks, MIT App Inventor makes it easy for even non-programmers to create apps for health, education, business

Automatic Fault Localization by Filtering Likely Invariants An important step in repairing software failures discovered during testing or production runs is to diagnose the root cause(s) of the

I will first give a brief overview of recent results about a compiler for high-performance image processing, an authoring tool for online video lectures, and Metropolis light transport.

The past decade has shown both the great strengths and great weaknesses of large scale, distributed crowd action. As we enter the next decade, how might we do better?

Electron microscopes (EM) can now provide the nanometer resolution that is needed to image synapses, and therefore connections, while Light Microscopes (LM) see at the micrometer resolution required

I will report on recent work in the Multicore Programming Group at Imperial on the verification of data parallel programs.

To a great extent, the language we think in defines what we can know. Thus for all the strengths of words, there are aspects of understanding that remain outside their reach.

The unprecedented growth of mega datacenters, in which hundreds of thousands of machines are assembled to process a massive amount of data for Internet-scale services, has been driving the evolution

A growing online phenomenon is that of crowdsourcing, where groups of disparate people, connected through technology, contribute to a common product.

The classical wisdom is that hashing is preferred method to implement joins in main memory.

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.

Modern computer networks perform a bewildering array of tasks, from routing and traffic monitoring, to access control and server load balancing.

Communication and sharing of information has become as pervasive and multimodal as the science fictional imagination of various works such as Star Trek, except of course where there is a

Recent development of 3D technologies and depth sensing devices have posed new challenges in processing of depth maps, which are crucial elements in 3D rendering and scene analysis.

Instruction-by-instruction checking of program execution is a powerful method for identifying and mitigating hard-to-find software bugs, including security vulnerabilities.

Access control deals with regulating the accesses principals have to resources, and is an important aspect of security. Intractable (NP-hard) problems arise frequently in access control.