Microsoft Research

Recent advances in speaker verification technology have resulted in dramatic performance improvements in both speed and accuracy.

Although distributed systems are widely used nowadays, their implementation and deployment is still a time-consuming, error-prone, and hardly predictive task.

This talk presents two separate pieces of work that share a common challenge: dealing with uncertainty in data.

Object recognition is now becoming a usable technology. When it is used in applications, fundamental questions arise: What should we recognize in images?

Visionaries in Computer Science have long seen the computer as a tool to augment our intellect.

Current techniques for energy-based image segmentation are not well suited to the incorporation of topological information about image regions, such as their connectedness or holefreeness.

Talk 1: 3:30 to 4:15 Title: Probabilistic Approximation Theorems in Game Theory and Stochastic Optimization Speaker: Costis Daskalakis, MIT Abstract: In Economics, reliability theory and other

In this talk, IΓÇÖd like to present two very diverse topics: API usability evaluation and collaborative faceted search around the tabletop.

In the first part of the talk I give new results for a first-order primal-dual algorithm to solve non-smooth convex optimization problems with known saddle-point structure.

I will discuss two results in quantitative finance in which algorithmic arguments play a central role.

11:15 -12:00 WELCOME MSR Overview: Introduction & Logistics, Overview, Data-Intensive Science: The 4th Paradigm) Welcome Lee Dirks – Director, Education & Scholarly Communications “MSR

Inductive program synthesis (IPS) is concerned with the automated construction of computer programs from incomplete specifications, such as input-output examples.

An important goal of software testing is to achieve at least high structural coverage.

Of all the genres of photography, sports and action is one of the most challenging.

Real-world images are notoriously complex and variable due to both photometric changes of images (such as varying illuminations and shadows) as well as geometric changes (such as view point

A number of data sets are naturally described in matrix form. Examples range from microarrays to collaborative filtering data, to the set of pairwise distances of a cloud of points.

Adaptive Indexing targets dynamic environments where there is no workload knowledge and there is not enough time to invest in physical design preparations and tuning, e.g., due to very large data

Artificial Intelligence methods open up new possibilities in interactive storytelling, enabling the creation of believable characters with rich personalities and emotions, interactive story systems

Adapx provides solutions for users who have substantive data collection needs, but who have yet to adopt or have rejected existing digital technologies.

The goal of component-based synthesis is to build a system from components. The nature of this generic problem changes as we concretize what is a component and what constitutes a composition.

Programming concurrent systems is notoriously subtle and error-prone.

We present a Multi-Authority Attribute-Based Encryption (ABE) system.

Standard Principal Components are directions that optimize second moments of a given set of points and have proven to be a powerful tool.

Machine vision approaches for accurate and efficient visual recognition have the potential to play a transformative role in numerous applications, and while seemingly simple visual tasks continue to

What does it mean to 'understand' an image? One popular answer is simply naming the objects seen in the image.

Join us for a session in which Elizabeth Lawley and Andrew Phelps from the RIT School of Interactive Games & Media discuss their plans for the design, implementation, deployment, and evaluation of a

Traditional models of rationality in economics assume that agents can immediately play the equilibrium of any game they find themselves in.

In the past few years, the number of applications that need to process large-scale data has grown remarkably.

Audio-visual event detection aims to identify semantically defined events that reveal human activities.

The Internet has allowed electronic markets like eBay or Amazon to become ubiquitous.