Computer Vision
Enabling computers and devices to understand what they see.
Video
Automated Video Looping with Progressive Dynamism
Given a short video we create a representation that captures a spectrum of looping videos with varying levels of dynamism, ranging from a static image to a highly animated loop. In such a progressively dynamic…
Video
Visual Recognition
The fields of Computer Vision and Machine Learning are becoming increasingly intertwined, with many of the recent breakthroughs in object and scene recognition coming from the availability of large labeled datasets and sophisticated machine learning…
Video
Deep Machine Learning: a Panel
This panel session of the 2013 Microsoft Research Faculty Summit looks at deep learning, a sub-field of machine learning that focuses on hierarchical representations of features or concepts, where high-level semantic-like features can emerge via…
Video
Visual Motion and Structure
For several decades, the analysis of visual motion and 3-D scene structure have been central to the study of computer vision. Recent breakthroughs in analyzing and amplifying subtle motions can now give us insights into…
Video
Research Bits: Juan Carlos and Agustin Gravano
“Research Bits” provide a glimpse into the research being conducted around the world through brief interviews with researchers. First, Juan Carlos Niebles from the Universidad del Norte in Colombia, talks about his research in computer…
Video
Research in Focus: Fueling the Future
Harold Javid, director of Regional Programs for Microsoft Research Connections, describes some of the projects and programs that are part of Microsoft Research’s effort to “fuel the future.” He discusses the Microsoft Research-FAPESP partnership that…
Video
3D Vision in a Changing World
3D reconstruction from images has been a tremendous success-story of computer vision, with city-scale reconstruction now a reality. However, these successes apply almost exclusively in a static world, where the only motion is that of…
