Professor Kristen Grauman of the University of Texas at Austin presents the keynote on machine learning at the December 2012 Embedded Vision Alliance Member Summit. Grauman is a rising star in computer vision research. Among other distinctions, she was recently recognized with a Regents' Outstanding Teaching Award and, along with Devi Parikh, received the prestigious Marr Prize for the paper "Relative Attributes," presented at the 2011 International Conference on Computer Vision.
Machine learning is a type of artificial intelligence that provides systems with the ability to learn without being explicitly programmed. Machine learning focuses on the development of programs that can teach themselves to grow and change when exposed to new data. Machine learning is an essential part of many vision applications.
Grauman's group at UT Austin focuses on problems in computer vision and machine learning, particularly visual recognition and large-scale image and video retrieval. The goal of their research is to develop algorithms to categorize and detect objects, activities, or scenes, and large-scale visual search techniques that can rapidly identify the most relevant content within massive collections. Grauman’s presentation at the Alliance Member Summit introduced key problems in machine learning for computer vision, and highlighted recent work tackling those problems.