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 techniques.

In this session of the 2013 Microsoft Research Faculty Summit, leading researchers in these fields share their perspectives on recent advances and current challenges. How do sophisticated machine learning approaches aid in solving difficult recognition problems? What role do large labeled datasets and recognition challenges play in advancing the state of the art and enabling data-driven approaches to recognition? And how can the layout of objects in a scene as well as relationship to natural language models give us an edge in describing complex scenes with multiple actors and objects? These are just some of the questions at the forefront of this rapidly evolving research field.

Speaker Bios

Kristen Grauman is a Clare Boothe Luce Assistant Professor in the Department of Computer Science at the University of Texas at Austin. Her research in computer vision and machine learning focuses on visual search and object recognition. Before joining UT-Austin in 2007, she received her Ph.D. in the EECS department at MIT, working in the Computer Science and Artificial Intelligence Laboratory. She is a Microsoft Research New Faculty Fellow, and a recipient of an NSF CAREER award and the Howes Scholar Award in Computational Science.

Date:
Haut-parleurs:
Fei Fei Li, Kristen Grauman, and Larry Zitnick
Affiliation:
University of Texas, Stanford University, Microsoft Research

Taille: Microsoft Research Faculty Summit