-
-
Kristen L Grauman
Professor
Department of Computer Science, Applied Research Laboratories
Professorship in Computer Sciences #4 (Holder) | Distinguished Teaching ProfessorArtificial Intelligence, Data Mining, Machine Learning, Natural Computationgrauman@cs.utexas.edu
Phone: 512-471-9521
Office Location
GDC 4.726
Postal Address
2317 SPEEDWAY
AUSTIN, TX 78712-
Ph.D., Massachusetts Institute of Technology, Cambridge, MA (2006)
S.M., Massachusetts Institute of Technology, Cambridge, MA (2003)
B.A., Boston College, Chestnut Hill, MA (2001)Research Interests
Computer vision and machine learning, and their applications to information retrieval;
Object recognition, image search, large-scale retrieval, visual discovery, active learning.
Grauman's group 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.
My research interests are in computer vision and machine learning. In general, the goal of computer vision is to develop the algorithms and representations that will allow a computer to autonomously analyze visual information. I am especially interested in learning and recognizing visual object categories, and scalable methods for content-based retrieval and visual search.
Large amounts of interconnected visual data (images, videos) are readily available---but we don’t yet have the tools to easily access and analyze them. My group’s research aims to remove this disparity, and transform how we retrieve and evaluate visual information. This requires robust methods to recognize objects, actions, and scenes, and to automatically organize and search images and videos based on their content. Key research issues that we are exploring are scalable search for meaningful similarity metrics, unsupervised visual discovery, and cooperative learning between machine and human vision systems.
-
Selected Publications:
Cost-Sensitive Active Visual Category Learning. S. Vijayanarasimhan and K. Grauman. International Journal of Computer Vision (IJCV), Vol. 91, No. 1, 2010.
Object-Graphs for Context-Aware Category Discovery. Y. J. Lee and K. Grauman. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2010.
Fast Similarity Search for Learned Metrics. B. Kulis, P. Jain, and K. Grauman. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), Vol. 31, No. 12, 2009.
Foreground Focus: Unsupervised Learning from Partially Matching Images. Y. J. Lee and K. Grauman. International Journal of Computer Vision (IJCV), Vol. 85, No. 2, 2009.
The Pyramid Match Kernel: Efficient Learning with Sets of Features. K. Grauman and T. Darrell. Journal of Machine Learning Research (JMLR), 8 (Apr): 725-760, 2007.
Books:
Visual Object Recognition, K. Grauman and B. Leibe. Synthesis Lectures on Computer Vision. Morgan and Claypool Publishers, 2011.
-
- Computers and Thought Award, International Joint Conferences on Artificial Intelligence, 2013
- Alfred P. Sloan Research Fellow, 2012
- Office of Naval Research Young Investigator Research Award (ONR YIP), 2012
- Regents’ Outstanding Teaching Award, University of Texas System, 2012
- Marr Prize, Best Paper Award, International Conference on Computer Vision (ICCV), 2011
- For the paper “Relative Attributes”, with D. Parikh.
- Society for Teaching Excellence, University of Texas at Austin, 2011-present
- AI's 10 to Watch, IEEE Intelligent Systems, 2011
- National Science Foundation Faculty Early Career Development Award (NSF CAREER), 2008
- Microsoft Research New Faculty Fellow, 2008
- Best Student Paper Award, with Prateek Jain and Brian Kulis, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2008
- Frederick A. Howes Scholar Award in Computational Science, Krell Institute, 2007
- Morris Joseph Levin Award, MIT Electrical Engineering and Computer Science Department, 2003
-
