Computer Vision
Director: Kristen Grauman
In general, the goal of computer vision is to develop the algorithms and representations that will allow a computer to autonomously analyze visual information. We are 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. Our 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.
Chao Yeh Chen Ph.D. Student chaoyehchen [at] gmail com
Kristen Grauman Faculty grauman [at] cs utexas edu
Sung Ju Hwang Ph.D. Student sjhwang [at] cs utexas edu
Jaechul Kim Ph.D. Student jaechul [at] cs utexas edu
Adriana Kovashka Ph.D. Student adriana [at] cs utexas edu
Yong Jae Lee Ph.D. Student yjlee0222 [at] mail utexas edu
Sudheendra Vijayanarasimhan Ph.D. Student svnaras [at] cs utexas edu
     [Expand to show all 32][Minimize]
Accounting for the Relative Importance of Objects in Image Retrieval 2010
S. J. Hwang and K. Grauman, In British Machine Vision Conference (BMVC) 2010.
Asymmetric Region-to-Image Matching for Comparing Images with Generic Object Categories 2010
A. Kovashka and K. Grauman, In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2010.
Collect-Cut: Segmentation with Top-Down Cues Discovered in Multi-Object Images 2010
Y.J. Lee and K. Grauman, In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2010.
Far-Sighted Active Learning on a Budget for Image and Video Recognition 2010
S. Vijayanarasimhan, P. Jain and K. Grauman, In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2010.
Learning a Hierarchy of Discriminative Space-Time Neighborhood Features for Human Action Recognition 2010
A. Kovashka and K. Grauman, In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2010.
Object-Graphs for Context-Aware Category Discovery 2010
Y.J. Lee and K. Grauman, In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2010.
Reading Between The Lines: Object Localization Using Implicit Cues from Image Tags 2010
S.J. Hwang and K. Grauman, In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2010.
Top-Down Pairwise Potentials for Piecing Together Multi-Class Segmentation Puzzles 2010
S. Vijayanarasimhan and K. Grauman, In The seventh IEEE Computer Society Workshop on Perceptual Organization in Computer Vision (POCV) 2010.
Kernelized Locality-Sensitive Hashing for Scalable Image Search 2009
B. Kulis and K. Grauman, In IEEE International Conference on Computer Vision (ICCV) 2009.
Observe Locally, Infer Globally: a Space-Time MRF for Detecting Abnormal Activities with Incremental Updates 2009
Jaechul Kim and Kristen Grauman, In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2009.
Shape Discovery from Unlabeled Image Collections 2009
Y. J. Lee and K. Grauman, In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2009.
What's It Going to Cost You?: Predicting Effort vs. Informativeness for Multi-Label Image Annotations 2009
S. Vijayanarasimhan and K. Grauman, In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2009.
Fast Image Search for Learned Metrics 2008
P. Jain, B. Kulis, and K. Grauman, In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2008.
Foreground Focus: Finding Meaningful Features in Unlabeled Images 2008
Y. J. Lee and K. Grauman, In British Machine Vision Conference (BMVC) 2008.
Keywords to Visual Categories: Multiple-Instance Learning for Weakly Supervised Object Categorization 2008
S. Vijayanarasimhan and K. Grauman, In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2008.
Multi-Level Active Prediction of Useful Image Annotations for Recognition 2008
S. Vijayanarasimhan and K. Grauman, In Advances in Neural Information Processing Systems (NIPS) 2008.
Online Metric Learning and Fast Similarity Search 2008
P. Jain, B. Kulis, I. Dhillon, and K. Grauman, In Advances in Neural Information Processing Systems (NIPS) 2008.
Watch, Listen & Learn: Co-training on Captioned Images and Videos 2008
Sonal Gupta, Joohyun Kim, Kristen Grauman and Raymond Mooney, In Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD), pp. 457--472, Antwerp Belgium, September 2008.
Active Learning with Gaussian Processes for Object Categorization 2007
A. Kapoor, K. Grauman, R. Urtasun, and T. Darrell, In IEEE International Conference on Computer Vision (ICCV) 2007.
Approximate Correspondences in High Dimensions 2007
K. Grauman and T. Darrell, In Advances in Neural Information Processing Systems 19 (NIPS) 2007.
Pyramid Match Hashing: Sub-Linear Time Indexing Over Partial Correspondences 2007
K. Grauman and T. Darrell, In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2007.
The Pyramid Match: Efficient Learning with Partial Correspondences 2007
K. Grauman, In Association for the Advancement of Artificial Intelligence (AAAI), Nectar track 2007.
Unsupervised Learning of Categories from Sets of Partially Matching Image Features 2006
K. Grauman and T. Darrell, In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2006.
A Picture is Worth a Thousand Keywords: Image-Based Object Search on a Mobile Platform 2005
T. Yeh, K. Grauman, K. Tollmar, and T. Darrell, In Conference on Human Factors in Computing Systems (CHI) 2005.
Avoiding the ``Streetlight Effect'': Tracking by Exploring Likelihood Modes 2005
D. Demirdjian, L. Taycher, G. Shakhnarovich, K. Grauman, and T. Darrell, In IEEE International Conference on Computer Vision (ICCV) 2005.
Efficient Image Matching with Distributions of Local Invariant Features 2005
K. Grauman and T. Darrell, In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2005.
The Pyramid Match Kernel: Discriminative Classification with Sets of Image Features 2005
K. Grauman and T. Darrell, In IEEE International Conference on Computer Vision (ICCV) 2005.
Fast Contour Matching Using Approximate Earth Mover's Distance 2004
K. Grauman and T. Darrell, In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2004.
Virtual Visual Hulls: Example-Based 3D Shape Inference from a Single Silhouette 2004
K. Grauman, G. Shakhnarovich, and T. Darrell, In The 2nd Workshop on Statistical Methods in Video Processing, in conjunction with ECCV 2004.
A Bayesian Approach to Image-Based Visual Hull Reconstruction 2003
K. Grauman, G. Shakhnarovich, and T. Darrell, In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2003.
Inferring 3D Structure with a Statistical Image-Based Shape Model 2003
K. Grauman, G. Shakhnarovich, and T. Darrell, In IEEE International Conference on Computer Vision (ICCV) 2003.
Communication via Eye Blinks: Detection and Duration Analysis in Real Time 2001
K. Grauman, M. Betke, J. Gips, and G. Bradski, In IIEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2001.