- Scene Text Recognition using Similarity and a Lexicon with Sparse Belief Propagation with E. Learned-Miller and A. Hanson. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI) 21. Oct. 2009 . [PDF] [bib] [doi]
- A Discriminative Semi-Markov Model for Robust Scene Text Recognition with E. Learned-Miller and A. Hanson. Intl. Conference on Pattern Recognition (ICPR) Dec. 2008. [PDF] [bib]
- Efficiently Learning Random Fields for Stereo Vision with Sparse Message Passing with L. Tran and C. Pal. European Conference on Computer Vision (ECCV) Oct. 2008. [PDF] [bib]
- Fast Lexicon-Based Scene Text Recognition with Sparse Belief Propagation, with E. Learned-Miller and A. Hanson. Intl. Conference on Document Analysis and Recognition (ICDAR) Sept. 2007. [PDF] [bib] [doi]
- Techniques and Applications for Persistent Backgrounding in a Humanoid Torso Robot, with D. W. Duhon† and E. Learned-Miller. IEEE Intl. Conference on Robotics and Automation (ICRA), April 2007 [PDF] [bib] [doi].
- Improving Recognition of Novel Input with Similarity, with E. Learned-Miller. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) June 2006. [PDF] [bib] [doi]
- Nonlinear diffusion scale-space and fast marching level sets for segmentation of MR imagery and volume estimation of stroke lesions, with G. Bissias, E. Riseman, A. Hanson, and J. Horowitz. In Sixth Annual International Conference Medical Image Computing and Computer Assisted Intervention (MICCAI), Nov 2003. [PS.gz] [PDF] [bib] [doi]
Refereed Workshops
- A Discriminative Semi-Markov Model for Robust Scene Text Recognition, with E. Learned-Miller and A. Hanson. New England Student Colloquium on Artificial Intelligence May 2008. [PDF] [bib]
- Automatic Sign Detection and Recognition in Natural Scenes, with P. Silapachote†, A. Hanson, R. Weiss, and M.A. Mattar. IEEE Workshop on Computer Vision Applications for the Visually Impaired June 2005. [PDF] [bib] [doi]
- Sign Detection in Natural Images with Conditional Random Fields, with A. Hanson and A. McCallum. IEEE International Workshop on Machine Learning for Signal Processing (MLSP), pp. 549-558. Sept. 2004 [PS.gz] [PDF] [bib] [doi]
Ph.D. Thesis
- Unified Detection and Recognition for Reading Text in Scene Images Ph.D. Thesis, University of Massachusetts Amherst, May 2008. [PDF] [bib]
Technical Reports
- Sparse Message Passing and Efficiently Learning Random Fields for Stereo Vision Technical Report UM-CS-2007-054, University of Massachusetts-Amherst, Amherst, MA 01003-4601, Oct. 2007. [PDF] [bib]
- Joint Feature Selection for Object Detection and Recognition Technical Report UM-CS-2006-054, University of Massachusetts-Amherst, Amherst, MA 01003-4601, Oct. 2006. [PDF] [bib]
- Data-Dependent Spatial Context for Computer Vision with Conditional Markov Fields Technical Report UM-CS-2005-052 / Master's Project Report, University of Massachusetts-Amherst, Amherst, MA 01003-4601, Sept. 2005. [PDF] [bib]
- Confidence-based segmentation of MR imagery using region and boundary information with nonlinear scale-space and fast marching level sets, with G. Bissias, E. Riseman, A. Hanson, and J. Horowitz. Technical Report UM-CS-2003-017, University of Massachusetts-Amherst, Amherst, MA 01003-4601, April 2003. [PS.gz] [PDF] [bib]
Talks
- An Alternative to Modeling Appearance: Modeling Relative Appearance, with E. Learned-Miller. NIPS Interclass Transfer Workshop: Why Learning to Recognize Many Objects Might be Easier Than Learning to Recognize Just One, 10 December 2005. [PDF]
- Segmentation and Volume Estimation of Ischemic Stroke Lesions in MR Images, with G. Bissias. Annual Conference of the UMass/Baystate Collaborative Biomedical Research Program, 20 May 2002.
† First author
This material is presented to ensure timely dissemination of scholarly
and technical work. Copyright and all rights therein are retained by
authors or by other copyright holders. All persons copying this
information are expected to adhere to the terms and constraints
invoked by each author's copyright. In most cases, these works may not
be reposted without the explicit permission of the copyright holder.
|