Erik Learned-Miller Erik G. Learned-Miller
Professor and Chair of the Faculty
The Manning College of Information and Computer Sciences
University of Massachusetts, Amherst

140 Governors Drive, Office 200
Amherst, MA 01003

E-mail: elm at cs.umass.edu
Computer Vision Lab

News:

  • We have started work on a New Building! Check out the College web pages for architectural drawings and renderings.
  • On September 1, 2022, I started my new position as Chair of the Faculty in the Manning College of Information and Computer Sciences. I continue to co-direct the Computer Vision Lab with Subhransu Maji.

Home Publications Students Teaching Funding Code FAQ

By Date

By Area

By Keyword

By Type

By Publication Locale
Publications by Keyword

Backgrounding | Bounds | Color | Congealing (joint alignment) | Detection | Distribution Fields | Entropy | Face Recognition and Modeling | Gene Expression | Hyper-Features | Independent Components Analysis | Motion Estimation and Segmentation | Neural Net Architectures | Object Recognition | Learning from One Example | Medical and Biological Image Registration | Mobile Manipulation | Mutual Information | OCR and Text Recognition | Security | Segmentation | Self-Supervised Learning | Tracking
Backgrounding
Theoretical bounds
Color
  • Kinh Tieu and Erik Miller.
    Unsupervised color constancy.
    In Neural Information Processing Systems (NIPS) 15, pp. 1303-1310, 2003.
    [pdf]

  • Erik Miller and Kinh Tieu.
    Color eigenflows: Statistical modeling of joint color changes.
    International Conference on Computer Vision (ICCV), Volume 1, pp. 607-614, 2001.
    [pdf]

  • Erik Miller, Kinh Tieu and Eric Grimson.
    Lighting invariance through joint color change models.
    Proceedings of Workshop on Identifying Object Across Variations in Lighting: Psychophysics and Computation, at IEEE Conference on Computer Vision and Pattern Recognition, 2001.
    [pdf]

  • Erik Miller, Kinh Tieu and Chris Stauffer.
    Learning object-independent modes of variation with feature flow fields.
    Massachusetts Institute of Technology, AI-Memo: AIM-2001-021, 9 pages, 2001.
    [pdf]

Congealing (Joint Alignment)
  • Gary B. Huang, Marwan Mattar, Honglak Lee, and Erik Learned-Miller.
    Learning to align from scratch.
    In Neural Information Processing Systems (NIPS) , 2012.
    [pdf]

  • Marwan Mattar, Allen Hanson, and Erik Learned-Miller.
    Unsupervised joint alignment and clustering using Bayesian nonparametrics.
    Proceedings of the Conference on Uncertainty in Artificial Intelligence (UAI), 2012.
    [pdf]

  • Laura Sevilla Lara and Erik Learned-Miller.
    Distribution Fields.
    UMass Amherst Technical Report UM-CS-2011-027, 18 pages, 2011.
    [pdf]

  • Marwan Mattar, Michael G. Ross and Erik Learned-Miller.
    Non-parametric curve alignment.
    International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2009.
    [pdf]

  • Gary B. Huang, Vidit Jain, and Erik Learned-Miller.
    Unsupervised joint alignment of complex images.
    International Conference on Computer Vision (ICCV), 2007.
    [pdf]

  • Erik Learned-Miller.
    Data driven image models through continuous joint alignment.
    In IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 28:2, pp. 236-250, 2006.
    [pdf]

  • Erik Miller, Nick Matsakis, and Paul Viola.
    Learning from one example through shared densities on transforms.
    Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Volume 1, pp. 464-471, 2000.
    [pdf]

  • Lilla Zollei, Erik Learned-Miller, Eric Grimson, and William Wells.
    Efficient population registration of 3D data.
    In Workshop on Computer Vision for Biomedical Image Applications: Current Techniques and Future Trends, at the International Conference of Computer Vision (best paper award), 2005.
    [pdf]

  • Erik Learned-Miller and Vidit Jain.
    Many heads are better than one: Jointly removing bias from multiple MRs using nonparametric maximum likelihood.
    In Proceedings of Information Processing in Medical Imaging, pp. 615-626, 2005.
    [pdf]

  • Erik Learned-Miller and Parvez Ahammad.
    Joint MRI bias removal using entropy minimization across images.
    In Neural Information Processing Systems (NIPS) 17, pp. 761-768, 2005.
    [pdf]

  • Chris Stauffer, Erik Miller and Kinh Tieu.
    Transform-invariant image decomposition with similarity templates.
    In Neural Information Processing Systems (NIPS) 14, pp. 1295-1302, 2002.
    [pdf]

Detection
Distribution Fields
Entropy
  • Erik Learned-Miller and Joseph DeStefano.
    A probabilistic upper bound on differential entropy.
    IEEE Transactions on Information Theory, Vol. 54, No. 11, pp. 5223-5230, 2008.
    [pdf]

  • Erik Learned-Miller.
    Data driven image models through continuous joint alignment.
    In IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 28:2, pp. 236-250, 2006.
    [pdf]

  • Erik Miller, Nick Matsakis, and Paul Viola.
    Learning from one example through shared densities on transforms.
    Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Volume 1, pp. 464-471, 2000.
    [pdf]

  • Erik Miller.
    A new class of entropy estimators for multi-dimensional densities.
    International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2003.
    [pdf]

  • Erik Learned-Miller and Parvez Ahammad.
    Joint MRI bias removal using entropy minimization across images.
    In Neural Information Processing Systems (NIPS) 17, pp. 761-768, 2005.
    [pdf]

  • Erik Learned-Miller and Vidit Jain.
    Many heads are better than one: Jointly removing bias from multiple MRs using nonparametric maximum likelihood.
    In Proceedings of Information Processing in Medical Imaging, pp. 615-626, 2005.
    [pdf]

  • Lilla Zollei, Erik Learned-Miller, Eric Grimson, and William Wells.
    Efficient population registration of 3D data.
    In Workshop on Computer Vision for Biomedical Image Applications: Current Techniques and Future Trends, at the International Conference of Computer Vision (best paper award), 2005.
    [pdf]

  • Erik Learned-Miller and John W. Fisher, III.
    ICA using spacings estimates of entropy.
    Journal of Machine Learning Research (JMLR), Volume 4, pp. 1271-1295, 2003.
    [pdf]

  • Simon Warfield, Jan Rexilius, Petra Huppi, Terrie Inder, Erik Miller, William Wells, Gary Zientara, Ferenc Jolesz, and Ron Kikinis.
    A binary entropy measure to assess nonrigid registration algorithms.
    Proceedings of Medical Image Computing and Computer-Assisted Intervention (MICCAI), pp. 266-274, 2001.
    [pdf]

  • Joseph DeStefano, Qifeng Lu, and Erik Learned-Miller.
    A probabilistic upper bound on differential entropy.
    UMass Amherst Technical Report 05-12, 2005.
    [pdf]

  • Erik Learned-Miller.
    Hyperspacings and the estimation of information theoretic quantities.
    UMass Amherst Technical Report 04-104, 2004.
    [pdf]

Face Recognition and Modeling
  • Joy Buolamwini, Vicente Ordonez, Jamie Morgenstern, and Erik Learned-Miller.
    Facial Recognition Technologies: A Primer.
    18 pages, May 29, 2020.
    [pdf]

  • Erik Learned-Miller, Vicente Ordonez, Jamie Morgenstern, and Joy Buolamwini.
    Facial Recognition Technologies in the Wild: A Call for a Federal Office.
    56 pages, May 29, 2020.
    [pdf]

  • Aruni RoyChowdhury, Xiang Yu, Kihyuk Sohn, Erik Learned-Miller, and Manmohan Chandraker.
    Improving recognition with unlabeled faces in the wild.
    European Conference on Computer Vision (ECCV), 2020.
    [pdf]

  • Gary B. Huang and Erik Learned-Miller.
    Labeled Faces in the Wild: Updates and new reporting procedures.
    UMass Amherst Technical Report UM-CS-2014-003, 5 pages, 2014.
    [pdf]

  • SouYoung Jin, Hang Su, Chris Stauffer, and Erik Learned-Miller.
    End-to-end face detection and cast grouping in movies using Erdos-Renyi clustering.
    International Conference on Computer Vision (ICCV), 10 pages, 2017.
    [pdf] [Project page]

  • Huaizu Jiang and Erik Learned-Miller.
    Face detection with the Faster R-CNN.
    IEEE Conference on Automatic Face and Gesture Recognition (FandG), 6 pages, 2017.
    [pdf]

  • Aruni RoyChowdhury, Tsung-Yu Lin, Subhransu Maji, and Erik Learned-Miller.
    One-to-many face recognition with bilinear CNNs.
    Winter Conference on Applications of Computer Vision (WACV), 2016.
    [pdf]

  • Erik Learned-Miller, Gary B. Huang, Aruni RoyChowdhury, Haoxiang Li, and Gang Hua.
    Labeled Faces in the Wild: A Survey.
    In Advances in Face Detection and Facial Image Analysis,, edited by Michal Kawulok, M. Emre Celebi, and Bogdan Smolka, Springer, pages 189-248, 2016.
    [Springer Page] [Draft pdf]

  • Andrew Kae, Benjamin Marlin, and Erik Learned-Miller.
    The shape-time random field for semantic video labeling.
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014.
    [pdf]

  • Andrew Kae*, Kihyuk Sohn*, Honglak Lee and Erik Learned-Miller.
    Augmenting CRFs with Boltzmann machine shape priors for image labeling.
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013.
    *The first and second authors made equal contributions and should be considered co-first authors.
    [pdf]

  • Gary B. Huang, Marwan Mattar, Honglak Lee, and Erik Learned-Miller.
    Learning to align from scratch.
    In Neural Information Processing Systems (NIPS) , 2012.
    [pdf]

  • Gary B. Huang, Honglak Lee, and Erik Learned-Miller.
    Learning hierarchical representations for face verification.
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2012.
    [pdf]

  • Gang Hua, Ming-Hsuan Yang, Erik Learned-Miller, Yi Ma, Matthew Turk, David J. Kriegman, and Thomas S. Huang.
    Introduction to the special section on real-world face recognition.
    IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), Vol. 33, No. 10, pp. 1921-1924, 2011.
    [pdf]

  • Vidit Jain and Erik Learned-Miller.
    Online domain-adaptation of a pre-trained cascade of classifiers.
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011.
    [pdf]

  • Ralph E. Miller, Erik Learned-Miller, Peter Trainer, Angela Paisley and Volker Blanz.
    Early diagnosis of acromegaly: computers vs clinicians.
    Clinical Endocrinology, Vol. 75, No. 2, pp. 226-231, 2011.
    [pdf]

  • Vidit Jain and Erik Learned-Miller.
    FDDB: A benchmark for face detection in unconstrained settings.
    UMass Amherst Technical Report UM-CS-2010-009, 11 pages, 2010.
    [pdf]

  • Gary B. Huang, Michael J. Jones, and Erik Learned-Miller.
    LFW results using a combined Nowak plus MERL recognizer.
    In The Workshop on Faces in Real-Life Images at European Conference on Computer Vision, 2008.
    [pdf]

  • Gary B. Huang, Marwan Mattar, Tamara Berg, and Erik Learned-Miller.
    Labeled faces in the wild: A database for studying face recognition in unconstrained environments.
    In The Workshop on Faces in Real-Life Images at European Conference on Computer Vision, 2008.
    [pdf]

  • Erik Learned-Miller, Peter Trainer, Angela Paisley, Volker Blanz, and Ralph Miller.
    Acromegalic features: Recognition by physicians versus a computer model.
    In The Program and Abstracts Book of the 90th Meeting of the Endocrine Society, San Francisco, June, 2008.

  • Gary B. Huang, Manjunath Narayana, and Erik Learned-Miller.
    Towards unconstrained face recognition.
    In The Sixth IEEE Computer Society Workshop on Perceptual Organization in Computer Vision IEEE CVPR, 2008.
    [pdf]

  • Andras Ferencz, Erik Learned-Miller, and Jitendra Malik.
    Learning to locate informative features for visual identification.
    International Journal of Computer Vision: Special Issue on Learning and Vision, Vol. 77, No. 1, pp. 3-24, May, 2008.
    [pdf]

  • Tamara L. Berg, Alex C. Berg, Jaety Edwards, Michael Maire, Ryan White, Yee Whye Teh, Erik Learned-Miller, and David Forsyth.
    Names and faces.
    To appear International Journal of Computer Vision, 2008.

  • Gary B. Huang, Manu Ramesh, Tamara Berg and Erik Learned-Miller.
    Labeled Faces in the Wild: A database for studying face recognition in unconstrained environments.
    UMass Amherst Technical Report 07-49, 11 pages, 2007.
    [pdf]

  • Gary B. Huang, Vidit Jain, and Erik Learned-Miller.
    Unsupervised joint alignment of complex images.
    International Conference on Computer Vision (ICCV), 2007.
    [pdf]

  • Vidit Jain, Erik Learned-Miller, and Andrew McCallum.
    People-LDA: Anchoring topics to people using face recognition.
    International Conference on Computer Vision (ICCV), 2007.
    [pdf]

  • Vidit Jain, Andras Ferencz and Erik Learned-Miller.
    Discriminative training of hyper-feature models for object identification.
    Proceedings of the British Machine Vision Conference (BMVC), Volume 1, pp. 357-366, 2006.
    [pdf]

  • Erik Learned-Miller, Qifeng Lu, Angela Paisley, Peter Trainer, Volker Blanz, Katrin Dedden, and Ralph E. Miller.
    Detecting acromegaly: Screening for disease with a morphable model.
    Medical Image Computing and Computer-Assisted Intervention (MICCAI), Volume 2, pp. 495-503, 2006.
    [pdf]

  • Andras Ferencz, Erik Learned-Miller, and Jitendra Malik.
    Building a classification cascade for visual identification from one example.
    In International Conference on Computer Vision (ICCV), pp. 286-293, 2005.
    [pdf]

  • Andras Ferencz, Erik Learned-Miller and Jitendra Malik.
    Learning hyper-features for visual identification.
    In Neural Information Processing Systems (NIPS) 17, pp. 425-432, 2005.
    [pdf]

  • Erik Learned-Miller, Qifeng Lu, Angela Paisley, Peter Trainer, Volker Blanz, Katrin Dedden, and Ralph Miller.
    Early diagnosis of acromegaly by facial pattern recognition.
    Abstract for The Ninth International Pituitary Congress, San Diego, CA, 2005.

  • Qifeng Lu, Erik Learned-Miller, Angela Paisley, Peter Trainer, Volker Blanz, Katrin Dedden, and Ralph Miller.
    Detecting acromegaly: Screening for diseases with a morphable model.
    UMass Amherst Technical Report 05-37, 2005.
    [pdf]

Gene Expression
Hyper-Features
Independent Components Analysis
Motion Estimation and Segmentation
Neural net architectures
Object Recognition
  • Hang Su, Subhransu Maji, Evangelos Kalogerakis, and Erik Learned-Miller.
    Multi-view convolutional neural networks for 3D shape recognition.
    International Conference on Computer Vision (ICCV), 9 pages, 2015.
    [project] [pdf]

  • Vidit Jain and Erik Learned-Miller.
    FDDB: A benchmark for face detection in unconstrained settings.
    UMass Amherst Technical Report UM-CS-2010-009, 11 pages, 2010.
    [pdf]

  • Gary B. Huang, Manu Ramesh, Tamara Berg and Erik Learned-Miller.
    Labeled Faces in the Wild: A database for studying face recognition in unconstrained environments.
    UMass Amherst Technical Report 07-49, 11 pages, 2007.
    [pdf]

  • Andras Ferencz, Erik Learned-Miller, and Jitendra Malik.
    Learning to locate informative features for visual identification.
    International Journal of Computer Vision: Special Issue on Learning and Vision, Vol. 77, No. 1, pp. 3-24, May, 2008.
    [pdf]

  • Vidit Jain, Erik Learned-Miller, and Andrew McCallum.
    People-LDA: Anchoring topics to people using face recognition.
    International Conference on Computer Vision (ICCV), 2007.
    [pdf]

  • Vidit Jain, Andras Ferencz and Erik Learned-Miller.
    Discriminative training of hyper-feature models for object identification.
    Proceedings of the British Machine Vision Conference (BMVC), Volume 1, pp. 357-366, 2006.
    [pdf]

  • Andras Ferencz, Erik Learned-Miller and Jitendra Malik.
    Learning hyper-features for visual identification.
    In Neural Information Processing Systems (NIPS) 17, pp. 425-432, 2005.
    [pdf]

  • Andras Ferencz, Erik Learned-Miller, and Jitendra Malik.
    Building a classification cascade for visual identification from one example.
    In International Conference on Computer Vision (ICCV), pp. 286-293, 2005.
    [pdf]

Learning from one example
  • Andras Ferencz, Erik Learned-Miller, and Jitendra Malik.
    Learning to locate informative features for visual identification.
    International Journal of Computer Vision: Special Issue on Learning and Vision, Vol. 77, No. 1, pp. 3-24, May, 2008.
    [pdf]

  • Vidit Jain, Andras Ferencz and Erik Learned-Miller.
    Discriminative training of hyper-feature models for object identification.
    Proceedings of the British Machine Vision Conference (BMVC), Volume 1, pp. 357-366, 2006.
    [pdf]

  • Erik Miller, Nick Matsakis, and Paul Viola.
    Learning from one example through shared densities on transforms.
    Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Volume 1, pp. 464-471, 2000.
    [pdf]

  • Erik Miller.
    Learning from one example in machine vision by sharing probability densities.
    Ph.D. Thesis, Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2002.
    [pdf]

  • Andras Ferencz, Erik Learned-Miller, and Jitendra Malik.
    Building a classification cascade for visual identification from one example.
    In International Conference on Computer Vision (ICCV), pp. 286-293, 2005.
    [pdf]

  • Andras Ferencz, Erik Learned-Miller and Jitendra Malik.
    Learning hyper-features for visual identification.
    In Neural Information Processing Systems (NIPS) 17, pp. 425-432, 2005.
    [pdf]

  • Erik Miller, Kinh Tieu and Chris Stauffer.
    Learning object-independent modes of variation with feature flow fields.
    Massachusetts Institute of Technology, AI-Memo: AIM-2001-021, 9 pages, 2001.
    [pdf]

  • Erik Miller and Kinh Tieu.
    Color eigenflows: Statistical modeling of joint color changes.
    International Conference on Computer Vision (ICCV), Volume 1, pp. 607-614, 2001.
    [pdf]

Medical and Biological Image Registration
  • Manjunatha Jagalur, Chris Pal, Erik Learned-Miller, R. Thomas Zoeller and David Kulp.
    Analyzing in situ gene expression in the mouse brain with image registration, feature extraction and block clustering.
    BMC Bioinformatics, 8(Suppl 10):S5, 2007.
    [pdf]

  • Manjunatha N. Jagalur, Chris Pal, Erik Learned-Miller, R. T. Zoeller and David Kulp.
    The processing and analysis of in situ gene expression images of the mouse brain.
    Workshop on New Problems and Methods in Computational Biology, at Neural Information Processing Systems, 2006.
    [pdf]

  • Lilla Zollei, Erik Learned-Miller, Eric Grimson, and William Wells.
    Efficient population registration of 3D data.
    In Workshop on Computer Vision for Biomedical Image Applications: Current Techniques and Future Trends, at the International Conference of Computer Vision (best paper award), 2005.
    [pdf]

  • Douglas Cohen, Jonathan Lustgarten, Erik Miller, Alexander Khandji and Robert Goodman.
    Effects of coregistration of MR to CT images on MR stereotactic accuracy.
    Journal of Neurosurgery, Volume 82, pp. 772-779, 1995.

  • Robert Malison, Erik Miller, Robin Greene, Greg McCarthy, Dennis Charney and Robert Innis.
    Computer assisted coregistration of multislice SPECT and MR brain images by fixed external fiducials.
    Journal of Computer Assisted Tomography, Volume 17, pp. 952-960, 1993.
Mobile Manipulation
  • Li Yang Ku, Erik Learned-Miller and Rod Grupen.
    Modeling objects as aspect transition graphs to support manipulation.
    International Symposium of Robotics Research (ISRR), 16 pages, 2015.
    [pdf]

  • Li Yang Ku, Shiraj Sen, Erik Learned-Miller and Rod Grupen.
    Action-based models for belief-space planning.
    In Workshop on Information-Based Grasp and Manipulation Planning, at Robotics: Science and Systems, 6 pages, July, 2014.
    [pdf]

  • Li Yang Ku, Shiraj Sen, Erik Learned-Miller and Rod Grupen.
    The aspect transition graph: An affordance-based model.
    In Second Workshop on Affordances: Visual Perception of Affordances and Functional Visual Primitives for Scene Analysis, at the European Conference on Computer Vision, 7 pages, September, 2014.
    [pdf]

  • Dov Katz, Emily Horrell, Yuandong Yang, Brendan Burns, Thomas Buckley, Anna Grishkan, Volodymyr Zhylkovskyy, Oliver Brock, and Erik Learned-Miller.
    The UMass mobile manipulator UMan: An experimental platform for autonomous mobile manipulation.
    In Workshop on Manipulation in Human Environments, at Robotics: Science and Systems, 2006.
    [pdf]

Mutual Information
  • Marwan Mattar, Michael G. Ross and Erik Learned-Miller.
    Non-parametric curve alignment.
    International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2009.
    [pdf]

  • Andras Ferencz, Erik Learned-Miller, and Jitendra Malik.
    Learning to locate informative features for visual identification.
    International Journal of Computer Vision: Special Issue on Learning and Vision, Vol. 77, No. 1, pp. 3-24, May, 2008.
    [pdf]

  • Marwan Mattar and Erik Learned-Miller.
    Improved generative models for continuous image features through tree-structured non-parametric distributions.
    UMass Amherst Technical Report 06-57, 10 pages, 2006.
    [pdf]

  • Vidit Jain, Andras Ferencz and Erik Learned-Miller.
    Discriminative training of hyper-feature models for object identification.
    Proceedings of the British Machine Vision Conference (BMVC), Volume 1, pp. 357-366, 2006.
    [pdf]

  • Manjunatha N. Jagalur, Chris Pal, Erik Learned-Miller, R. T. Zoeller and David Kulp.
    The processing and analysis of in situ gene expression images of the mouse brain.
    Workshop on New Problems and Methods in Computational Biology, at Neural Information Processing Systems, 2006.
    [pdf]

  • Andras Ferencz, Erik Learned-Miller, and Jitendra Malik.
    Building a classification cascade for visual identification from one example.
    In International Conference on Computer Vision (ICCV), pp. 286-293, 2005.
    [pdf]

  • Andras Ferencz, Erik Learned-Miller and Jitendra Malik.
    Learning hyper-features for visual identification.
    In Neural Information Processing Systems (NIPS) 17, pp. 425-432, 2005.
    [pdf]

  • Erik Learned-Miller.
    Hyperspacings and the estimation of information theoretic quantities.
    UMass Amherst Technical Report 04-104, 2004.
    [pdf]

OCR and Text Recognition
  • Jacqueline Feild, Erik Learned-Miller and David A. Smith.
    Using a probabilistic syllable model to improve scene text recognition.
    Proceedings of the International Conference on Document Analysis and Recognition (ICDAR), 2013.
    [pdf]

  • Jacqueline Feild and Erik Learned-Miller.
    Improving open-vocabulary scene text recognition.
    Proceedings of the International Conference on Document Analysis and Recognition (ICDAR), 2013.
    [pdf]

  • Yahan Zhou, Jacqueline Feild, Rui Wang, and Erik Learned-Miller.
    Scene text segmentation via inverse rendering.
    Proceedings of the International Conference on Document Analysis and Recognition (ICDAR), 2013.
    [pdf]

  • Jacqueline Feild and Erik Learned-Miller.
    Scene text recognition with bilateral regression.
    UMass Amherst Technical Report UM-CS-2012-021, 15 pages, 2012.
    [pdf]

  • Gary B. Huang, Andrew Kae, Carl Doersch, and Erik Learned-Miller.
    Bounding the probability of error for high precision optical character recognition.
    Journal of Machine Learning Research (JMLR), Volume 13, pp. 363-387, 2012.
    [pdf]

  • David L. Smith, Jacqueline Feild, and Erik Learned-Miller.
    Enforcing similarity constraints with integer programming for better scene text recognition.
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011.
    [pdf]

  • Andrew Kae, David A. Smith and Erik Learned-Miller.
    Learning on the fly: A font-free approach towards multilingual OCR.
    International Journal on Document Analysis and Recognition (IJDAR), Vol. 14, No. 3, 13 pages, 2011.
    [pdf]

  • Andrew Kae, Gary B. Huang, Carl Doersch, and Erik Learned-Miller.
    Improving state-of-the-art OCR through high-precision document-specific modeling.
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2010.
    [pdf]

  • Andrew Kae, Gary B. Huang, and Erik Learned-Miller.
    Bounding the probability of error for high precision recognition.
    UMass Amherst Technical Report UM-CS-2009-031, 12 pages, 2009.
    [pdf]

  • Andrew Kae and Erik Learned-Miller.
    Learning on the fly: Font free approaches to difficult OCR problems.
    Proceedings of the International Conference on Document Analysis and Recognition (ICDAR), 2009.
    [pdf]

  • Jerod Weinman, Erik Learned-Miller and Allen Hanson.
    Scene text recognition using similarity and a lexicon with sparse belief propagation.
    IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), Special Issue on Probabilistic Graphical Models, Vol. 31, No. 10, pp. 1733-1746, 2009.
    [pdf]

  • Jerod Weinman, Erik Learned-Miller, and Allen Hanson.
    A discriminative semi-Markov model for robust scene text recognition.
    In International Conference on Pattern Recognition (ICPR), 2008.
    [pdf]

  • Michael Wick, Michael G. Ross and Erik Learned-Miller.
    Context-sensitive error correction: Using topic models to improve OCR.
    Proceedings of the International Conference on Document Analysis and Recognition (ICDAR), 2007.
    [pdf]

  • Jerod Weinman, Erik Learned-Miller, and Allen Hanson.
    Fast lexicon-based scene text recognition with sparse belief propagation.
    Proceedings of the International Conference on Document Analysis and Recognition (ICDAR), 2007.
    [pdf]

  • Gary C. Huang, Erik Learned-Miller, and Andrew McCallum.
    Cryptogram decoding for OCR using numerization strings.
    Proceedings of the International Conference on Document Analysis and Recognition (ICDAR), 2007.
    [pdf]

  • Jerod Weinman and Erik Learned-Miller.
    Improving recognition of novel input with similarity.
    In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Volume 1, pp. 308-315, 2006.
    [pdf]

  • Jerod J. Weinman, Allen Hanson and Erik Learned-Miller.
    Joint feature selection for object detection and recognition.
    UMass Amherst Technical Report 06-54, 8 pages, 2006.
    [pdf]

  • Gary Huang, Erik Learned-Miller and Andrew McCallum.
    Cryptogram decoding for optical character recognition.
    UMass Amherst Technical Report 06-45, 12 pages, 2006.
    [pdf]

  • Erik Miller and Paul Viola.
    Ambiguity and constraint in mathematical expression recognition.
    Proceedings of the National Conference of Artificial Intelligence (AAAI), pp. 784-791, 1998.
    [pdf]

Security
Segmentation
Self-Supervised Learning
Tracking