%% to add a publication search for "insert publications here", copy a similar entry, %% and fill in the appropriate fields. @string{aaai = "Proceedings AAAI"} @string{ai = "Artificial Intelligence"} @string{berk = "University of California Berkeley"} @string{biocyb = "Biological Cybernetics"} @string{cmu = "Carnegie-Mellon University"} @string{cacm = "Communications of the ACM"} @string{capami = "Proc. 1987 Workshop on Comp. Arch. for Patt. Anal. and Mach. Intell."} @string{vs99 = "Second IEEE Workshop on Visual Surveillance"} @string{computer = "IEEE Computer"} @string{cgip = "Computer Graphics and Image Processing"} @string{cvgip = "Computer Vision, Graphics, and Image Processing"} @string{cviu = "Computer Vision and Image Understanding"} @string{cvpr = "Proceedings IEEE Conf. on Computer Vision and Pattern Recognition"} @string{focs = "Proceedings Symposium on Foundations of Comp. Sci."} @string{iccv = "Proceedings of the International Conference on Computer Vision"} @string{icpp = "Proceedings Int. Conf. on Parallel Processing"} @string{icpr = "Proceedings Int. Conf. on Pattern Recognition"} @string{ieee = "Proceedings of the IEEE"} @string{ijcai = "Proceedings IJCAI"} @string{ijcv = "International Journal of Computer Vision"} @string{iu = "Proceedings Image Understanding Workshop"} @string{josa = "Journal of the Optical Society of America"} @string{jrr = "International Journal of Robotics Research"} @string{mit = "Massachusetts Institute of Technology"} @string{mitai = "Artificial Intelligence Laboratory, Massachusetts Institute of Technology"} @string{opteng = "Optical Engineering"} @string{pami = "IEEE Transactions on Pattern Analysis and Machine Intelligence"} @string{patt = "Proceedings Int. Conf. on Pattern Recognition"} @string{pnas = "Proceedings of the National Academy of Science"} @string{pr = "Pattern Recognition"} @string{prip = "Proceedings of IEEE Computer Society Conference on Pattern Recognition and Image Processing"} @string{prsl = "Proceedings of the Royal Society of London"} @string{prslb = "Proceedings of the Royal Society of London B"} @string{robau = "Proceedings of IEEE Conference on Robotics and Automation"} @string{sciam = "Scientific American"} @string{siam = "SIAM J. Comp."} @string{stoc = "Proceedings ACM Symposium on Theory of Computing"} @string{tmc = "Thinking Machines Corporation"} @string{visres = "Vision Research"} @string{jcogneuro = "Journal of Cognitive Neuroscience"} @string{jexppsych = "Journal of Experimental Psychology"} @string{annrevneuro = "Annual Review of Neuroscience"} @string{Ailab = "MIT Artificial Intelligence Laboratory"} @string{media-vision = "MIT Media Laboratory Vision and Modeling Group"} @string{aaai-87 = "Sixth National Conference on Artificial Intelligence"} @string{bbs = "Brain and Behavioral Sciences"} @string{belknap = "The Belknap Press of Harvard University Press"} @string{mit = "Massachusetts Institute of Technology"} @string{mitpress = "MIT Press"} @string{ieee-proc = "Proceedings of the IEEE"} @string{ieee-ra = "IEEE Journal of Robotics and Automation"} @string{ieee-ra-86 = "The 1986 IEEE Conference an Robotics and Automation"} @string{ieee-smc = "IEEE Transactions on Systems, Man, and Cybernetics"} @string{ieee-com = "IEEE Transactions on Communications"} @string{ieee-nn = "IEEE Transactions on Neural Networks"} @string{ijcai-87 = "Tenth International Joint Conference on Artificial Intelligence"} @string{umass = "University of Massachusetts at Amherst"} @string{nips = "Advances in Neural Information Processing"} @string{Tnips2 = "Advances in Neural Information Processing 2"} @string{Tnips3 = "Advances in Neural Information Processing 3"} @string{Tnips4 = "Advances in Neural Information Processing 4"} @string{Tnips5 = "Advances in Neural Information Processing 5"} @string{Tnips6 = "Advances in Neural Information Processing 6"} @string{jneusci= "Journal of Neuroscience"} @string{icsi = "Internation Computer Science Institute"} @string{neuropros = "Placed in the Neuroprose archive."} @string{aaaisymp93 = "AAAI Fall Symposium Series Working Notes"} @string{colt = "Proceedings of the Conference on Computational Learning Theory"} @string{ACM = "Association for Computing Machinery"} %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% %% insert publications here %% @inProceedings{Warfield_MICCAI, author="Simon Warfield and Jan Rexilius and Petra Huppi and Terrie Inder and Erik Miller and William Wells and Gary Zientara and Ferenc Jolesz and and Ron Kikinis", title="A Binary Entropy Measure to Assess Nonrigid Registration Algorithms.", booktitle="Proceedings Medical Image Computing and Computer-Assisted Intervention", year="2001" } @inProceedings{MillerTieu01, author="Erik Miller and Kinh Tieu", title="Color Eigenflows: Statistical Modeling of Joint Color Changes", booktitle=iccv, year="2001", urlpdf="http://www.ai.mit.edu/people/emiller/papers/Miller_color_flows.pdf" } @Article{Dror_JOSA_01, author = "Dror, R. O. and O'Carroll, D. C. and Laughlin, S. B.", title = "Accuracy of velocity estimation by Reichardt correlators", journal = "Journal of the Optical Society of America A", year = "2001", volume = "18", number = "?", pages = "241-252", urlpdf = "http://www.ai.mit.edu/people/rondror/papers/dror_josa_01.pdf" } @InProceedings{Dror_BMCV_00, author = "Dror, R. O. and O'Carroll, D. C. and Laughlin, S. B.", title = "The Role of Natural Image Statistics in Biological Motion Estimation", booktitle = "Biologically Motivated Computer Vision", pages = "492--501", year = "2000", editor = "Lee, Seong-Whan and Bulthoff, Heinrich H. and Poggio, Tomaso", volume = "1811", series = "Lecture Notes in Computer Science", address = "Seoul, Korea", month = "May", organization = "First IEEE International Workshop, BMCV 2000", publisher = "Springer", urlpdf = "http://www.ai.mit.edu/people/rondror/papers/dror_bmcv_00.pdf" } @InProceedings{Dror_SCTV_01, author = "Dror, R. O. and Adelson, E. H. and Willsky, A. S.", title = "Surface Reflectance Estimation and Natural Illumination Statistics", booktitle = "Proceedings of the Second International Workshop on Statistical and Computational Theories of Vision", year = "2001", address = "Vancouver, Canada", month = "July", urlpdf = "http://www.ai.mit.edu/people/rondror/papers/dror_sctv_01.pdf" } @InProceedings{Dror_01, author = "Dror, R. O. and Adelson, E. H. and Willsky, A. S.", title = "Estimating surface reflectance properties from images under unknown illumination", booktitle = "SPIE Conference on Human Vision and Electronic Imaging", address = "San Jose, CA", year = "2001", pages = "231-242" urlpdf = "http://www.ai.mit.edu/people/rondror/papers/dror_spie_01.pdf" } @Article{StaufferGrimson_PAMI99, author = "Chris Stauffer and Eric Grimson", title = "Learning Patterns of Activity Using Real-Time Tracking", journal = pami, volume = 22, number = 8, pages = "747-757" year = "Aug 2000" urlps = "http://www.ai.mit.edu/people/stauffer/Papers/vsam-pami-tracking.ps", urlpdf = "http://www.ai.mit.edu/people/stauffer/Papers/vsam-pami-tracking.pdf", url = "http://www.ai.mit.edu/projects/vsam/" } @InProceedings{IvanovEtAl_VS99, author = "Yuri Ivanov and Chris Stauffer and Aaron Bobick and W.E.L. Grimson", title = "Video Surveillance of Interactions", journal = vs99, address = "Fort Collins, Colorado, June 26, 1999", urlpsgz = "http://www.ai.mit.edu/people/stauffer/Papers/interactions_CVPRVS99-ready.ps" urlpdf = "http://www.ai.mit.edu/people/stauffer/Papers/interactions_CVPRVS99-ready.pdf" url = "http://whitechapel.media.mit.edu/people/yivanov/Slides/CVPRVS99-talk/index.htm" } @InProceedings{Grimson_et_al_CVPR98, author = "W.E.L. Grimson and Chris Stauffer and Lily Lee and Raquel Romano", title = "Using Adaptive Tracking to Classify and Monitor Activities in a Site", booktitle = cvpr, pages = "22-31" year = 1998 address = "Santa Barbara, CA 1998", urlps = "http://www.ai.mit.edu/projects/vsam/Publications/vsam-cvpr98.ps" urlpdf = "http://www.ai.mit.edu/projects/vsam/Publications/vsam-cvpr98.pdf" url = "http://www.ai.mit.edu/projects/vsam/" } @InProceedings{Stauffer_hier_CVPR99, author = "Chris Stauffer", title = "Automatic hierarchical classification using time-based co-occurrences", booktitle = cvpr, pages = "333-339" year = 1999 address = "Fort Colins, CO" urlps = "http://www.ai.mit.edu/projects/vsam/Publications/stauffer_cvpr98_hier.ps" urlpdf = "http://www.ai.mit.edu/projects/vsam/Publications/stauffer_cvpr98_hier.pdf" url = "http://www.ai.mit.edu/projects/vsam/" } @InProceedings{Stauffer_track_CVPR99, author = "Chris Stauffer", title = "Adaptive background mixture models for real-time tracking", booktitle = cvpr, pages = "246-252" year = 1999 address = "Fort Colins, CO" urlps = "http://www.ai.mit.edu/projects/vsam/Publications/stauffer_cvpr98_track.ps" urlpdf = "http://www.ai.mit.edu/projects/vsam/Publications/stauffer_cvpr98_track.pdf" url = "http://www.ai.mit.edu/projects/vsam/" } @MastersThesis{Stauffer_Masters_97, author = "Chris Stauffer", title = "Scene Reconstruction Using Accumulated Line-of-Sight", school = "Massachusetts Institute of Technology", year = 1997, address = "Cambridge, MA", month = "May", urlps = "http://www.ai.mit.edu/people/stauffer/Papers/sm-thesis.ps", urlpdf = "http://www.ai.mit.edu/people/stauffer/Papers/sm-thesis.pdf", } @InProceedings{MillerMatsakisViola00, author = "Erik Miller and Nick Matsakis and Paul Viola", title = "Learning from One Example Through Shared Densities on Transforms", booktitle = cvpr, year = 2000 urlpsgz = "http://www.ai.mit.edu/people/emiller/papers/cvpr2000.ps.gz" urlpdf = "http://www.ai.mit.edu/people/emiller/papers/cvpr2000.pdf" urlimage = "http://www.ai.mit.edu/people/emiller/papers/0_big_aligned_36.gif" abstract = " We define a process called 'congealing' in which elements of a dataset (images) are brought into correspondence with each other jointly, producing a data-defined model. It is based upon minimizing the summed component-wise (pixel-wise) entropies over a continuous set of transforms on the data. One of the biproducts of this minimization is a set of transforms, one associated with each original training sample. We then demonstrate a procedure for effectively bringing test data into correspondence with the data-defined model produced in the congealing process. Subsequently, we develop a probability density over the set of transforms that arose from the congealing process. We suggest that this density over transforms may be shared by many classes, and demonstrate how using this density as ``prior knowledge'' can be used to develop a classifier based on only a single training example for each class." } @InProceedings{Snow00, author = "Dan Snow, Paul Viola and Ramin Zabih", title = "Exact Voxel Occupancy with Graph Cuts", booktitle = cvpr, year = 2000, urlpsgz = "http://www.ai.mit.edu/~viola/research/publications/snow/cvpr00.ps.gz", urlpdf = "http://www.ai.mit.edu/~viola/research/publications/snow/cvpr00.pdf", urlimage = "http://www.ai.mit.edu/~viola/research/publications/snow/cvpr00.gif", abstract = "Voxel occupancy is one approach for reconstructing the 3-dimensional shape of an object from multiple views. In voxel occupancy, the task is to produce a binary labeling of a set of voxels, that determines which voxels are filled and which are empty. In this paper, we give an energy minimization formulation of the voxel occupancy problem. The global minimum of this energy can be rapidly computed with a single graph cut, using a result due to Greig, Porteous and Seheult. The energy function we minimize contains a data term and a smoothness term. The data term is a sum over the individual voxels, where the penalty for a voxel is based on the observed intensities of the pixels that intersect it. The smoothness term is the number of empty voxels adjacent to filled ones. Our formulation can be viewed as a generalization of silhouette intersection, with two advantages: we do not compute silhouettes, which are a major source of errors; and we can naturally incorporate spatial smoothness. We give experimental results showing reconstructions from both real and synthetic imagery. Reconstruction using this smoothed energy function is not much more time consuming than simple silhouette intersection; it takes about 10 seconds to reconstruct a one million voxel volume. " } @InProceedings{tieu00, author = "Kinh Tieu and Paul Viola", title = "Boosting Image Retrieval", booktitle = cvpr, year = 2000 urlpsgz = "http://www.ai.mit.edu/~viola/research/publications/tieu/cvpr00.ps.gz" urlpdf = "http://www.ai.mit.edu/~viola/research/publications/tieu/cvpr00.pdf" urlimage = "http://www.ai.mit.edu/~viola/research/publications/tieu/jets.jpg" abstract = " We present an approach for image retrieval using a very large number of highly selective features and efficient online learning. Our approach is predicated on the assumption that each image is generated by a sparse set of visual ``causes'' and that images which are visually similar share causes. We propose a mechanism for computing a very large number of highly selective features which capture some aspects of this causal structure (in our implementation there are over 45,000 highly selective features). At query time a user selects a few example images, and a technique known as ``boosting'' is used to learn a classification function in this feature space. By construction, the boosting procedure learns a simple classifier which only relies on 20 of the features. As a result a very large database of images can be scanned rapidly, perhaps a million images per second. Finally we will describe a set of experiments performed using our retrieval system on a database of 3000 images." } @Article{Miller99, author = "Erik G. Miller", title = "Alternative Tilings for Improved Surface Area Estimates by Local Counting Algorithms", journal = cviu, volume = 74, number = 3, pages = "193-211", year = 1999 } @InProceedings{FisVioIhl99, author = "John W. Fisher and Paul A. Viola, and Alexander T. Ihler", title = "Learning Informative Statistics: A Nonparametric Approach", year = 1999, address = "Denver 1999", publisher = "MIT Press, Cambridge", volume = 12, booktitle = nips, abstract = " We discuss an information theoretic approach for categorizing and modeling dynamic processes. The approach can learn a compact and informative statistic which summarizes past states to predict future observations. Furthermore, the uncertainty of the prediction is characterized nonparametrically by a joint density over the learned statistic and present observation. We discuss the application of the technique to both noise driven dynamical systems and random processes sampled from a density which is conditioned on the past. In the first case we show results in which both the dynamics of random walk and the statistics of the driving noise are captured. In the second case we present results in which a summarizing statistic is learned on noisy random telegraph waves with differing dependencies on past states. In both cases the algorithm yields a principled approach for discriminating processes with differing dynamics and/or dependencies. The method is grounded in ideas from information theory and nonparametric statistics. " } @InProceedings{DeBonet99a, author = "J. S. {De Bonet} and P. Viola", title = "Roxels: Responsibility Weighted 3D Volume Reconstruction", booktitle = "Proceedings of ICCV", month = "September", year = "1999", urlpsgz = "http://www.ai.mit.edu/~viola/research/publications/jsd/DeBonet-ICCV99-Poxels.ps.gz" urlpdf = "http://www.ai.mit.edu/~viola/research/publications/jsd/DeBonet-ICCV99-Poxels.pdf" urlimage = "http://www.ai.mit.edu/~viola/research/publications/jsd/DeBonet-ICCV99-Poxels.gif" abstract = " This paper examines the problem of reconstructing a voxelized representation of 3D space from a series of images. An iterative algorithm is used to find the scene model which jointly explains all the observed images by determining which region of space is responsible for each of the observations. The current approach formulates the problem as one of optimization over estimates of these responsibilities. The process converges to a distribution of responsibility which accurately reflects the constraints provided by the observations, the positions and shape of both solid and transparent objects, and the uncertainty which remains. Reconstruction is robust, and gracefully represents regions of space in which there is little certainty about the exact structure due to limited, non-existent, or contradicting data. Rendered images of voxel spaces recovered from synthetic and real observation images are shown." } @InProceedings{Rikert99, author = "Tom Rikert and Mike Jones and Paul Viola", title = "A Cluster-Based Statistical Model for Object Detection", booktitle = "Proceedings of ICCV", month = "September", year = "1999", urlpsgz = "http://www.ai.mit.edu/~viola/research/publications/ICCV99-Rikert-Jones-Viola.ps.gz" urlpdf = "http://www.ai.mit.edu/~viola/research/publications/ICCV99-Rikert-Jones-Viola.pdf" urlimage = "http://www.ai.mit.edu/~viola/research/publications/ICCV99-Rikert-Jones-Viola.gif" abstract = "This paper presents an approach to object detection which is based on recent work in statistical models for texture synthesis and recognition (Heeger95,DeBonetViola,Zhu98,SimPor98). Our method follows the texture recognition work of De Bonet and Viola (DeBonetViola97). We use feature vectors which capture the joint occurrence of local features at multiple resolutions. The distribution of feature vectors for a set of training images of an object class is estimated by clustering the data and then forming a mixture of gaussian model. The mixture model is further refined by determining which clusters are the most discriminative for the class and retaining only those clusters. After the model is learned, test images are classified by computing the likelihood of their feature vectors with respect to the model. We present promising results in applying our technique to face detection and car detection. " } @TechReport{tieu99, author = "Kinh Tieu and Paul Viola", title = "Boosting Image Retrieval", institution = "MIT AI Lab", year = 1999, number = 1669, month = "September", urlpsgz = "http://www.ai.mit.edu/~viola/research/publications/tieu/ai-memo-1669.ps.gz" urlpdf = "http://www.ai.mit.edu/~viola/research/publications/tieu/ai-memo-1669.pdf" urlpdf = "http://www.ai.mit.edu/~viola/research/publications/tieu/cvpr00.pdf" urlimage = "http://www.ai.mit.edu/~viola/research/publications/tieu/jets.jpg" abstract = "We present an approach for image database retrieval using a very large number of highly-selective features and simple on-line learning. Our approach is predicated on the assumption that each image is generated by a sparse set of visual ``causes'' and that images which are visually similar share causes. We propose a mechanism for generating a large number of complex features which capture some aspects of this causal structure. Boosting is used to learn simple and efficient classifiers in this complex feature space. Finally we will describe a practical implementation of our retrieval system on a database of 3000 images." } @MastersThesis{Matsakis99, author = "Nicholas Matsakis", title = "Recognition of Handwritten Mathematical Expressions", school = "Massachusetts Institute of Technology", year = 1999, address = "Cambridge, MA", month = "May", urlpsgz = "http://www.ai.mit.edu/~viola/research/publications/matsakis-MS-99.ps.gz", urlpdf = "http://www.ai.mit.edu/~viola/research/publications/matsakis-MS-99.pdf", urlimage = "http://www.ai.mit.edu/~viola/research/publications/matsakis-MS-99.gif", url = "http://www.ai.mit.edu/projects/lv/projects/notebook", abstract = " In recent years, the recognition of handwritten mathematical expressions has recieved an increasing amount of attention in pattern recognition research. The diversity of approaches to the problem and the lack of a commercially viable system, however, indicate that there is still much research to be done in this area. In this thesis, I will describe an on-line approach for converting a handwritten mathematical expression into an equivalent expression in a typesetting command language such as {\TeX} or MathML, as well as a feedback-oriented user interface which can make errors more tolerable to the end user since they can be quickly corrected.

The three primary components of this system are a method for classifying isolated handwritten symbols, an algorithm for partitioning an expression into symbols, and an algorithm for converting a two-dimensional arrangements of symbols into a typeset expression. For symbol classification, a Gaussian classifier is used to rank order the interpretations of a set of strokes as a single symbol. To partition an expression, the values generated by the symbol classifier are used to perform a constrained search of possible partitions for the one with the minimum summed cost. Finally, the expression is parsed using a simple geometric grammar. " } @MastersThesis{JNorrisMEng, author = "Jeffrey S. Norris", title = "Face Detection and Recognition in Office Environments", school = "Massachusetts Institute of Technology", year = 1999, address = "Cambridge, MA", month = "May", urlpsgz = "http://www.ai.mit.edu/~viola/research/publications/MEng-jnorris.ps.gz", urlpdf = "http://www.ai.mit.edu/~viola/research/publications/MEng-jnorris.pdf", urlimage = "http://www.ai.mit.edu/~viola/research/publications/MEng-jnorris.jpg", abstract = " The Gatekeeper is a vision-based door security system developed at the MIT Artificial Intelligence Laboratory. Faces are detected in a real-time video stream using an efficient algorithmic approach, and are recognized using principal component analysis with class specific linear projection. The system sends commands to an automatic sliding door, speech synthesizer, and touchscreen through a multi-client door control server. The software for the Gatekeeper was written using a set of tools created by the author to facilitate the development of real-time machine vision applications in Matlab, C, and Java. " } @Unpublished{DeBonet99b, author = "J. S. {De Bonet}", title = "Data Compression Techniques for Branch Prediction", year = 1999, urlpsgz = "http://www.ai.mit.edu/~jsd/research/publications/1999/DeBonet-BranchPrediction.ps.gz" urlpdf = "http://www.ai.mit.edu/~jsd/research/publications/1999/DeBonet-BranchPrediction.pdf" urlimage = "http://www.ai.mit.edu/~jsd/research/publications/1999/DeBonet-BranchPrediction.gif" abstract = "Without special handling branch instructions would disrupt the smooth flow of instructions into the microprocessor pipeline. To eliminate this disruption, many modern systems attempt to predict the outcome of branch instructions, and use this prediction to fetch, decode and even evaluate future instructions. Recently, researchers have realized that the task of branch prediction for processor optimization is similar to the task of symbol prediction for data compression. Substantial progress has been made in developing approximations to asymptotically optimal compression methods, while respecting the limited resources available within the instruction prefetching phase of the processor pipeline. Not only does the infusion of data compression ideas result in a theoretical fortification of branch prediction, it results in real and significant empirical improvement in performance, as well. We present an overview of branch prediction, beginning with early techniques through more recent data compression inspired schemes. A new approach is described which uses a non-parametric probability density estimator similar to the LZ77 compression scheme \cite{Ziv77}. Results are presented comparing the branch prediction accuracy of several schemes with those achieved by our new approach." } @InProceedings{IsbVio98, author = "{Charles Lee} Isbell and Paul Viola", title = "Restructuring Sparse High Dimensional Data for Effective Retrieval", year = 1998, volume = 11, booktitle = nips, urlpsgz="http://www.ai.mit.edu/~viola/research/publications/isbell-NIPS99.ps.gz", urlpdf="http://www.ai.mit.edu/~viola/research/publications/isbell-NIPS99.pdf", abstract = "The task in text retrieval is to find the subset of a collection of documents relevant to a user's information request, usually expressed as a set of words. Classically, documents and queries are represented as vectors of word counts. In its simplest form, relevance is defined to be the dot product between a document and a query vector--a measure of the number of common terms. A central difficulty in text retrieval is that the presence or absence of a word is not sufficient to determine relevance to a query. Linear dimensionality reduction has been proposed as a technique for extracting underlying structure from the document collection. In some domains (such as vision) dimensionality reduction reduces computational complexity. In text retrieval it is more often used to improve retrieval performance. We propose an alternative and novel technique that produces {\em sparse} representations constructed from sets of highly-related words. Documents and queries are represented by their distance to these sets. and relevance is measured by the number of common clusters. This technique significantly improves retrieval performance, is efficient to compute and shares properties with the optimal linear projection operator and the {\em independent components} of documents." } @TechReport{Husbell98, author = "Parry Husbands and {Charles Lee} Isbell and Alan Edelman", title = "Interactive Supercomputing with MITMatlab", institution = "MIT AI Laboratory", year = 1998, type = "Memo", number = 1642, urlpsgz="ftp://ftp.ai.mit.edu/people/isbell/papers/ppserver.ps.gz", abstract = "This paper describes MITMatlab, a system that enables users of supercomputers or networked PCs to work on large data sets within Matlab transparently. MITMatlab is based on the Parallel Problems Server (PPServer), a standalone ``linear algebra server'' that provides a mechanism for running distributed memory algorithms on large data sets. The PPServer and MITMatlab enable high-performance interactive supercomputing. With such a tool, researchers can now use Matlab as more than a prototyping tool for experimenting with small problems. Instead, MITMatlab makes is possible to visualize and operate interactively on large data sets. This has implications not only in supercomputing, but for Artificial Intelligence applications such as Machine Learning, Information Retrieval and Image Processing." } @InProceedings{MillerViola98, author = "Erik G. Miller and Paul A. Viola", title = "Ambiguity and Constraint in Mathematical Expression Recognition", year = 1998, booktitle = "Proceedings of the National Conference of Artificial Intelligence", organization = "American Association of Artificial Intelligence", urlpsgz = "http://www.ai.mit.edu/people/emiller/papers/AAAI-98.ps.gz", urlpdf = "http://www.ai.mit.edu/people/emiller/papers/AAAI-98.pdf", urlimage = "http://www.ai.mit.edu/people/emiller/images/math_demo.jpg", url = "http://www.ai.mit.edu/people/emiller/OQE_slides/index.htm", abstract = "The problem of recognizing mathematical expressions differs significantly from the recognition of standard prose. While in prose significant constraints can be put on the interpretation of a character by the characters immediately preceding and following it, few such simple constraints are present in a mathematical expression. In order to make the problem tractable, effective methods of recognizing mathematical expressions will need to put intelligent constraints on the possible interpretations. The authors present preliminary results on a system for the recognition of both handwritten and typeset mathematical expressions. While previous systems perform character recognition out of context, the current system maintains ambiguity of the characters until context can be used to disambiguate the interpretation. In addition, the system limits the number of potentially valid interpretations by decomposing the expressions into a sequence of compatible convex regions. To appear in Proceedings AAAI-98." } @InProceedings{DeBonet98a, author = "J. S. {De Bonet} and P. Viola", title = "Texture Recognition Using a Non-parametric Multi-Scale Statistical Model", booktitle = "Proceedings IEEE Conf. on Computer Vision and Pattern Recognition", year = 1998, urlpsgz = "http://www.ai.mit.edu/~jsd/research/publications/1998/DeBonet-CVPR98.ps.gz", urlpdf = "http://www.ai.mit.edu/~jsd/research/publications/1998/DeBonet-CVPR98.pdf", urlimage = "http://www.ai.mit.edu/~jsd/research/publications/1998/DeBonet-CVPR98.jpg", abstract = "We describe a technique for using the joint occurrence of local features at multiple resolutions to measure the similarity between texture images. Though superficially similar to a number of ``Gabor'' style techniques, which recognize textures through the extraction of multi-scale feature vectors, our approach is derived from an accurate generative model of texture, which is explicitly multi-scale and non-parametric. The resulting recognition procedure is similarly non-parametric, and can model complex non-homogeneous textures. We report results on publicly available texture databases. In addition, experiments indicate that this approach may have sufficient discrimination power to perform target detection in synthetic aperture radar images (SAR)." } @InProceedings{DeBonet98b, author = "J. S. {De Bonet} and P. Viola and J. W. {Fisher III}", title = "Flexible Histograms: A Multiresolution Target Discrimination Model", volume = "3370", number = "12", booktitle = "Proceedings of SPIE", year = "1998", editor = "E. G. Zelnio", urlpsgz = "http://www.ai.mit.edu/~jsd/research/publications/1998/DeBonet-SPIE98-FlexibleHistograms.ps.gz", urlpdf = "http://www.ai.mit.edu/~jsd/research/publications/1998/DeBonet-SPIE98-FlexibleHistograms.pdf", urlimage = "http://www.ai.mit.edu/~jsd/research/publications/1998/DeBonet-SPIE98-FlexibleHistograms.jpg", abstract = "In previous work we have developed a methodology for texture recognition and synthesis that estimates and exploits the dependencies across scale that occur within images \{cite DeBonet97a DeBonet98a\}. In this paper we discuss the application of this technique to synthetic aperture radar (SAR) vehicle classification. Our approach measures characteristic cross-scale dependencies in training imagery; targets are recognized when these characteristic dependencies are detected. We present classification results over a large public database containing SAR images of vehicles. Classification performance is compared to the Wright Patterson baseline classifier \{cite Velten98\}. These preliminary experiments indicate that this approach has sufficient discrimination power to perform target detection/classification in SAR." } @InProceedings{DeBonet98c, author = "J. S. {De Bonet} and A. Chao", title = "Structure-driven SAR image registration", volume = "3371", number = "65", booktitle = "Proceedings of SPIE", year = "1998", editor = "F. A. Sadjadi", urlpsgz = "http://www.ai.mit.edu/~jsd/research/publications/1998/DeBonet-SPIE98-Registration.ps.gz", urlpdf = "http://www.ai.mit.edu/~jsd/research/publications/1998/DeBonet-SPIE98-Registration.pdf", urlimage = "http://www.ai.mit.edu/~jsd/research/publications/1998/DeBonet-SPIE98-Registration.jpg", abstract = "We present a fully automatic method for the alignment SAR images, which is capable of precise and robust alignment. A multiresolution SAR image matching metric is first used to automatically determine tie-points, which are then used to perform coarse-to-fine resolution image alignment. A formalism is developed for the automatic determination of tie-point regions that contain sufficiently distinctive structure to provide strong constraints on alignment. The coarse-to-fine procedure for the refinement of the alignment estimate both improves computational efficiency and yields robust and consistent image alignment." } @MastersThesis{DeBonetMS, author = "J. S. {De Bonet}", title = "Novel Statistical Multiresolution Techniques for Image Synthesis, Discrimination, and Recognition", school = "Massachusetts Institute of Technology", year = 1997, address = "Cambridge, MA", month = "May", urlpdf = "http://www.ai.mit.edu/~jsd/Research/Publications/1997/DeBonet-MastersThesis.pdf", urlimage = "http://www.ai.mit.edu/~jsd/Research/Publications/1997/DeBonet-MastersThesis.jpg", url = "http://www.ai.mit.edu/~jsd", abstract = "By treating images as samples from probabilistic distributions, the fundamental problems in vision -- image similarity and object recognition -- can be posed as statistical questions. Within this framework, the crux of visual understanding is to accurately characterize the underlying distribution from which each image was generated. Developing good approximations to such distributions is a difficult, and in the general case, unsolved problem. A series of novel techniques is discussed for modeling images by attempting to approximate such distributions directly. These techniques provide the foundations for texture synthesis, texture discrimination, and general image classification systems. " } @MastersThesis{EMillerMS, author = "E. G. Miller", title = "An Analysis of Surface Area Estimates of Binary Volumes Under Three Tilings", school = "Massachusetts Institute of Technology", year = 1997, address = "Cambridge, MA", month = "May", url = "http://www.ai.mit.edu/people/emiller/masters/main.html", urlpsgz = "http://www.ai.mit.edu/people/emiller/masters/Erik_Millers_masters_thesis.ps.gz", urlpdf = "http://www.ai.mit.edu/people/emiller/masters/masters_thesis.pdf", urlimage = "http://www.ai.mit.edu/people/emiller/images/three_spheres.jpg", abstract = "In this paper, we first review local counting methods for perimeter estimation of piecewise smooth binary figures on square and hexagonal grids. We verify that better perimeter estimates can be obtained on a hexagonal grid. We then compare surface area estimates using local counting techniques for binary three-dimensional volumes under three distinct tilings: the cubic, truncated octahedral, and rhombic dodecahedral tilings. It is shown that under certain assumptions of piecewise smoothness, the mean error of surface area estimates is smaller for the truncated octahedral and rhombic dodecahedral tilings than for the standard cubic or rectangular prism tilings of space. Additional properties of these tessellations are reviewed and potential applications of better surface area estimates are discussed." } @InProceedings{DeBonet97a, author = "J. S. {De Bonet}", title = "Multiresolution Sampling Procedure for Analysis and Synthesis of Texture Images", organization = "ACM SIGGRAPH", booktitle = "Computer Graphics", year = 1997, pages = "361-368", url = "http://www.ai.mit.edu/~jsd/Research/TextureSynthesis", urlpsgz = "http://www.ai.mit.edu/~jsd/research/publications/1997/DeBonet-SIGGRAPH97-TextureSynthesis.ps.gz", urlpdf = "http://www.ai.mit.edu/~jsd/research/publications/1997/DeBonet-SIGGRAPH97-TextureSynthesis.pdf", urlimage = "http://www.ai.mit.edu/~jsd/Research/TextureSynthesis/1500/\{RANDOM 0 800\}_synth1500.jpg", abstract = " This paper outlines a technique for treating input texture images as probability density estimators from which new textures, with similar appearance and structural properties, can be sampled. In a two-phase process, the input texture is first analyzed by measuring the joint occurrence of texture discrimination features at multiple resolutions. In the second phase, a new texture is synthesized by sampling successive spatial frequency bands from the input texture, conditioned on the similar joint occurrence of features at lower spatial frequencies. Textures synthesized with this method more successfully capture the characteristics of input textures than do previous techniques. " } @InProceedings{Freeman97, author = "William T. Freeman and Paul A. Viola", title = "Bayesian approach to surface perception", editor = "Michael Jordan, Michael Mozer and Michael Perrone", volume = 10, booktitle = nips, year = 1997 } @InProceedings{DeBonet97b, author = "J. S. {De Bonet} and P. Viola", title = "A Non-parametric Multi-Scale Statistical Model for Natural Images", booktitle = nips, editor = "Michael Jordan, Michael Mozer and Michael Perrone", volume = 10, year = 1997, urlpsgz = "http://www.ai.mit.edu/~jsd/research/publications/1997/DeBonet-NIPS97-NonParametricImageModel.ps.gz", urlpdf = "http://www.ai.mit.edu/~jsd/research/publications/1997/DeBonet-NIPS97-NonParametricImageModel.pdf", urlimage = "http://www.ai.mit.edu/~jsd/research/publications/1997/DeBonet-NIPS97-NonParametricImageModel.jpg", url = "http://www.ai.mit.edu/~jsd/research/synthesis/FRAME_Compare", abstract = " The observed distribution of visual images is far from uniform. On the contrary, images have complex and important structure that can be used for image processing, recognition and analysis. There have been many proposed approaches to the principled statistical modeling of images, but each has been limited in either the complexity of the models or the complexity of the images. We present a non-parametric multi-scale statistical model for images that can be used for recognition, image de-noising, and in a ``generative mode'' to synthesize high quality textures." } @InProceedings{DeBonet97c, author = "J. S. {De Bonet} and P. Viola", title = "Structure Driven Image Database Retrieval", booktitle = nips, volume = 10, year = 1997, urlpsgz = "http://www.ai.mit.edu/~jsd/research/publications/1997/DeBonet-NIPS97-ImageDatabase.ps.gz", urlpdf = "http://www.ai.mit.edu/~jsd/research/publications/1997/DeBonet-NIPS97-ImageDatabase.pdf", urlimage = "http://www.ai.mit.edu/~jsd/research/publications/1997/DeBonet-NIPS97-ImageDatabase.jpg", url = "http://www.ai.mit.edu/~jsd/Research/ImageDatabase/Abstract", abstract = " A new algorithm is presented which approximates the perceived visual similarity between images. The images are initially transformed into a feature space which captures visual structure, texture and color using a tree of filters. Similarity is the inverse of the distance in this {\em perceptual feature space}. Using this algorithm we have constructed an image database system which can perform example based retrieval on large image databases. Using carefully constructed target sets, which limit variation to only a single visual characteristic, retrieval rates are quantitatively compared to those of standard methods." } @Article{ViolaWells97, author = "Paul Viola and William M. {Wells III}", title = "Alignment by Maximization of Mutual Information", journal = ijcv, year = 1997, urlpsgz = "http://www.ai.mit.edu/people/viola/research/publications/IJCV-97.ps.gz", urlpdf = "http://www.ai.mit.edu/people/viola/research/publications/IJCV-97.pdf", urlimage = "http://www.ai.mit.edu/people/viola/research/publications/IJCV-97.jpg", abstract = "A new information-theoretic approach is presented for finding the pose of an object in an image. The technique does not require information about the surface properties of the object, besides its shape, and is robust with respect to variations of illumination. In our derivation few assumptions are made about the nature of the imaging process. As a result the algorithms are quite general and may foreseeably be used in a wide variety of imaging situations.

Experiments are presented that demonstrate the approach registering magnetic resonance (MR) images, aligning a complex 3D object model to real scenes including clutter and occlusion, tracking a human head in a video sequence and aligning a view-based 2D object model to real images.

The method is based on a formulation of the mutual information between the model and the image. As applied here the technique is intensity-based, rather than feature-based. It works well in domains where edge or gradient-magnitude based methods have difficulty, yet it is more robust than traditional correlation. Additionally, it has an efficient implementation that is based on stochastic approximation." } @TechReport{Vio96, author = "Paul Viola", title = "Complex Feature Recognition: A Bayesian Approach for Learning to Recognize Objects", institution = "MIT AI Lab", year = 1996, number = 1591, urlpsgz = "http://www.ai.mit.edu/people/viola/research/publications/AIMEMO-96.ps.gz", urlpdf = "http://www.ai.mit.edu/people/viola/research/publications/AIMEMO-96.pdf", urlimage = "http://www.ai.mit.edu/people/viola/research/publications/AIMEMO-96.gif", abstract = "We have developed a new Bayesian framework for visual object recognition which is based on the insight that images of objects can be modeled as a conjunction of local features. This framework can be used to both derive an object recognition algorithm and an algorithm for learning the features themselves. The overall approach, called complex feature recognition or CFR, is unique for several reasons: it is broadly applicable to a wide range of object types, it makes constructing object models easy, it is capable of identifying either the class or the identity of an object, and it is computationally efficient~--~requiring time proportional to the size of the image.

Instead of a single simple feature such as an edge, CFR uses a large set of complex features that are learned from experience with model objects. The response of a single complex feature contains much more class information than does a single edge. This significantly reduces the number of possible correspondences between the model and the image. In addition, CFR takes advantage of a type of image processing called {\em oriented energy}. Oriented energy is used to efficiently pre-process the image to eliminate some of the difficulties associated with changes in lighting and pose." } @InProceedings{DeBonet96, author = "J. S. {De Bonet} and C. Isbell and P. Viola", title = "MIMIC: Finding Optima by Estimating Probability Densities", editor = "Michael Jordan, Michael Mozer and Michael Perrone", booktitle = nips, volume = 9, address = "Denver 1996", publisher = "MIT Press, Cambridge", year = 1996, urlpsgz = "http://www.ai.mit.edu/~jsd/research/publications/1996/DeBonet-NIPS96-MIMIC.ps.gz", urlpdf = "http://www.ai.mit.edu/~jsd/research/publications/1996/DeBonet-NIPS96-MIMIC.pdf", abstract = "In many optimization problems the structure of solutions reflects complex relationships between the different input parameters. Any search of the cost landscape should take advantage of these relations. For example, experience may tell us that certain parameters are closely related and should not be explored independently. Similarly, experience may establish that a subset of parameters must take on particular values. We present a framework in which we analyze the structural relationships of the optimization landscape. A novel and efficient algorithm for the estimation of this structure is derived. We use knowledge of this structure to guide a randomized search through the solution space. Our technique obtains significant speed gains over other randomized optimization procedures." } @Article{WellsEtc96, author = "William M. {Wells III} and Paul Viola and Hideki Atsumi and Shin Nakajima and Ron Kikinis", title = "Multi-Modal Volume Registration by Maximization of Mutual Information", journal = "Medical Image Analysis", year = 1996, volume = 1, number = 1, url = "http://splweb.bwh.harvard.edu:8000/pages/papers/swells/mia-html/mia.html", urlpsgz = "http://www.ai.mit.edu/people/viola/research/publications/MIA-95.ps.gz", urlpsgz = "http://www.ai.mit.edu/people/viola/research/publications/MIA-95.pdf", urlimage = "http://www.ai.mit.edu/people/viola/research/publications/MIA-95-MR-PET.gif", abstract = "A new information-theoretic approach is presented for finding the registration of volumetric medical images of differing modalities. Registration is achieved by adjustment of the relative position and orientation until the mutual information between the images is maximized. In our derivation of the registration procedure, few assumptions are made about the nature of the imaging process. As a result the algorithms are quite general and can foreseeably be used with a wide variety of imaging devices.

This approach works directly with image data; no pre-processing or segmentation is required. This technique is however more flexible and robust than other intensity based techniques like correlation. Additionally, it has an efficient implementation that is based on stochastic approximation.

Experiments are presented that demonstrate the approach registering magnetic resonance (MR) images with computed tomography (CT) images, and with positron-emission tomography (PET) images.

A surgical application of the registration method is described." } @Article{Cohen95, author = "Douglas S. Cohen and Jonathan H. Lustgarten and Erik G. Miller and Alexander Khandji and Robert R. Goodman", title = "Effects of Coregistration of MR to CT Images on MR Stereotactic Accuracy.", journal = "Journal of Neurosurgery", year = 1995, volume = 82, number = 5, abstract = "Coregistration of different modality imaging serves to increase the ease and accuracy of stereotactic procedures. In many cases, magnetic resonance (MR) stereotaxis is supplanting computerized tomography (CT). The advantages of increased anatomical detail and multiplanar imaging afforded by MR, however, are offset by its potential inaccuracy as well as the more cumbersome and less available nature of its hardware. A system has been developed by one of the authors by which MR imaging can be performed separately without a stereotactic fiducial headring. Then, immediately prior to surgery, a stereotactic CT scan is obtained and software is used to coregister CT and MR images anatomically by matching cranial landmarks in the two scans.

The authors examined this system in six patients as well as with the use of a lucite phantom. After initially coregistering CT and MR images, six separate anatomical (for the patients) and eight artificial (for the phantom) targets were compared. With coregistration, in comparison to CT fiducial scans, errors in each axis are less than or equal to 1 mm using the Cosman-Roberts-Wells system. In fact, the coregistered images are more accurate than MR fiducial images, in the anteroposterior (p=0.001), lateral (p<0.05), and vertical (p<0.03) planes. Three-dimensional error was significantly less in the coregistered scans than the MR fiducial images (p<0.005). The coregistration procedure therefore not only increases the ease of MR stereotaxis but also increases its accuracy." } @inproceedings{VioSchSej95, author = "Paul A. Viola and Nicol N. Schraudolph and Terrence J. Sejnowski", title = "Empirical Entropy Manipulation for Real-World Problems", editor = "David S. Touretzky, Michael Mozer and Michael Perrone", booktitle = nips, volume = 8, address = "Denver 1995", publisher = "MIT Press, Cambridge", year = 1995, urlpsgz = "http://www.ai.mit.edu/people/viola/research/publications/NIPS-95.ps.gz", urlimage = "http://www.ai.mit.edu/people/viola/research/publications/NIPS-95.jpg", abstract = "No finite sample is sufficient to determine the density, and therefore the entropy, of a signal directly. Some assumption about either the functional form of the density or about its smoothness is necessary. Both amount to a prior over the space of possible density functions. By far the most common approach is to assume that the density has a parametric form.

By contrast we derive a differential learning rule called EMMA that optimizes entropy by way of kernel density estimation. Entropy and its derivative can then be calculated by sampling from this density estimate. The resulting parameter update rule is surprisingly simple and efficient.

We will describe two real-world applications that can be solved efficiently and reliably using EMMA. In the first application EMMA is used to align 3D models to complex natural images. In the second application EMMA is used to detect and correct corruption in magnetic resonance images (MRI). Both applications are beyond the scope of existing parametric entropy models." } @PhdThesis{ViolaPhD, author = "Paul A. Viola", title = "Alignment by Maximization of Mutual Information.", school = "Massachusetts Institute of Technology", year = "1995", booktitle = "MIT AI Laboratory TR 1548 (Ph.D Thesis)", urlpsgz = "http://www.ai.mit.edu/people/viola/research/publications/PHD-thesis.ps.gz", urlpdf = "http://www.ai.mit.edu/people/viola/research/publications/PHD-thesis.pdf", urlimage = "http://www.ai.mit.edu/people/viola/research/publications/PHD-thesis.jpg", abstract = "Over the last 30 years the problems of image registration and recognition have proven more difficult than even the most pessimistic might have predicted. Progress has been hampered by the sheer complexity of the relationship between an object and its image, which involves the object's shape, surface properties, position, and illumination.

Changes in illumination can radically alter the intensity and shading of an image. Nevertheless, the human visual system can use shading both for recognition and image interpretation. We will present a measure for comparing objects and images that uses shading information, yet is explicitly insensitive to changes in illumination. This measure is unique in that it compares 3D object models directly to raw images. No pre-processing or edge detection is required. We will show that when the {\em mutual information} between model and image is large they are likely to be aligned. Toward making this technique a reality we have defined a concrete and efficient technique for evaluating entropy called EMMA.

In our derivation of mutual information based alignment few assumptions are made about the nature of the imaging process. As a result the algorithms are quite general and can be used in a wide variety of imaging situations. Experiments demonstrate this approach aligning a number of complex 3D object models to real images. In addition, we demonstrate that the same technique can be used to solve problems in medical registration.

Alignment is accomplished by adjusting the pose of an object until the mutual information between image and object is maximized. We will present a gradient descent alignment procedure based on stochastic approximation that has a very efficient implementation. For this application stochastic approximation affords a speed up of at least a factor of 500 over gradient descent. In addition, stochastic approximation can be used to accelerate a variety of other vision applications. We will describe an existing vision application which can be accelerated by a factor of 30 using stochastic approximation.

Finally, we will describe a number of additional real-world applications that can be solved efficiently and reliably using EMMA. EMMA can be used in machine learning to find maximally informative projections of high-dimensional data. EMMA can also be used to detect and correct corruption in magnetic resonance images (MRI)." } @InProceedings{Stewart96, author = "Marion Stewart and Paul Viola and Terrence Sejnowski and Beatrice Golomb and Jan Larsen and J Hager and P Ekman", title = "Classifying facial action", booktitle = nips, volume = 8, address = "Denver 1995", publisher = "MIT Press, Cambridge", year = 1995 urlpsgz = "http://www.ai.mit.edu/people/viola/research/publications/NIPS-95.ps.gz", } @Unpublished{DeBonet95, author = "J. S. {De Bonet}", title = "Reconstructing Rectangular Polyhedra From Hand-Drawn Wireframe Sketches", year = 1995, urlpsgz = "http://www.ai.mit.edu/~jsd/research/publications/1995/DeBonet-SketchReconstruction.ps.gz", urlpdf = "http://www.ai.mit.edu/~jsd/research/publications/1995/DeBonet-SketchReconstruction.pdf", urlimage = "http://www.ai.mit.edu/~jsd/research/publications/1995/DeBonet-SketchReconstruction.jpg", url = "http://www.ai.mit.edu/~jsd/Projects/SketchReconstruction/sketch.html", abstract = "Human observers are capable of interpreting hand drawn sketches as three- dimensional objects, despite inconsistencies in lengths, variability in angles, and uncon- nected vertices. The current system is an attempt to achieve such robust performance in the limited domain of sketches of wireframe rectangular polyhedra. The Latest version of this system reconstructs three-dimensional objects from perfect drawings, in which all angles and line junctions are consistent with projections of rectangular poly- hedron. Ambiguities which are inherent in such drawings are avoided by choosing a line grammar which yields only a single interpretation. Next, reconstruction from im- perfect drawings, in which all the line segments were randomly perturbed, was then achieved by grouping line endpoints into vertices while simultaneously restricting lines to particular orientations, and recovering three-dimensional form from the corrected line drawing. Finally, when actual hand-drawn sketches were used as input, we found that to successfully perform reconstruction the constraints on line orientations had to be replaced with constraints segment lengths and an additional three-dimensional point clustering process was needed." } %% Journals %% Refereed conference proceedings @Article{Malison93, author = "Robert Malison and Erik Miller and Robin Greene and Greg McCarthy and Dennis Charney and Robert Innis", title = "Computer Assisted Coregistration of Multislice SPECT and MR Brain Images by Fixed External Fiducials.", journal = "Journal of Computer Assisted Tomography", year = 1993, volume = 17, number = 6, abstract = "We have developed and validated in a phantom a method of computer-assisted coregistration using multislice SPECT and MR images. Reusable fiducial markers were fabricated from nylon-based plastic and consist of two parts: a base that remains fixed to the skin with adhesive between scans and a removable, spherical cavity insert that can be filled with contrast agents appropriate for multiple imaging modalities. Markers external and internal to a three-dimensional brain phantom provided a means of quantifying the method's accuracy." } @InProceedings{BroVio90, author = "Rodney A. Brooks and Paul Viola", title = "Network Based Autonomous Robot Motor Control: from Hormones to Learning", year = 1990, booktitle = "Conference on Neural Networks for Motor Control", address = "Dusseldorf, Germany", month = "March" } @InProceedings{ConVio90, author = "Jonathan H. Connel and Paul Viola", title = "Cooperative Control of a Semi-Autonomous Mobile Robot", booktitle = robau, year = 1990 } @InProceedings{VioLisSej91, author = "Paul Viola and Stephen G. Lisberger and Terrence J. Sejnowski", title = "Recurrent Eye Tracking Network Using a Distributed Representation of Image Motion", editor = "John E. Moody and Steven J. Hanson and Richard P. Lippmann", booktitle = nips, volume = 4, address = "Denver 1991", publisher = "Morgan Kaufmann, San Mateo", year = 1992 } @inproceedings{VioWel95, author = "Paul A. Viola and William M. {Wells III}", title = "Alignment by Maximization of Mutual Information", pages = "16--23", booktitle = "Fifth Intl.\ Conf.\ on Computer Vision", address = "Cambridge, MA", publisher = "IEEE", year = 1995 } @InProceedings{Viola89, author = "Paul Viola", title = "Neurally Inspired Plasticity in Oculomotor Processes", editor = "David S. Touretzky", booktitle = nips, volume = 2, address = "Denver 1989", publisher = "Morgan Kaufmann, San Mateo", year = 1990 } %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% @proceedings{NN:nips2, editor = "David S. Touretzky", title = nips, booktitle = nips, volume = 2, address = "Denver 1989", publisher = "Morgan Kaufmann, San Mateo", year = 1990 } @proceedings{NN:nips3, editor = "Richard P. Lippmann and John E. Moody and David S. Touretzky", title = nips, booktitle = nips, volume = 3, address = "Denver 1990", publisher = "Morgan Kaufmann, San Mateo", year = 1991 } @proceedings{NN:nips4, editor = "John E. Moody and Steven J. Hanson and Richard P. Lippmann", title = nips, booktitle = nips, volume = 4, address = "Denver 1991", publisher = "Morgan Kaufmann, San Mateo", year = 1992 } @proceedings{NN:nips5, editor = "Steven J. Hanson and Jack D. Cowan and C. Lee Giles", title = nips, booktitle = nips, volume = 5, address = "Denver 1992", publisher = "Morgan Kaufmann, San Mateo", year = "1993" } @proceedings{NN:nips6, editor = "Jack D. Cowan and Gerald Tesauro and Joshua Alspector", title = nips, booktitle = nips, volume = 6, address = "Denver 1993", publisher = "Morgan Kaufmann, San Francisco", year = "1994" } @proceedings{NN:nips7, editor = "Gerald Tesauro and David S. Touretzky and Todd K. Leen", title = nips, booktitle = nips, volume = 7, address = "Denver 1994", publisher = "MIT Press, Cambridge", year = 1995 } @proceedings{NN:nips8, editor = "David S. Touretzky, Michael Mozer and Michael Perrone", title = nips, booktitle = nips, volume = 8, address = "Denver 1995", publisher = "MIT Press, Cambridge", year = 1995 } @proceedings{NN:nips9, editor = "Michael Jordan, Michael Mozer and Michael Perrone", title = nips, booktitle = nips, volume = 9, address = "Denver 1996", publisher = "MIT Press, Cambridge", year = 1996 }