@article {19717, title = {Whole genome analysis of Leptospira licerasiae provides insight into leptospiral evolution and pathogenicity.}, journal = {PLoS Negl Trop Dis}, volume = {6}, year = {2012}, month = {2012}, pages = {e1853}, abstract = {

The whole genome analysis of two strains of the first intermediately pathogenic leptospiral species to be sequenced (Leptospira licerasiae strains VAR010 and MMD0835) provides insight into their pathogenic potential and deepens our understanding of leptospiral evolution. Comparative analysis of eight leptospiral genomes shows the existence of a core leptospiral genome comprising 1547 genes and 452 conserved genes restricted to infectious species (including L. licerasiae) that are likely to be pathogenicity-related. Comparisons of the functional content of the genomes suggests that L. licerasiae retains several proteins related to nitrogen, amino acid and carbohydrate metabolism which might help to explain why these Leptospira grow well in artificial media compared with pathogenic species. L. licerasiae strains VAR010(T) and MMD0835 possess two prophage elements. While one element is circular and shares homology with LE1 of L. biflexa, the second is cryptic and homologous to a previously identified but unnamed region in L. interrogans serovars Copenhageni and Lai. We also report a unique O-antigen locus in L. licerasiae comprised of a 6-gene cluster that is unexpectedly short compared with L. interrogans in which analogous regions may include >90 such genes. Sequence homology searches suggest that these genes were acquired by lateral gene transfer (LGT). Furthermore, seven putative genomic islands ranging in size from 5 to 36 kb are present also suggestive of antecedent LGT. How Leptospira become naturally competent remains to be determined, but considering the phylogenetic origins of the genes comprising the O-antigen cluster and other putative laterally transferred genes, L. licerasiae must be able to exchange genetic material with non-invasive environmental bacteria. The data presented here demonstrate that L. licerasiae is genetically more closely related to pathogenic than to saprophytic Leptospira and provide insight into the genomic bases for its infectiousness and its unique antigenic characteristics.

}, keywords = {DNA, Bacterial, Evolution, Molecular, Gene Transfer, Horizontal, Genome, Bacterial, Genomic islands, HUMANS, Leptospira, Molecular Sequence Data, Multigene Family, Prophages, Sequence Analysis, DNA, Virulence factors}, issn = {1935-2735}, doi = {10.1371/journal.pntd.0001853}, author = {Ricaldi, Jessica N and Fouts, Derrick E and Jeremy D Selengut and Harkins, Derek M and Patra, Kailash P and Moreno, Angelo and Lehmann, Jason S and Purushe, Janaki and Sanka, Ravi and Torres, Michael and Webster, Nicholas J and Vinetz, Joseph M and Matthias, Michael A} } @conference {14192, title = {Active scene recognition with vision and language}, booktitle = {2011 IEEE International Conference on Computer Vision (ICCV)}, year = {2011}, month = {2011/11/06/13}, pages = {810 - 817}, publisher = {IEEE}, organization = {IEEE}, abstract = {This paper presents a novel approach to utilizing high level knowledge for the problem of scene recognition in an active vision framework, which we call active scene recognition. In traditional approaches, high level knowledge is used in the post-processing to combine the outputs of the object detectors to achieve better classification performance. In contrast, the proposed approach employs high level knowledge actively by implementing an interaction between a reasoning module and a sensory module (Figure 1). Following this paradigm, we implemented an active scene recognizer and evaluated it with a dataset of 20 scenes and 100+ objects. We also extended it to the analysis of dynamic scenes for activity recognition with attributes. Experiments demonstrate the effectiveness of the active paradigm in introducing attention and additional constraints into the sensing process.}, keywords = {accuracy, active scene recognition, classification performance, Cognition, Computer vision, Detectors, Equations, high level knowledge utilization, HUMANS, image classification, inference mechanisms, object detectors, Object recognition, reasoning module, sensing process, sensory module, support vector machines, Training}, isbn = {978-1-4577-1101-5}, doi = {10.1109/ICCV.2011.6126320}, author = {Yu,Xiaodong and Ferm{\"u}ller, Cornelia and Ching Lik Teo and Yezhou Yang and Aloimonos, J.} } @conference {12453, title = {Recent advances in age and height estimation from still images and video}, booktitle = {2011 IEEE International Conference on Automatic Face \& Gesture Recognition and Workshops (FG 2011)}, year = {2011}, month = {2011/03/21/25}, pages = {91 - 96}, publisher = {IEEE}, organization = {IEEE}, abstract = {Soft-biometrics such as gender, age, race, etc have been found to be useful characterizations that enable fast pre-filtering and organization of data for biometric applications. In this paper, we focus on two useful soft-biometrics - age and height. We discuss their utility and the factors involved in their estimation from images and videos. In this context, we highlight the role that geometric constraints such as multiview-geometry, and shape-space geometry play. Then, we present methods based on these geometric constraints for age and height-estimation. These methods provide a principled means by fusing image-formation models, multi-view geometric constraints, and robust statistical methods for inference.}, keywords = {age estimation, biometrics (access control), Calibration, Estimation, Geometry, height estimation, HUMANS, image fusion, image-formation model fusion, Legged locomotion, multiview-geometry, Robustness, SHAPE, shape-space geometry, soft-biometrics, statistical analysis, statistical methods, video signal processing}, isbn = {978-1-4244-9140-7}, doi = {10.1109/FG.2011.5771367}, author = {Chellapa, Rama and Turaga,P.} } @conference {12413, title = {Simulating Audiences: Automating Analysis of Values, Attitudes, and Sentiment}, booktitle = {Privacy, Security, Risk and Trust (PASSAT), 2011 IEEE Third International Conference on and 2011 IEEE Third International Confernece on Social Computing (SocialCom)}, year = {2011}, month = {2011/10/09/11}, pages = {734 - 737}, publisher = {IEEE}, organization = {IEEE}, abstract = {Current events such as the Park51 Project in downtown Manhattan create "critical discourse moments," explosions of discourse around a topic that can be exploited for data gathering. Policymakers have a need to understand the dynamics of public discussion in real time. Human values, which are cognitively related to attitudes and serve as reference points in moral argument, are important indicators of what{\textquoteright}s at stake in a public controversy. This work shows that it is possible to link values data with reader behavior to infer values implicit in a topical corpus, and that it is possible to automate this process using machine learning.}, keywords = {audience simulation, behavioural sciences computing, crowdsourcing, Educational institutions, human values, HUMANS, learning (artificial intelligence), machine learning, moral argument, natural language processing, Park51 project, Presses, public controversy, public discussion, Security, social sciences computing, support vector machines, Weaving}, isbn = {978-1-4577-1931-8}, doi = {10.1109/PASSAT/SocialCom.2011.238}, author = {Templeton,T.C. and Fleischmann,K.R. and Jordan Boyd-Graber} } @conference {12436, title = {Sparse dictionary-based representation and recognition of action attributes}, booktitle = {2011 IEEE International Conference on Computer Vision (ICCV)}, year = {2011}, month = {2011/11/06/13}, pages = {707 - 714}, publisher = {IEEE}, organization = {IEEE}, abstract = {We present an approach for dictionary learning of action attributes via information maximization. We unify the class distribution and appearance information into an objective function for learning a sparse dictionary of action attributes. The objective function maximizes the mutual information between what has been learned and what remains to be learned in terms of appearance information and class distribution for each dictionary item. We propose a Gaussian Process (GP) model for sparse representation to optimize the dictionary objective function. The sparse coding property allows a kernel with a compact support in GP to realize a very efficient dictionary learning process. Hence we can describe an action video by a set of compact and discriminative action attributes. More importantly, we can recognize modeled action categories in a sparse feature space, which can be generalized to unseen and unmodeled action categories. Experimental results demonstrate the effectiveness of our approach in action recognition applications.}, keywords = {action attributes, appearance information, class distribution, Dictionaries, dictionary learning process, Encoding, Entropy, Gaussian process model, Gaussian processes, Histograms, HUMANS, Image coding, image representation, information maximization, learning (artificial intelligence), modeled action categories, Mutual information, Object recognition, probabilistic logic, sparse coding property, sparse dictionary-based recognition, sparse dictionary-based representation, sparse feature space, unmodeled action categories}, isbn = {978-1-4577-1101-5}, doi = {10.1109/ICCV.2011.6126307}, author = {Qiang Qiu and Zhuolin Jiang and Chellapa, Rama} } @article {12439, title = {Statistical Computations on Grassmann and Stiefel Manifolds for Image and Video-Based Recognition}, journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence}, volume = {33}, year = {2011}, month = {2011/11//}, pages = {2273 - 2286}, abstract = {In this paper, we examine image and video-based recognition applications where the underlying models have a special structure-the linear subspace structure. We discuss how commonly used parametric models for videos and image sets can be described using the unified framework of Grassmann and Stiefel manifolds. We first show that the parameters of linear dynamic models are finite-dimensional linear subspaces of appropriate dimensions. Unordered image sets as samples from a finite-dimensional linear subspace naturally fall under this framework. We show that an inference over subspaces can be naturally cast as an inference problem on the Grassmann manifold. To perform recognition using subspace-based models, we need tools from the Riemannian geometry of the Grassmann manifold. This involves a study of the geometric properties of the space, appropriate definitions of Riemannian metrics, and definition of geodesics. Further, we derive statistical modeling of inter and intraclass variations that respect the geometry of the space. We apply techniques such as intrinsic and extrinsic statistics to enable maximum-likelihood classification. We also provide algorithms for unsupervised clustering derived from the geometry of the manifold. Finally, we demonstrate the improved performance of these methods in a wide variety of vision applications such as activity recognition, video-based face recognition, object recognition from image sets, and activity-based video clustering.}, keywords = {activity based video clustering, activity recognition, computational geometry, Computational modeling, Data models, face recognition, feature representation, finite dimensional linear subspaces, geometric properties, Geometry, Grassmann Manifolds, Grassmann., HUMANS, Image and video models, image recognition, linear dynamic models, linear subspace structure, Manifolds, maximum likelihood classification, maximum likelihood estimation, Object recognition, Riemannian geometry, Riemannian metrics, SHAPE, statistical computations, statistical models, Stiefel, Stiefel Manifolds, unsupervised clustering, video based face recognition, video based recognition, video signal processing}, isbn = {0162-8828}, doi = {10.1109/TPAMI.2011.52}, author = {Turaga,P. and Veeraraghavan,A. and Srivastava, A. and Chellapa, Rama} } @article {12474, title = {Applications of a Simple Characterization of Human Gait in Surveillance}, journal = {Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on}, volume = {40}, year = {2010}, month = {2010/08//}, pages = {1009 - 1020}, abstract = {Applications of a simple spatiotemporal characterization of human gait in the surveillance domain are presented. The approach is based on decomposing a video sequence into x-t slices, which generate periodic patterns referred to as double helical signatures (DHSs). The features of DHS are given as follows: 1) they naturally encode the appearance and kinematics of human motion and reveal geometric symmetries and 2) they are effective and efficient for recovering gait parameters and detecting simple events. We present an iterative local curve embedding algorithm to extract the DHS from video sequences. Two applications are then considered. First, the DHS is used for simultaneous segmentation and labeling of body parts in cluttered scenes. Experimental results showed that the algorithm is robust to size, viewing angles, camera motion, and severe occlusion. Then, the DHS is used to classify load-carrying conditions. By examining various symmetries in DHS, activities such as carrying, holding, and walking with objects that are attached to legs are detected. Our approach possesses several advantages: a compact representation that can be computed in real time is used; furthermore, it does not depend on silhouettes or landmark tracking, which are sensitive to errors in background subtraction stage.}, keywords = {algorithms, Artificial intelligence, Automated;Photography;Reproducibility of Results;Sensitivity and Specificity;Video Recording;, Biometry, Computer-Assisted;Pattern Recognition, double helical signatures, Gait, gait analysis, human gait, human motion kinematics, HUMANS, Image Enhancement, Image Interpretation, Image motion analysis, iterative local curve embedding algorithm, Object detection, simple spatiotemporal characterization, video sequence, Video surveillance}, isbn = {1083-4419}, doi = {10.1109/TSMCB.2010.2044173}, author = {Yang Ran and Qinfen Zheng and Chellapa, Rama and Strat, T.M.} } @conference {14227, title = {Learning shift-invariant sparse representation of actions}, booktitle = {2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2010}, month = {2010/06/13/18}, pages = {2630 - 2637}, publisher = {IEEE}, organization = {IEEE}, abstract = {A central problem in the analysis of motion capture (MoCap) data is how to decompose motion sequences into primitives. Ideally, a description in terms of primitives should facilitate the recognition, synthesis, and characterization of actions. We propose an unsupervised learning algorithm for automatically decomposing joint movements in human motion capture (MoCap) sequences into shift-invariant basis functions. Our formulation models the time series data of joint movements in actions as a sparse linear combination of short basis functions (snippets), which are executed (or {\textquotedblleft}activated{\textquotedblright}) at different positions in time. Given a set of MoCap sequences of different actions, our algorithm finds the decomposition of MoCap sequences in terms of basis functions and their activations in time. Using the tools of L1 minimization, the procedure alternately solves two large convex minimizations: Given the basis functions, a variant of Orthogonal Matching Pursuit solves for the activations, and given the activations, the Split Bregman Algorithm solves for the basis functions. Experiments demonstrate the power of the decomposition in a number of applications, including action recognition, retrieval, MoCap data compression, and as a tool for classification in the diagnosis of Parkinson (a motion disorder disease).}, keywords = {action characterization, Action recognition, action retrieval, action synthesis, Character recognition, data compression, human motion capture, HUMANS, Image matching, Image motion analysis, image representation, Image sequences, Information retrieval, joint movements, large convex minimizations, learning (artificial intelligence), learning shift-invariant sparse representation, Matching pursuit algorithms, minimisation, Minimization methods, MoCap data compression, Motion analysis, motion capture analysis, motion disorder disease, motion sequences, orthogonal matching pursuit, Parkinson diagnosis, Parkinson{\textquoteright}s disease, Pursuit algorithms, shift-invariant basis functions, short basis functions, snippets, sparse linear combination, split Bregman algorithm, time series, time series data, Unsupervised learning, unsupervised learning algorithm}, isbn = {978-1-4244-6984-0}, doi = {10.1109/CVPR.2010.5539977}, author = {Li,Yi and Ferm{\"u}ller, Cornelia and Aloimonos, J. and Hui Ji} } @conference {12479, title = {Moving vistas: Exploiting motion for describing scenes}, booktitle = {2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2010}, month = {2010/06/13/18}, pages = {1911 - 1918}, publisher = {IEEE}, organization = {IEEE}, abstract = {Scene recognition in an unconstrained setting is an open and challenging problem with wide applications. In this paper, we study the role of scene dynamics for improved representation of scenes. We subsequently propose dynamic attributes which can be augmented with spatial attributes of a scene for semantically meaningful categorization of dynamic scenes. We further explore accurate and generalizable computational models for characterizing the dynamics of unconstrained scenes. The large intra-class variation due to unconstrained settings and the complex underlying physics present challenging problems in modeling scene dynamics. Motivated by these factors, we propose using the theory of chaotic systems to capture dynamics. Due to the lack of a suitable dataset, we compiled a dataset of {\textquoteleft}in-the-wild{\textquoteright} dynamic scenes. Experimental results show that the proposed framework leads to the best classification rate among other well-known dynamic modeling techniques. We also show how these dynamic features provide a means to describe dynamic scenes with motion-attributes, which then leads to meaningful organization of the video data.}, keywords = {Application software, Automation, Chaos, chaotic system, Computational modeling, Computer vision, dynamic scene categorization, Educational institutions, HUMANS, image recognition, in the wild dynamic scene, Layout, motion attribute, natural scenes, Physics, probability, scene recognition, Snow, video data}, isbn = {978-1-4244-6984-0}, doi = {10.1109/CVPR.2010.5539864}, author = {Shroff, N. and Turaga,P. and Chellapa, Rama} } @conference {12490, title = {The role of geometry in age estimation}, booktitle = {2010 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)}, year = {2010}, month = {2010/03/14/19}, pages = {946 - 949}, publisher = {IEEE}, organization = {IEEE}, abstract = {Understanding and modeling of aging in human faces is an important problem in many real-world applications such as biometrics, authentication, and synthesis. In this paper, we consider the role of geometric attributes of faces, as described by a set of landmark points on the face, in age perception. Towards this end, we show that the space of landmarks can be interpreted as a Grassmann manifold. Then the problem of age estimation is posed as a problem of function estimation on the manifold. The warping of an average face to a given face is quantified as a velocity vector that transforms the average to a given face along a smooth geodesic in unit-time. This deformation is then shown to contain important information about the age of the face. We show in experiments that exploiting geometric cues in a principled manner provides comparable performance to several systems that utilize both geometric and textural cues. We show results on age estimation using the standard FG-Net dataset and a passport dataset which illustrate the effectiveness of the approach.}, keywords = {age estimation, Aging, Biometrics, computational geometry, Face, Face Geometry, Facial animation, Feature extraction, function estimation problem, geometric face attributes, Geometry, Grassmann manifold, human face modeling, human face understanding, HUMANS, Mouth, regression, Regression analysis, SHAPE, Solid modeling, solid modelling, velocity vector}, isbn = {978-1-4244-4295-9}, doi = {10.1109/ICASSP.2010.5495292}, author = {Turaga,P. and Biswas,S. and Chellapa, Rama} } @article {19368, title = {Structural and dynamic determinants of ligand binding and regulation of cyclin-dependent kinase 5 by pathological activator p25 and inhibitory peptide CIP.}, journal = {Journal of molecular biology}, volume = {401}, year = {2010}, month = {2010 Aug 20}, pages = {478-92}, abstract = {The crystal structure of the cdk5/p25 complex has provided information on possible molecular mechanisms of the ligand binding, specificity, and regulation of the kinase. Comparative molecular dynamics simulations are reported here for physiological conditions. This study provides new insight on the mechanisms that modulate such processes, which may be exploited to control pathological activation by p25. The structural changes observed in the kinase are stabilized by a network of interactions involving highly conserved residues within the cyclin-dependent kinase (cdk) family. Collective motions of the proteins (cdk5, p25, and CIP) and their complexes are identified by principal component analysis, revealing two conformational states of the activation loop upon p25 complexation, which are absent in the uncomplexed kinase and not apparent from the crystal. Simulations of the uncomplexed inhibitor CIP show structural rearrangements and increased flexibility of the interfacial loop containing the critical residue E240, which becomes fully hydrated and available for interactions with one of several positively charged residues in the kinase. These changes provide a rationale for the observed high affinity and enhanced inhibitory action of CIP when compared to either p25 or the physiological activators of cdk5.}, keywords = {Crystallography, X-Ray, Cyclin-Dependent Kinase 5, Cyclin-Dependent Kinase Inhibitor Proteins, HUMANS, Ligands, molecular dynamics simulation, Nerve Tissue Proteins, Principal component analysis, Protein Binding, Protein Conformation}, issn = {1089-8638}, doi = {10.1016/j.jmb.2010.06.040}, author = {Cardone, Antonio and Hassan, S A and Albers,R.W. and Sriram,R.D. and Pant,H.C.} } @article {12513, title = {Multicamera Tracking of Articulated Human Motion Using Shape and Motion Cues}, journal = {Image Processing, IEEE Transactions on}, volume = {18}, year = {2009}, month = {2009/09//}, pages = {2114 - 2126}, abstract = {We present a completely automatic algorithm for initializing and tracking the articulated motion of humans using image sequences obtained from multiple cameras. A detailed articulated human body model composed of sixteen rigid segments that allows both translation and rotation at joints is used. Voxel data of the subject obtained from the images is segmented into the different articulated chains using Laplacian eigenmaps. The segmented chains are registered in a subset of the frames using a single-frame registration technique and subsequently used to initialize the pose in the sequence. A temporal registration method is proposed to identify the partially segmented or unregistered articulated chains in the remaining frames in the sequence. The proposed tracker uses motion cues such as pixel displacement as well as 2-D and 3-D shape cues such as silhouettes, motion residue, and skeleton curves. The tracking algorithm consists of a predictor that uses motion cues and a corrector that uses shape cues. The use of complementary cues in the tracking alleviates the twin problems of drift and convergence to local minima. The use of multiple cameras also allows us to deal with the problems due to self-occlusion and kinematic singularity. We present tracking results on sequences with different kinds of motion to illustrate the effectiveness of our approach. The pose of the subject is correctly tracked for the duration of the sequence as can be verified by inspection.}, keywords = {2D shape cues, 3D shape cues, algorithms, Anatomic;Models, articulated human motion, automatic algorithm, Biological;Movement;Posture;Skeleton;Video Recording;, Computer-Assisted;Models, Eigenvalues and eigenfunctions, human pose estimation, HUMANS, Image motion analysis, IMAGE PROCESSING, image registration, Image segmentation, Image sequences, kinematic singularity, Laplacian eigenmaps, multicamera tracking algorithm, pixel displacement, pose estimation, single-frame registration technique, temporal registration method, tracking}, isbn = {1057-7149}, doi = {10.1109/TIP.2009.2022290}, author = {Sundaresan, A. and Chellapa, Rama} } @article {17397, title = {Temporal Summaries: Supporting Temporal Categorical Searching, Aggregation and Comparison}, journal = {IEEE Transactions on Visualization and Computer Graphics}, volume = {15}, year = {2009}, month = {2009/12//Nov}, pages = {1049 - 1056}, abstract = {When analyzing thousands of event histories, analysts often want to see the events as an aggregate to detect insights and generate new hypotheses about the data. An analysis tool must emphasize both the prevalence and the temporal ordering of these events. Additionally, the analysis tool must also support flexible comparisons to allow analysts to gather visual evidence. In a previous work, we introduced align, rank, and filter (ARF) to accentuate temporal ordering. In this paper, we present temporal summaries, an interactive visualization technique that highlights the prevalence of event occurrences. Temporal summaries dynamically aggregate events in multiple granularities (year, month, week, day, hour, etc.) for the purpose of spotting trends over time and comparing several groups of records. They provide affordances for analysts to perform temporal range filters. We demonstrate the applicability of this approach in two extensive case studies with analysts who applied temporal summaries to search, filter, and look for patterns in electronic health records and academic records.}, keywords = {Aggregates, Collaborative work, Computational Biology, Computer Graphics, Data analysis, data visualisation, Data visualization, Databases, Factual, Displays, Event detection, Filters, Heparin, History, Human computer interaction, Human-computer interaction, HUMANS, Information Visualization, Interaction design, interactive visualization technique, Medical Records Systems, Computerized, Pattern Recognition, Automated, Performance analysis, Springs, temporal categorical data visualization, temporal categorical searching, temporal ordering, temporal summaries, Thrombocytopenia, Time factors}, isbn = {1077-2626}, doi = {10.1109/TVCG.2009.187}, author = {Wang,T. D and Plaisant, Catherine and Shneiderman, Ben and Spring, Neil and Roseman,D. and Marchand,G. and Mukherjee,V. and Smith,M.} } @conference {18477, title = {Imaging concert hall acoustics using visual and audio cameras}, booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing, 2008. ICASSP 2008}, year = {2008}, month = {2008///}, pages = {5284 - 5287}, publisher = {IEEE}, organization = {IEEE}, abstract = {Using a developed real time audio camera, that uses the output of a spherical microphone array beamformer steered in all directions to create central projection to create acoustic intensity images, we present a technique to measure the acoustics of rooms and halls. A panoramic mosaiced visual image of the space is also create. Since both the visual and the audio camera images are central projection, registration of the acquired audio and video images can be performed using standard computer vision techniques. We describe the technique, and apply it to the examine the relation between acoustical features and architectural details of the Dekelbaum concert hall at the Clarice Smith Performing Arts Center in College Park, MD.}, keywords = {Acoustic imaging, acoustic intensity images, acoustic measurement, Acoustic measurements, Acoustic scattering, acoustic signal processing, acoustical camera, acoustical scene analysis, acquired audio registration, audio cameras, audio signal processing, CAMERAS, central projection, Computer vision, Educational institutions, HUMANS, image registration, Image segmentation, imaging concert hall acoustics, Layout, microphone arrays, panoramic mosaiced visual image, Raman scattering, reverberation, room acoustics, spherical microphone array beamformer, spherical microphone arrays, video image registration, visual cameras}, isbn = {978-1-4244-1483-3}, doi = {10.1109/ICASSP.2008.4518852}, author = {O{\textquoteright}Donovan,A. and Duraiswami, Ramani and Zotkin,Dmitry N} } @article {12544, title = {Model Driven Segmentation of Articulating Humans in Laplacian Eigenspace}, journal = {Pattern Analysis and Machine Intelligence, IEEE Transactions on}, volume = {30}, year = {2008}, month = {2008/10//}, pages = {1771 - 1785}, abstract = {We propose a general approach using Laplacian Eigenmaps and a graphical model of the human body to segment 3D voxel data of humans into different articulated chains. In the bottom-up stage, the voxels are transformed into a high-dimensional (6D or less) Laplacian Eigenspace (LE) of the voxel neighborhood graph. We show that LE is effective at mapping voxels on long articulated chains to nodes on smooth 1D curves that can be easily discriminated, and prove these properties using representative graphs. We fit 1D splines to voxels belonging to different articulated chains such as the limbs, head and trunk, and determine the boundary between splines using the spline fitting error. A top-down probabilistic approach is then used to register the segmented chains, utilizing their mutual connectivity and individual properties. Our approach enables us to deal with complex poses such as those where the limbs form loops. We use the segmentation results to automatically estimate the human body models. While we use human subjects in our experiments, the method is fairly general and can be applied to voxel-based segmentation of any articulated object composed of long chains. We present results on real and synthetic data that illustrate the usefulness of this approach.}, keywords = {3D voxel data segmentation, algorithms, Anatomic;Pattern Recognition, Artificial intelligence, Automated;Reproducibility of Results;Sensitivity and Specificity;Whole Body Imaging;, Computer simulation, Computer-Assisted;Imaging, curve fitting, Eigenvalues and eigenfunctions, graph theory, human articulation, human body graphical model, human motion analysis, HUMANS, Image Enhancement, Image Interpretation, Image motion analysis, image registration, Image segmentation, Laplace transforms, Laplacian eigenspace transform, model driven segmentation, probability, representative graph, skeleton registration, Smoothing methods, solid modelling, spline fitting error, splines (mathematics), Three-Dimensional;Joints;Models, top-down probabilistic approach, voxel neighborhood graph}, isbn = {0162-8828}, doi = {10.1109/TPAMI.2007.70823}, author = {Sundaresan, A. and Chellapa, Rama} } @conference {18458, title = {Fast Multipole Accelerated Boundary Elements for Numerical Computation of the Head Related Transfer Function}, booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing, 2007. ICASSP 2007}, volume = {1}, year = {2007}, month = {2007/04//}, pages = {I-165-I-168 - I-165-I-168}, publisher = {IEEE}, organization = {IEEE}, abstract = {The numerical computation of head related transfer functions has been attempted by a number of researchers. However, the cost of the computations has meant that usually only low frequencies can be computed and further the computations take inordinately long times. Because of this, comparisons of the computations with measurements are also difficult. We present a fast multipole based iterative preconditioned Krylov solution of a boundary element formulation of the problem and use a new formulation that enables the reciprocity technique to be accurately employed. This allows the calculation to proceed for higher frequencies and larger discretizations. Preliminary results of the computations and of comparisons with measured HRTFs are presented.}, keywords = {Acceleration, Acoustic measurements, Acoustic scattering, audio signal processing, boundary element formulation, Boundary element method, Boundary element methods, boundary-elements methods, Costs, Ear, Fast Multipole Method, Frequency, Head related transfer function, HUMANS, Irrigation, iterative methods, multipole accelerated boundary elements, multipole based iterative preconditioned Krylov solution, numerical computation, Reciprocity, Transfer functions}, isbn = {1-4244-0727-3}, doi = {10.1109/ICASSP.2007.366642}, author = {Gumerov, Nail A. and Duraiswami, Ramani and Zotkin,Dmitry N} } @article {17203, title = {Human Responsibility for Autonomous Agents}, journal = {IEEE Intelligent Systems}, volume = {22}, year = {2007}, month = {2007/04//March}, pages = {60 - 61}, abstract = {Automated or autonomous systems can sometimes fail harmlessly, but they can also destroy data, compromise privacy, and consume resources, such as bandwidth or server capacity. What{\textquoteright}s more troubling is that automated systems embedded in vital systems can cause financial losses, destruction of property, and loss of life. Controlling these dangers will increase trust while enabling broader use of these systems with higher degrees of safety. Obvious threats stem from design errors and software bugs, but we can{\textquoteright}t overlook mistaken assumptions by designers, unanticipated actions by humans, and interference from other computerized systems. This article is part of a special issue on Interacting with Autonomy.}, keywords = {Automatic control, Autonomous agents, autonomous systems, Bandwidth, Computer bugs, Computer errors, Control systems, data privacy, Human-computer interaction, HUMANS, Robots, Safety, Software design}, isbn = {1541-1672}, doi = {10.1109/MIS.2007.32}, author = {Shneiderman, Ben} } @article {12036, title = {A Language for Human Action}, journal = {Computer}, volume = {40}, year = {2007}, month = {2007/05//}, pages = {42 - 51}, abstract = {Human-centered computing (HCC) involves conforming computer technology to humans while naturally achieving human-machine interaction. In a human-centered system, the interaction focuses on human requirements, capabilities, and limitations. These anthropocentric systems also focus on the consideration of human sensory-motor skills in a wide range of activities. This ensures that the interface between artificial agents and human users accounts for perception and action in a novel interaction paradigm. In turn, this leads to behavior understanding through cognitive models that allow content description and, ultimately, the integration of real and virtual worlds. Our work focuses on building a language that maps to the lower-level sensory and motor languages and to the higher-level natural language. An empirically demonstrated human activity language provides sensory-motor-grounded representations for understanding human actions. A linguistic framework allows the analysis and synthesis of these actions.}, keywords = {anthropocentric system, artificial agent, Artificial intelligence, cognitive model, Concrete, Databases, human action, human activity language, Human computer interaction, human factors, human sensory-motor skill, human-centered computing, human-machine interaction, HUMANS, Intelligent sensors, linguistic framework, linguistics, Mirrors, Morphology, natural language, natural languages, Neurons, Power system modeling, user interface, User interfaces}, isbn = {0018-9162}, doi = {10.1109/MC.2007.154}, author = {Guerra-Filho,G. and Aloimonos, J.} } @conference {12026, title = {A Sensory-Motor Language for Human Activity Understanding}, booktitle = {2006 6th IEEE-RAS International Conference on Humanoid Robots}, year = {2006}, month = {2006/12/04/6}, pages = {69 - 75}, publisher = {IEEE}, organization = {IEEE}, abstract = {We have empirically discovered that the space of human actions has a linguistic framework. This is a sensory-motor space consisting of the evolution of the joint angles of the human body in movement. The space of human activity has its own phonemes, morphemes, and sentences. We present a human activity language (HAL) for symbolic non-arbitrary representation of visual and motor information. In phonology, we define atomic segments (kinetemes) that are used to compose human activity. We introduce the concept of a kinetological system and propose five basic properties for such a system: compactness, view-invariance, reproducibility, selectivity, and reconstructivity. In morphology, we extend sequential language learning to incorporate associative learning with our parallel learning approach. Parallel learning is effective in identifying the kinetemes and active joints in a particular action. In syntax, we suggest four lexical categories for our human activity language (noun, verb, adjective, and adverb). These categories are combined into sentences through syntax for human movement}, keywords = {Actuators, associative learning, atomic segments, computational linguistics, Computer science, Computer vision, Educational institutions, grammars, human activity language, human activity understanding, human movement syntax, Humanoid robots, HUMANS, joint angles, kinetemes, kinetological system, Laboratories, learning (artificial intelligence), List key index terms here, Morphology, motor information, No mare than 5, parallel learning, Reproducibility of results, Robot kinematics, Robot programming, robot vision, sensory-motor language, sequential language learning, symbolic nonarbitrary representation, visual information}, isbn = {1-4244-0200-X}, doi = {10.1109/ICHR.2006.321365}, author = {Guerra-Filho,G. and Aloimonos, J.} } @conference {11897, title = {Identifying and segmenting human-motion for mobile robot navigation using alignment errors}, booktitle = {12th International Conference on Advanced Robotics, 2005. ICAR {\textquoteright}05. Proceedings}, year = {2005}, month = {2005/07//}, pages = {398 - 403}, publisher = {IEEE}, organization = {IEEE}, abstract = {This paper presents a new human-motion identification and segmentation algorithm, for mobile robot platforms. The algorithm is based on computing the alignment error between pairs of object images acquired from a moving platform. Pairs of images generating relatively small alignment errors are used to estimate the fundamental frequency of the object{\textquoteright}s motion. A decision criterion is then used to test the significance of the estimated frequency and to classify the object{\textquoteright}s motion. To verify the validity of the proposed approach, experimental results are shown on different classes of objects}, keywords = {Computer errors, Educational institutions, Frequency estimation, human-motion identification, human-motion segmentation, HUMANS, Image motion analysis, Image segmentation, mobile robot navigation, Mobile robots, Motion estimation, Navigation, Object detection, robot vision, SHAPE}, isbn = {0-7803-9178-0}, doi = {10.1109/ICAR.2005.1507441}, author = {Abd-Almageed, Wael and Burns,B. J and Davis, Larry S.} } @article {17258, title = {Interactive sonification of choropleth maps}, journal = {IEEE Multimedia}, volume = {12}, year = {2005}, month = {2005/06//April}, pages = {26 - 35}, abstract = {Auditory information is an important channel for the visually impaired. Effective sonification (the use of non-speech audio to convey information) promotes equal working opportunities for people with vision impairments by helping them explore data collections for problem solving and decision making. Interactive sonification systems can make georeferenced data accessible to people with vision impairments. The authors compare methods for using sound to encode georeferenced data patterns and for navigating maps.}, keywords = {audio signal processing, audio user interfaces, Auditory (non-speech) feedback, auditory information, cartography, choropleth maps, data collections, decision making, Evaluation, Feedback, georeferenced data, Guidelines, handicapped aids, Hardware, HUMANS, information resources, interaction style, Interactive sonification, interactive systems, Navigation, nonspeech audio, problem solving, Problem-solving, sound, universal usability, US Government, User interfaces, vision impairments, World Wide Web}, isbn = {1070-986X}, doi = {10.1109/MMUL.2005.28}, author = {Zhao,Haixia and Smith,B. K and Norman,K. and Plaisant, Catherine and Shneiderman, Ben} } @article {19663, title = {MCMC-based particle filtering for tracking a variable number of interacting targets}, journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence}, volume = {27}, year = {2005}, month = {2005/11//}, pages = {1805 - 1819}, abstract = {We describe a particle filter that effectively deals with interacting targets, targets that are influenced by the proximity and/or behavior of other targets. The particle filter includes a Markov random field (MRF) motion prior that helps maintain the identity of targets throughout an interaction, significantly reducing tracker failures. We show that this MRF prior can be easily implemented by including an additional interaction factor in the importance weights of the particle filter. However, the computational requirements of the resulting multitarget filter render it unusable for large numbers of targets. Consequently, we replace the traditional importance sampling step in the particle filter with a novel Markov chain Monte Carlo (MCMC) sampling step to obtain a more efficient MCMC-based multitarget filter. We also show how to extend this MCMC-based filter to address a variable number of interacting targets. Finally, we present both qualitative and quantitative experimental results, demonstrating that the resulting particle filters deal efficiently and effectively with complicated target interactions.}, keywords = {algorithms, Animals, Artificial intelligence, Computer simulation, Computer vision, Filtering, filtering theory, HUMANS, Image Enhancement, Image Interpretation, Computer-Assisted, Index Terms- Particle filters, Information Storage and Retrieval, Insects, interacting targets, Markov chain Monte Carlo sampling step, Markov chain Monte Carlo., Markov chains, Markov processes, Markov random field motion, Markov random fields, Models, Biological, Models, Statistical, Monte Carlo Method, Monte Carlo methods, MOTION, Movement, multitarget filter, multitarget tracking, particle filtering, Particle filters, Particle tracking, Pattern Recognition, Automated, Sampling methods, Subtraction Technique, target tracking, Video Recording}, isbn = {0162-8828}, author = {Zia Khan and Balch, T. and Dellaert, F.} } @conference {11908, title = {Pedestrian classification from moving platforms using cyclic motion pattern}, booktitle = {IEEE International Conference on Image Processing, 2005. ICIP 2005}, volume = {2}, year = {2005}, month = {2005/09//}, pages = {II- 854-7 - II- 854-7}, publisher = {IEEE}, organization = {IEEE}, abstract = {This paper describes an efficient pedestrian detection system for videos acquired from moving platforms. Given a detected and tracked object as a sequence of images within a bounding box, we describe the periodic signature of its motion pattern using a twin-pendulum model. Then a principle gait angle is extracted in every frame providing gait phase information. By estimating the periodicity from the phase data using a digital phase locked loop (dPLL), we quantify the cyclic pattern of the object, which helps us to continuously classify it as a pedestrian. Past approaches have used shape detectors applied to a single image or classifiers based on human body pixel oscillations, but ours is the first to integrate a global cyclic motion model and periodicity analysis. Novel contributions of this paper include: i) development of a compact shape representation of cyclic motion as a signature for a pedestrian, ii) estimation of gait period via a feedback loop module, and iii) implementation of a fast online pedestrian classification system which operates on videos acquired from moving platforms.}, keywords = {compact shape representation, cyclic motion pattern, data mining, Detectors, digital phase locked loop, digital phase locked loops, feedback loop module, gait analysis, gait phase information, human body pixel oscillations, HUMANS, image classification, Image motion analysis, image representation, image sequence, Image sequences, Motion detection, Object detection, pedestrian classification, pedestrian detection system, Phase estimation, Phase locked loops, principle gait angle, SHAPE, tracking, Videos}, isbn = {0-7803-9134-9}, doi = {10.1109/ICIP.2005.1530190}, author = {Yang Ran and Qinfen Zheng and Weiss, I. and Davis, Larry S. and Abd-Almageed, Wael and Liang Zhao} } @conference {17159, title = {Facilitating understanding of information visualizations: emerging principles and examples}, booktitle = {Eighth International Conference on Information Visualisation, 2004. IV 2004. Proceedings}, year = {2004}, month = {2004/07/14/16}, publisher = {IEEE}, organization = {IEEE}, abstract = {Summary form only given. The enthusiasm for information visualization has generated a wide variety of interesting tools for multi-dimensional, hierarchical, and other kinds of visualizations. However, some designs are readily accepted as understandable and useful, while others are perceived as confusing and useless. Controlled studies have begun to sort of some of the issues, but the insights of designers and usability tests are contributing interesting cognitive hypotheses for researchers and practical guidelines for developers. This paper offers examples of what works and what doesn{\textquoteright}t with a preliminary set of principles that might have wide applicability.}, keywords = {Computer science, data visualisation, Educational institutions, Guidelines, hierarchical visualization, HUMANS, Information Visualization, Laboratories, multidimensional visualization, Portable computers, Testing, usability, User interfaces, Visualization}, isbn = {0-7695-2177-0}, doi = {10.1109/IV.2004.1320117}, author = {Shneiderman, Ben} } @article {12682, title = {Visual tracking and recognition using appearance-adaptive models in particle filters}, journal = {IEEE Transactions on Image Processing}, volume = {13}, year = {2004}, month = {2004/11//}, pages = {1491 - 1506}, abstract = {We present an approach that incorporates appearance-adaptive models in a particle filter to realize robust visual tracking and recognition algorithms. Tracking needs modeling interframe motion and appearance changes, whereas recognition needs modeling appearance changes between frames and gallery images. In conventional tracking algorithms, the appearance model is either fixed or rapidly changing, and the motion model is simply a random walk with fixed noise variance. Also, the number of particles is typically fixed. All these factors make the visual tracker unstable. To stabilize the tracker, we propose the following modifications: an observation model arising from an adaptive appearance model, an adaptive velocity motion model with adaptive noise variance, and an adaptive number of particles. The adaptive-velocity model is derived using a first-order linear predictor based on the appearance difference between the incoming observation and the previous particle configuration. Occlusion analysis is implemented using robust statistics. Experimental results on tracking visual objects in long outdoor and indoor video sequences demonstrate the effectiveness and robustness of our tracking algorithm. We then perform simultaneous tracking and recognition by embedding them in a particle filter. For recognition purposes, we model the appearance changes between frames and gallery images by constructing the intra- and extrapersonal spaces. Accurate recognition is achieved when confronted by pose and view variations.}, keywords = {adaptive filters, adaptive noise variance, algorithms, appearance-adaptive model, Artificial intelligence, Cluster Analysis, Computer Graphics, Computer simulation, Feedback, Filtering, first-order linear predictor, hidden feature removal, HUMANS, Image Enhancement, Image Interpretation, Computer-Assisted, image recognition, Information Storage and Retrieval, Kinematics, Laboratories, Male, Models, Biological, Models, Statistical, MOTION, Movement, Noise robustness, Numerical Analysis, Computer-Assisted, occlusion analysis, Particle filters, Particle tracking, Pattern Recognition, Automated, Predictive models, Reproducibility of results, robust statistics, Sensitivity and Specificity, Signal Processing, Computer-Assisted, State estimation, statistical analysis, Subtraction Technique, tracking, Training data, visual recognition, visual tracking}, isbn = {1057-7149}, doi = {10.1109/TIP.2004.836152}, author = {Zhou,Shaohua Kevin and Chellapa, Rama and Moghaddam, B.} } @article {17293, title = {Meeting human needs with new digital imaging technologies}, journal = {IEEE Multimedia}, volume = {9}, year = {2002}, month = {2002/12//Oct}, pages = {8 - 14}, abstract = {It{\textquoteright}s a visual world. Images capture many people{\textquoteright}s thrills, emotions, and concerns. Art can shock or inspire, and family photos are some of our greatest treasures. It{\textquoteright}s not surprising that visual information is a vital component of the new computing. Most people depend on visual input to understand the world around them and as a basis for further creative activities. The popularity of visual media such as photos, short videos, and animations attests to their mainstream acceptance. Digital photos and image-laden Web pages have already become major computing applications, but users still want higher-resolution images and faster downloads}, keywords = {animation, animations, Computer applications, digital images, digital imaging technologies, Helium, History, HUMANS, Image databases, IMAGE PROCESSING, Photography, photos, software libraries, Videos, visual media, Web pages}, isbn = {1070-986X}, doi = {10.1109/MMUL.2002.1041942}, author = {Shneiderman, Ben} } @conference {14529, title = {Modeling the effect of a nearby boundary on the HRTF}, booktitle = {2001 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2001. Proceedings. (ICASSP {\textquoteright}01)}, volume = {5}, year = {2001}, month = {2001///}, pages = {3337-3340 vol.5 - 3337-3340 vol.5}, publisher = {IEEE}, organization = {IEEE}, abstract = {Understanding and simplified modeling of the head related transfer function (HRTF) holds the key to many applications in spatial audio. We develop an analytical solution to the problem of scattering of sound from a sphere in the vicinity of an infinite plane. Using this solution we study the influence of a nearby scattering rigid surface, on a spherical model for the HRTF}, keywords = {Acoustic scattering, acoustic signal processing, acoustic wave reflection, acoustic wave scattering, architectural acoustics, audio signal processing, Biological system modeling, boundary effect modeling, Computer interfaces, Ear, Educational institutions, Frequency, Head related transfer function, HRTF, HUMANS, infinite plane, Laboratories, Nails, Raman scattering, rigid surface, room environment, sound pressure level, sound scattering, spatial audio, sphere, spherical model, Transfer functions, wall influence}, isbn = {0-7803-7041-4}, doi = {10.1109/ICASSP.2001.940373}, author = {Gumerov, Nail A. and Duraiswami, Ramani} } @conference {11965, title = {Statistical biases in optic flow}, booktitle = {Computer Vision and Pattern Recognition, 1999. IEEE Computer Society Conference on.}, volume = {1}, year = {1999}, month = {1999///}, pages = {566 Vol. 1 - 566 Vol. 1}, publisher = {IEEE}, organization = {IEEE}, abstract = {The computation of optical flow from image derivatives is biased in regions of non uniform gradient distributions. A least-squares or total least squares approach to computing optic flow from image derivatives even in regions of consistent flow can lead to a systematic bias dependent upon the direction of the optic flow, the distribution of the gradient directions, and the distribution of the image noise. The bias a consistent underestimation of length and a directional error. Similar results hold for various methods of computing optical flow in the spatiotemporal frequency domain. The predicted bias in the optical flow is consistent with psychophysical evidence of human judgment of the velocity of moving plaids, and provides an explanation of the Ouchi illusion. Correction of the bias requires accurate estimates of the noise distribution; the failure of the human visual system to make these corrections illustrates both the difficulty of the task and the feasibility of using this distorted optic flow or undistorted normal flow in tasks requiring higher lever processing}, keywords = {Distributed computing, Frequency domain analysis, HUMANS, image derivatives, Image motion analysis, Image sequences, Least squares methods, Motion estimation, Optical computing, Optical distortion, optical flow, Optical noise, Ouchi illusion, perception of motion, Psychology, Spatiotemporal phenomena, statistical analysis, systematic bias, total least squares}, isbn = {0-7695-0149-4}, doi = {10.1109/CVPR.1999.786994}, author = {Ferm{\"u}ller, Cornelia and Pless, R. and Aloimonos, J.} } @conference {12047, title = {Which shape from motion?}, booktitle = {Sixth International Conference on Computer Vision, 1998}, year = {1998}, month = {1998/01/04/7}, pages = {689 - 695}, publisher = {IEEE}, organization = {IEEE}, abstract = {In a practical situation, the rigid transformation relating different views is recovered with errors. In such a case, the recovered depth of the scene contains errors, and consequently a distorted version of visual space is computed. What then are meaningful shape representations that can be computed from the images? The result presented in this paper states that if the rigid transformation between different views is estimated in a way that gives rise to a minimum number of negative depth values, then at the center of the image affine shape can be correctly computed. This result is obtained by exploiting properties of the distortion function. The distortion model turns out to be a very powerful tool in the analysis and design of 3D motion and shape estimation algorithms, and as a byproduct of our analysis we present a computational explanation of psychophysical results demonstrating human visual space distortion from motion information}, keywords = {3D motion estimation, affine shape, Algorithm design and analysis, Computer vision, distorted version, distortion function, human visual space distortion, HUMANS, Image motion analysis, image representation, Information analysis, Layout, Motion analysis, Motion estimation, motion information, Psychology, rigid transformation, SHAPE, shape estimation, shape representations, State estimation, visual space}, isbn = {81-7319-221-9}, doi = {10.1109/ICCV.1998.710792}, author = {Ferm{\"u}ller, Cornelia and Aloimonos, J.} } @article {18317, title = {Recognizing human facial expressions from long image sequences using optical flow}, journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence}, volume = {18}, year = {1996}, month = {1996/06//}, pages = {636 - 642}, abstract = {An approach to the analysis and representation of facial dynamics for recognition of facial expressions from image sequences is presented. The algorithms utilize optical flow computation to identify the direction of rigid and nonrigid motions that are caused by human facial expressions. A mid-level symbolic representation motivated by psychological considerations is developed. Recognition of six facial expressions, as well as eye blinking, is demonstrated on a large set of image sequences}, keywords = {Computer vision, Eyebrows, face recognition, facial dynamics, Facial features, human facial expression recognition, HUMANS, Image motion analysis, image recognition, image representation, Image sequences, Motion analysis, Motion estimation, Optical computing, optical flow, symbolic representation, tracking}, isbn = {0162-8828}, doi = {10.1109/34.506414}, author = {Yacoob,Yaser and Davis, Larry S.} } @conference {12031, title = {Iso-distortion contours and egomotion estimation}, booktitle = {Proceedings of International Symposium on Computer Vision, 1995}, year = {1995}, month = {1995/11/21/23}, pages = {55 - 60}, publisher = {IEEE}, organization = {IEEE}, abstract = {This paper introduces the framework of iso-distortion contour to deal with the problem of depth distortion due to erroneous motion estimates, and various related aspects such as the effectiveness of the visibility constraint. The framework can also be used to inquire the uniqueness aspect of normal flow. Future work will examine the implications of the iso-distortion contours for the problem of multiple frame integration}, keywords = {Automation, Computer vision, Degradation, depth distortion, Educational institutions, egomotion estimation, Equations, erroneous motion estimates, Error analysis, HUMANS, Image sequences, iso-distortion contours, Laboratories, Layout, Motion estimation, Robustness, visibility constraint}, isbn = {0-8186-7190-4}, doi = {10.1109/ISCV.1995.476977}, author = {LoongFah Cheong and Aloimonos, J.} } @article {16988, title = {Beyond intelligent machines: just do it}, journal = {IEEE Software}, volume = {10}, year = {1993}, month = {1993/01//}, pages = {100 - 103}, abstract = {The author argues that users want a sense of direct and immediate control over computers that differs from how they interact with people. He presents several examples of these predictable and controllable interfaces developed in the lab. The examples include tree maps and dynamic queries.<>}, keywords = {Artificial intelligence, Computer aided instruction, Computer errors, controllable interfaces, Displays, dynamic queries, Educational institutions, History, HUMANS, intelligent machines, learning systems, Machine intelligence, predictable interfaces, Speech recognition, tree maps, User interfaces}, isbn = {0740-7459}, doi = {10.1109/52.207235}, author = {Shneiderman, Ben} } @conference {17438, title = {Tree-maps: a space-filling approach to the visualization of hierarchical information structures}, booktitle = {, IEEE Conference on Visualization, 1991. Visualization {\textquoteright}91, Proceedings}, year = {1991}, month = {1991/10/22/25}, pages = {284 - 291}, publisher = {IEEE}, organization = {IEEE}, abstract = {A method for visualizing hierarchically structured information is described. The tree-map visualization technique makes 100\% use of the available display space, mapping the full hierarchy onto a rectangular region in a space-filling manner. This efficient use of space allows very large hierarchies to be displayed in their entirety and facilitates the presentation of semantic information. Tree-maps can depict both the structure and content of the hierarchy. However, the approach is best suited to hierarchies in which the content of the leaf nodes and the structure of the hierarchy are of primary importance, and the content information associated with internal nodes is largely derived from their children}, keywords = {Computer displays, Computer Graphics, Computer science, Data analysis, display space, Educational institutions, Feedback, hierarchical information structures, HUMANS, Laboratories, Libraries, Marine vehicles, rectangular region, semantic information, space-filling approach, tree-map visualization technique, trees (mathematics), Two dimensional displays, Visualization}, isbn = {0-8186-2245-8}, doi = {10.1109/VISUAL.1991.175815}, author = {Johnson,B. and Shneiderman, Ben} } @conference {11960, title = {Purposive and qualitative active vision}, booktitle = {Proceedings of 10th International Conference on Pattern Recognition, 1990}, volume = {i}, year = {1990}, month = {1990/06/16/21}, pages = {346-360 vol.1 - 346-360 vol.1}, publisher = {IEEE}, organization = {IEEE}, abstract = {The traditional view of the problem of computer vision as a recovery problem is questioned, and the paradigm of purposive-qualitative vision is offered as an alternative. This paradigm considers vision as a general recognition problem (recognition of objects, patterns or situations). To demonstrate the usefulness of the framework, the design of the Medusa of CVL is described. It is noted that this machine can perform complex visual tasks without reconstructing the world. If it is provided with intentions, knowledge of the environment, and planning capabilities, it can perform highly sophisticated navigational tasks. It is explained why the traditional structure from motion problem cannot be solved in some cases and why there is reason to be pessimistic about the optimal performance of a structure from motion module. New directions for future research on this problem in the recovery paradigm, e.g., research on stability or robustness, are suggested}, keywords = {active vision, Automation, brain models, complex visual tasks, Computer vision, environmental knowledge, highly sophisticated navigational tasks, HUMANS, Image reconstruction, intentions, Kinetic theory, Laboratories, Medusa, Motion analysis, Navigation, planning, planning (artificial intelligence), purposive-qualitative vision, recovery problem, Robust stability, Robustness, SHAPE, stability}, isbn = {0-8186-2062-5}, doi = {10.1109/ICPR.1990.118128}, author = {Aloimonos, J.} } @article {16027, title = {Some Brief Essays on Mind}, year = {1989}, month = {1989/07//}, institution = {ROCHESTER UNIV NY DEPT OF COMPUTER SCIENCE}, abstract = {The author tries to explain his view of artificial intelligence, and more broadly how it fits into science as a whole. In doing so, he will not hesitate to indulge in sheer speculation when it seems to fit the topic. He will begin with a negative thought (one that he does not agree with). Consider the statement that, while robots and AI (artificial intelligence) may make great strides in the future, still they never will be able to produce music with the sensitivity of certain humans with great musical talent. (kr)}, keywords = {*ARTIFICIAL INTELLIGENCE, CYBERNETICS, HUMANS, Music, Robots}, url = {http://stinet.dtic.mil/oai/oai?\&verb=getRecord\&metadataPrefix=html\&identifier=ADA213887}, author = {Perlis, Don} } @article {11994, title = {Visual shape computation}, journal = {Proceedings of the IEEE}, volume = {76}, year = {1988}, month = {1988/08//}, pages = {899 - 916}, abstract = {Perceptual processes responsible for computing shape from several cues, including shading, texture, contour, and stereo, are examined. It is noted that these computational problems, as well as that of computing shaping from motion, are ill-posed in the sense of Hadamard. It is suggested that regularization theory can be used along with a priori knowledge to restrict the space of possible solutions, and thus restore the problem{\textquoteright}s well-prosedness. Some alternative methods are outlined, and the idea of active vision is explored briefly in connection with the problem}, keywords = {a priori knowledge, active vision, computational problems, Computer vision, computing shaping from motion, contour, cues, Focusing, HUMANS, ill posed problems, Machine vision, Psychology, regularization theory, RETINA, sense of Hadamard, shading, SHAPE, space of possible solutions, Stereo vision, Surface texture, TEXTURE, visual shape computation, Visual system}, isbn = {0018-9219}, doi = {10.1109/5.5964}, author = {Aloimonos, J.} } @article {13842, title = {Principle-Based Parsing for Machine Translation}, year = {1987}, month = {1987/12//}, institution = {MASSACHUSETTS INST OF TECH CAMBRIDGE ARTIFICIAL INTELLIGENCE LAB}, abstract = {Many syntactic parsing strategies for machine translation systems are based entirely on context-free grammars. These parsers require an overwhelming number of rules; thus, translation systems using rule-based parsers either have limited linguistic coverage, or they have poor performance due to formidable grammar size. This report shows how a principle-based parser with a co-routine design improves parsing for translation. The parser consists of a skeletal structure-building mechanism that operates in conjunction with a linguistically based constraint module, passing control back and forth until a set of underspecified skeletal phrase-structures is converted into a fully instantiated parse tree. The modularity of the parsing design accommodates linguistic generalization, reduces the grammar size, allows extension to other languages, and is compatible with studies of human language processing. Keywords: Natural language processing, Interlingual translation, Parsing, Subroutines, Principles vs. Rules, Co-routine design, Linguistic constraints.}, keywords = {*MACHINE TRANSLATION, *PARSERS, *SYNTAX, CONTROL, COROUTINE DESIGN, CYBERNETICS, grammars, HUMANS, LANGUAGE, linguistics, MODULAR CONSTRUCTION, natural language, PRINCIPLES BASED PARSERS, PROCESSING, STRATEGY, SUBROUTINES}, url = {http://stinet.dtic.mil/oai/oai?\&verb=getRecord\&metadataPrefix=html\&identifier=ADA199183}, author = {Dorr, Bonnie J} } @article {12051, title = {Computing Intrinsic Images.}, year = {1986}, month = {1986/08//}, abstract = {Low level modern computer vision is not domain dependent, but concentrates on problems that correspond to identifiable modules in the human visual system. Several theories have been proposed in the literature for the computation of shape from shading, shape from texture, retinal motion from spatiotemporal derivatives of the image intensity function and the like. The problems with the existing approach are basically the following: (1) The employed assumptions are very strong and so most of the algorithms fail when applied to real images. (2) Usually the constraints from the geometry and the physics of the problem are not enough to guarantee uniqueness of the computed parameters. (3) In most cases the resulting algorithms are not robust, in the sense that if there is a slight error in the input this results in a catastrophic error in the output. In this thesis the problem of machine vision is explored from its basics. A low level mathematical theory is presented for the unique robust computation of intrinsic parameters. The computational aspect of the theory envisages a cooperative highly parallel implementation, bringing in information from five different sources (shading, texture, motion, contour and stereo), to resolve ambiguities and ensure uniqueness and stability of the intrinsic parameters. The problems of shape from texture, shape from shading and motion, visual motion analysis and shape and motion from contour are analyzed in detail.}, keywords = {*ARTIFICIAL INTELLIGENCE, *COMPUTERS, *IMAGE PROCESSING, *VISION, algorithms, CAMERAS, CATASTROPHIC CONDITIONS, COMPUTATIONS, CYBERNETICS, ERRORS, HUMANS, IMAGES, INTENSITY, LOW LEVEL, MATHEMATICS, MOTION, RETINA, Robots, SHADOWS, SHAPE, TEXTURE, THEORY, THESES.}, url = {http://stinet.dtic.mil/oai/oai?\&verb=getRecord\&metadataPrefix=html\&identifier=ADA189440}, author = {Aloimonos, J.} } @article {18988, title = {Pseudogenes for human small nuclear RNA U3 appear to arise by integration of self-primed reverse transcripts of the RNA into new chromosomal sites}, journal = {CellCell}, volume = {32}, year = {1983}, month = {1983/02//}, pages = {461 - 472}, abstract = {We find that both human and rat U3 snRNA can function as self-priming templates for AMV reverse transcriptase in vitro. The 74 base cDNA is primed by the 3{\textquoteright} end of intact U3 snRNA, and spans the characteristically truncated 69 or 70 base U3 sequence found in four different human U3 pseudogenes. The ability of human and rat U3 snRNA to self-prime is consistent with a U3 secondary structure model derived by a comparison between rat U3 snRNA and the homologous D2 snRNA from Dictyostelium discoideum. We propose that U3 pseudogenes are generated in vivo by integration of a self-primed cDNA copy of U3 snRNA at new chromosomal sites. We also consider the possibility that the same cDNA mediates gene conversion at the 5{\textquoteright} end of bona fide U3 genes where, over the entire region spanned by the U3 cDNA, the two rat U3 sequence variants U3A and U3B are identical.}, keywords = {Animals, Base Sequence, DNA, genes, HUMANS, Nucleic Acid Conformation, Rats, Recombination, Genetic, Repetitive Sequences, Nucleic Acid, RNA, RNA, Small Nuclear, RNA-Directed DNA Polymerase, Templates, Genetic, Transcription, Genetic}, isbn = {0092-8674}, url = {http://www.ncbi.nlm.nih.gov/pubmed/6186397}, author = {Bernstein,L B and Mount, Stephen M. and Weiner,A M} } @article {17301, title = {Multiparty Grammars and Related Features for Defining Interactive Systems}, journal = {IEEE Transactions on Systems, Man and Cybernetics}, volume = {12}, year = {1982}, month = {1982/03//}, pages = {148 - 154}, abstract = {Multiparty grammars are introduced which contain labeled nonterminals to indicate the party that produces the terminal string. For interactive person-computer systems, both the user commands and system responses can be described by the linked BNF grammars. Multiparty grammars may also be used to describe communication among several people (by way of computers or in normal dialogue), network protocols among several machines, or complex interactions involving several people and machines. Visual features such as underlining, reversal, blinking, and color, window declarations, and dynamic operations dependent on cursor movement are also covered.}, keywords = {Application software, Computer aided instruction, Computer displays, Computer languages, Computer networks, Debugging, HUMANS, interactive systems, Protocols, Writing}, isbn = {0018-9472}, doi = {10.1109/TSMC.1982.4308798}, author = {Shneiderman, Ben} } @article {19002, title = {Structure and function of small ribonucleoproteins from eukaryotic cells}, journal = {Princess Takamatsu symposiaInt. Symp. Princess Takamatsu Cancer Res. Fund}, volume = {12}, year = {1982}, month = {1982///}, pages = {101 - 107}, abstract = {Autoantibodies from patients with systemic lupus erythematosus and other related diseases have been used to identify and study small RNA-protein complexes from mammalian cells. Properties of three previously described and several new classes of small ribonucleoproteins (RNPs) are reviewed. The sequence of Drosophila U1 RNA reveals that the region proposed to pair with 5{\textquoteright} splice junctions is conserved, while that proposed to interact with 3{\textquoteright} junctions diverges; this forces some revision of the model for U1 small nuclear (sn)RNP participation in hnRNA splicing. Further characterization of the Ro and La small RNPs has shown that the Ro small cytoplasmic (sc)RNPs are a subclass of La RNPs. Both tRNA and 5S rRNA precursors are at least transiently associated with the La protein. This raises the possibility that the La protein may be an RNA polymerase III transcription factor.}, keywords = {Antigen-Antibody Complex, Autoantibodies, HUMANS, Lupus Erythematosus, Systemic, Nucleoproteins, Ribonucleoproteins, RNA Polymerase III, Transcription, Genetic}, url = {http://www.ncbi.nlm.nih.gov/pubmed/7166547}, author = {Steitz,J. A. and Berg,C and Gottlieb,E. and Hardin,J A and Hashimoto,C and Hendrick,J P and Hinterberger,M. and Krikeles,M and Lerner,M R and Mount, Stephen M.} }