%0 Journal Article %J Pattern Analysis and Machine Intelligence, IEEE Transactions on %D 2012 %T Density-Based Multifeature Background Subtraction with Support Vector Machine %A Han,Bohyung %A Davis, Larry S. %K algorithm;density-based %K application;illumination %K approximation;object %K background %K camera;support %K change;kernel %K Computer %K density %K detection;pixelwise %K detection;support %K extraction;image %K feature;background %K generative %K Haar-like %K likelihood %K machine;Haar %K machines;vectors; %K modeling %K multifeature %K segmentation %K segmentation;object %K subtraction %K technique;discriminative %K technique;high-level %K techniques;spatial %K transforms;cameras;computer %K variation;spatio-temporal %K variation;static %K vector %K vector;binary %K VISION %K vision;feature %X Background modeling and subtraction is a natural technique for object detection in videos captured by a static camera, and also a critical preprocessing step in various high-level computer vision applications. However, there have not been many studies concerning useful features and binary segmentation algorithms for this problem. We propose a pixelwise background modeling and subtraction technique using multiple features, where generative and discriminative techniques are combined for classification. In our algorithm, color, gradient, and Haar-like features are integrated to handle spatio-temporal variations for each pixel. A pixelwise generative background model is obtained for each feature efficiently and effectively by Kernel Density Approximation (KDA). Background subtraction is performed in a discriminative manner using a Support Vector Machine (SVM) over background likelihood vectors for a set of features. The proposed algorithm is robust to shadow, illumination changes, spatial variations of background. We compare the performance of the algorithm with other density-based methods using several different feature combinations and modeling techniques, both quantitatively and qualitatively. %B Pattern Analysis and Machine Intelligence, IEEE Transactions on %V 34 %P 1017 - 1023 %8 2012/05// %@ 0162-8828 %G eng %N 5 %R 10.1109/TPAMI.2011.243 %0 Journal Article %J Computer %D 2010 %T Face Recognition by Computers and Humans %A Chellapa, Rama %A Sinha, P. %A Phillips,P.J. %K access %K Computer %K control;aging;computer %K control;face %K entertainment;database %K interaction;national %K interaction;unconstrained %K reality;access %K recognition;homeland %K recognition;human %K retrieval;face %K security; %K security;human %K sequences;virtual %K video %X This article talks about how the study of how humans perceive faces can be used to help design practical systems for face recognition. Besides applications related to identification and verification-such as access control, law enforcement, ID and licensing, and surveillance-face recognition has also proven useful in applications such as human-computer interaction, virtual reality, database retrieval, multimedia, and computer entertainment. Continuing research into face recognition will provide scientists and engineers with many vital projects, in areas such as homeland security, human-computer interaction, and numerous consumer applications. The areas we are considering pursuing are recognition from unconstrained video sequences, incorporating familiarity into algorithms, modeling effects of aging, and developing biologically plausible models for human face recognition ability. %B Computer %V 43 %P 46 - 55 %8 2010/02// %@ 0018-9162 %G eng %N 2 %R 10.1109/MC.2010.37 %0 Conference Paper %B Shape Modeling and Applications, 2009. SMI 2009. IEEE International Conference on %D 2009 %T Classification of non-manifold singularities from transformations of 2-manifolds %A Leon,J.-C. %A De Floriani, Leila %A Hetroy,F. %K classification;search %K Computer %K graphic;continuous %K graphics;pattern %K model;nonmanifold %K problems;topology; %K property;computer %K SHAPE %K singularity;topological %K transformation;nonmanifold %X Non-manifold models are frequently encountered in engineering simulations and design as well as in computer graphics. However, these models lack shape characterization for modelling and searching purposes. Topological properties act as a kernel for deriving key features of objects. Here we propose a classification for the non-manifold singularities of non-manifold objects through continuous shape transformations of 2-manifolds without boundary up to the creation of non-manifold singularities. As a result, the non-manifold objects thus created can be categorized and contribute to the definition of a general purpose taxonomy for non-manifold shapes. %B Shape Modeling and Applications, 2009. SMI 2009. IEEE International Conference on %P 179 - 184 %8 2009/06// %G eng %R 10.1109/SMI.2009.5170146 %0 Book Section %B Passive and Active Network MeasurementPassive and Active Network Measurement %D 2009 %T Triangle Inequality and Routing Policy Violations in the Internet %A Lumezanu,Cristian %A Baden,Randy %A Spring, Neil %A Bhattacharjee, Bobby %E Moon,Sue %E Teixeira,Renata %E Uhlig,Steve %K Computer %K Science %X Triangle inequality violations (TIVs) are the effect of packets between two nodes being routed on the longer direct path between them when a shorter detour path through an intermediary is available. TIVs are a natural, widespread and persistent consequence of Internet routing policies. By exposing opportunities to improve the delay between two nodes, TIVs can help myriad applications that seek to minimize end-to-end latency. However, sending traffic along the detour paths revealed by TIVs may influence Internet routing negatively. In this paper we study the interaction between triangle inequality violations and policy routing in the Internet. We use measured and predicted AS paths between Internet nodes to show that 25% of the detour paths exposed by TIVs are in fact available to BGP but are simply deemed “less efficient”. We also compare the AS paths of detours and direct paths and find that detours use AS edges that are rarely followed by default Internet paths, while avoiding others that BGP seems to prefer. Our study is important both for understanding the various interactions that occur at the routing layer as well as their effects on applications that seek to use TIVs to minimize latency. %B Passive and Active Network MeasurementPassive and Active Network Measurement %S Lecture Notes in Computer Science %I Springer Berlin / Heidelberg %V 5448 %P 45 - 54 %8 2009/// %@ 978-3-642-00974-7 %G eng %U http://dx.doi.org/10.1007/978-3-642-00975-4_5 %0 Book Section %B Scalable Uncertainty ManagementScalable Uncertainty Management %D 2007 %T Aggregates in Generalized Temporally Indeterminate Databases %A Udrea,Octavian %A Majkić,Zoran %A Subrahmanian,V. %E Prade,Henri %E Subrahmanian,V. %K Computer %K Science %X Dyreson and Snodgrass as well as Dekhtyar et. al. have provided a probabilistic model (as well as compelling example applications) for why there may be temporal indeterminacy in databases. In this paper, we first propose a formal model for aggregate computation in such databases when there is uncertainty not just in the temporal attribute, but also in the ordinary (non-temporal) attributes. We identify two types of aggregates: event correlated aggregates, and non event correlated aggregations, and provide efficient algorithms for both of them. We prove that our algorithms are correct, and we present experimental results showing that the algorithms work well in practice. %B Scalable Uncertainty ManagementScalable Uncertainty Management %S Lecture Notes in Computer Science %I Springer Berlin / Heidelberg %V 4772 %P 171 - 186 %8 2007/// %@ 978-3-540-75407-7 %G eng %U http://dx.doi.org/10.1007/978-3-540-75410-7_13 %0 Conference Paper %B Computer Vision, 2005. ICCV 2005. Tenth IEEE International Conference on %D 2005 %T An algebraic approach to surface reconstruction from gradient fields %A Agrawal,A. %A Chellapa, Rama %A Raskar, R. %K algebra; %K algebraic %K approach; %K Computer %K confinement; %K discrete %K domain %K error %K field; %K from %K gradient %K graph %K image %K integrability; %K linear %K local %K methods; %K photometric %K reconstruction; %K shading; %K SHAPE %K stereo; %K surface %K system; %K theory; %K vision; %X Several important problems in computer vision such as shape from shading (SFS) and photometric stereo (PS) require reconstructing a surface from an estimated gradient field, which is usually non-integrable, i.e. have non-zero curl. We propose a purely algebraic approach to enforce integrability in discrete domain. We first show that enforcing integrability can be formulated as solving a single linear system Ax =b over the image. In general, this system is under-determined. We show conditions under which the system can be solved and a method to get to those conditions based on graph theory. The proposed approach is non-iterative, has the important property of local error confinement and can be applied to several problems. Results on SFS and PS demonstrate the applicability of our method. %B Computer Vision, 2005. ICCV 2005. Tenth IEEE International Conference on %V 1 %P 174 - 181 Vol. 1 - 174 - 181 Vol. 1 %8 2005/10// %G eng %R 10.1109/ICCV.2005.31 %0 Conference Paper %B INFOCOM 2005. 24th Annual Joint Conference of the IEEE Computer and Communications Societies. Proceedings IEEE %D 2005 %T Differentiated traffic engineering for QoS provisioning %A Tabatabaee,V. %A Bhattacharjee, Bobby %A La,R.J. %A Shayman,M.A. %K based %K Computer %K differentiated %K DiffServ %K DTE; %K engineering; %K evaluation; %K link; %K links; %K management; %K multipath %K network %K networks; %K nonconvex %K of %K optimisation; %K OPTIMIZATION %K packet %K performance %K problem; %K provisioning; %K QoS %K QUALITY %K routing; %K service; %K simulation-based %K source %K Telecommunication %K traffic %K traffic; %X We introduce a new approach for QoS provisioning in packet networks based on the notion of differentiated traffic engineering (DTE). We consider a single AS network capable of source based multi-path routing. We do not require sophisticated queuing or per-class scheduling at individual routers; instead, if a link is used to forward QoS sensitive packets, we maintain its utilization below a threshold. As a consequence, DTE eliminates the need for per-flow (IntServ) or per-class (DiffServ) packet processing tasks such as traffic classification, queueing, shaping, policing and scheduling in the core and hence poses a lower burden on the network management unit. Conversely, DTE utilizes network bandwidth much more efficiently than simple over-provisioning. In this paper, we propose a complete architecture and an algorithmic structure for DTE. We show that our scheme can be formulated as a non-convex optimization problem, and we present an optimal solution framework based on simulated annealing. We present a simulation-based performance evaluation of DTE, and compare our scheme to existing (gradient projection) methods. %B INFOCOM 2005. 24th Annual Joint Conference of the IEEE Computer and Communications Societies. Proceedings IEEE %V 4 %P 2349 - 2359 vol. 4 - 2349 - 2359 vol. 4 %8 2005/03// %G eng %R 10.1109/INFCOM.2005.1498521 %0 Book Section %B Computational Logic in Multi-Agent SystemsComputational Logic in Multi-Agent Systems %D 2005 %T Distributed Algorithms for Dynamic Survivability of Multiagent Systems %A Subrahmanian,V. %A Kraus,Sarit %A Zhang,Yingqian %E Dix,Jürgen %E Leite,João %K Computer %K Science %X Though multiagent systems (MASs) are being increasingly used, few methods exist to ensure survivability of MASs. All existing methods suffer from two flaws. First, a centralized survivability algorithm (CSA) ensures survivability of the MAS – unfortunately, if the node on which the CSA exists goes down, the survivability of the MAS is questionable. Second, no mechanism exists to change how the MAS is deployed when external factors trigger a re-evaluation of the survivability of the MAS. In this paper, we present three algorithms to address these two important problems. Our algorithms can be built on top of any CSA. Our algorithms are completely distributed and can handle external triggers to compute a new deployment. We report on experiments assessing the efficiency of these algorithms. %B Computational Logic in Multi-Agent SystemsComputational Logic in Multi-Agent Systems %S Lecture Notes in Computer Science %I Springer Berlin / Heidelberg %V 3259 %P 139 - 144 %8 2005/// %@ 978-3-540-24010-5 %G eng %U http://dx.doi.org/10.1007/978-3-540-30200-1_1 %0 Conference Paper %B Computer Vision, 2005. ICCV 2005. Tenth IEEE International Conference on %D 2005 %T Fast multiple object tracking via a hierarchical particle filter %A Yang,Changjiang %A Duraiswami, Ramani %A Davis, Larry S. %K (numerical %K algorithm; %K analysis; %K Color %K colour %K Computer %K Convergence %K detection; %K edge %K fast %K filter; %K Filtering %K hierarchical %K histogram; %K image %K images; %K integral %K likelihood; %K methods); %K methods; %K multiple %K numerical %K object %K observation %K of %K orientation %K particle %K processes; %K quasirandom %K random %K sampling; %K tracking %K tracking; %K vision; %K visual %X A very efficient and robust visual object tracking algorithm based on the particle filter is presented. The method characterizes the tracked objects using color and edge orientation histogram features. While the use of more features and samples can improve the robustness, the computational load required by the particle filter increases. To accelerate the algorithm while retaining robustness we adopt several enhancements in the algorithm. The first is the use of integral images for efficiently computing the color features and edge orientation histograms, which allows a large amount of particles and a better description of the targets. Next, the observation likelihood based on multiple features is computed in a coarse-to-fine manner, which allows the computation to quickly focus on the more promising regions. Quasi-random sampling of the particles allows the filter to achieve a higher convergence rate. The resulting tracking algorithm maintains multiple hypotheses and offers robustness against clutter or short period occlusions. Experimental results demonstrate the efficiency and effectiveness of the algorithm for single and multiple object tracking. %B Computer Vision, 2005. ICCV 2005. Tenth IEEE International Conference on %V 1 %P 212 - 219 Vol. 1 - 212 - 219 Vol. 1 %8 2005/10// %G eng %R 10.1109/ICCV.2005.95 %0 Conference Paper %B Computer Vision, 2005. ICCV 2005. Tenth IEEE International Conference on %D 2005 %T On-line density-based appearance modeling for object tracking %A Han,B. %A Davis, Larry S. %K appearance %K approximation;Gaussian %K Computer %K density %K density-based %K detection;target %K Gaussian %K mixtures;object %K modeling %K modeling;real-time %K processes;computer %K sequences;object %K technique;online %K tracking; %K tracking;online %K vision;image %K vision;sequential %X Object tracking is a challenging problem in real-time computer vision due to variations of lighting condition, pose, scale, and view-point over time. However, it is exceptionally difficult to model appearance with respect to all of those variations in advance; instead, on-line update algorithms are employed to adapt to these changes. We present a new on-line appearance modeling technique which is based on sequential density approximation. This technique provides accurate and compact representations using Gaussian mixtures, in which the number of Gaussians is automatically determined. This procedure is performed in linear time at each time step, which we prove by amortized analysis. Features for each pixel and rectangular region are modeled together by the proposed sequential density approximation algorithm, and the target model is updated in scale robustly. We show the performance of our method by simulations and tracking in natural videos %B Computer Vision, 2005. ICCV 2005. Tenth IEEE International Conference on %V 2 %P 1492 -1499 Vol. 2 - 1492 -1499 Vol. 2 %8 2005/10// %G eng %R 10.1109/ICCV.2005.181 %0 Book Section %B On the Move to Meaningful Internet Systems 2005: CoopIS, DOA, and ODBASEOn the Move to Meaningful Internet Systems 2005: CoopIS, DOA, and ODBASE %D 2005 %T Probabilistic Ontologies and Relational Databases %A Udrea,Octavian %A Yu,Deng %A Hung,Edward %A Subrahmanian,V. %E Meersman,Robert %E Tari,Zahir %K Computer %K Science %X The relational algebra and calculus do not take the semantics of terms into account when answering queries. As a consequence, not all tuples that should be returned in response to a query are always returned, leading to low recall. In this paper, we propose the novel notion of a constrained probabilistic ontology (CPO). We developed the concept of a CPO-enhanced relation in which each attribute of a relation has an associated CPO. These CPOs describe relationships between terms occurring in the domain of that attribute. We show that the relational algebra can be extended to handle CPO-enhanced relations. This allows queries to yield sets of tuples, each of which has a probability of being correct. %B On the Move to Meaningful Internet Systems 2005: CoopIS, DOA, and ODBASEOn the Move to Meaningful Internet Systems 2005: CoopIS, DOA, and ODBASE %S Lecture Notes in Computer Science %I Springer Berlin / Heidelberg %V 3760 %P 1 - 17 %8 2005/// %@ 978-3-540-29736-9 %G eng %U http://dx.doi.org/10.1007/11575771_1 %0 Conference Paper %B Advanced Video and Signal Based Surveillance, 2005. AVSS 2005. IEEE Conference on %D 2005 %T VidMAP: video monitoring of activity with Prolog %A Shet,V. D %A Harwood,D. %A Davis, Larry S. %K activities %K algorithms; %K based %K Computer %K computerised %K engine; %K higher %K image %K level %K Logic %K monitoring; %K multicamera %K processing; %K programming; %K Prolog %K PROLOG; %K reasoning %K recognition; %K scenario; %K signal %K streaming; %K streams; %K Surveillance %K surveillance; %K system; %K video %K VISION %K vision; %K visual %X This paper describes the architecture of a visual surveillance system that combines real time computer vision algorithms with logic programming to represent and recognize activities involving interactions amongst people, packages and the environments through which they move. The low level computer vision algorithms log primitive events of interest as observed facts, while the higher level Prolog based reasoning engine uses these facts in conjunction with predefined rules to recognize various activities in the input video streams. The system is illustrated in action on a multi-camera surveillance scenario that includes both security and safety violations. %B Advanced Video and Signal Based Surveillance, 2005. AVSS 2005. IEEE Conference on %P 224 - 229 %8 2005/09// %G eng %R 10.1109/AVSS.2005.1577271 %0 Conference Paper %B Acoustics, Speech, and Signal Processing, 2004. Proceedings. (ICASSP '04). IEEE International Conference on %D 2004 %T 3D model refinement using surface-parallax %A Agrawala, Ashok K. %A Chellapa, Rama %K 3D %K adaptive %K arbitrary %K camera %K coarse %K compensation; %K Computer %K DEM; %K depth %K digital %K ELEVATION %K environments; %K epipolar %K estimation; %K field; %K image %K incomplete %K INTENSITY %K map; %K model %K MOTION %K parallax; %K plane-parallax %K reconstruction; %K recovery; %K refinement; %K sequence; %K sequences; %K surface %K surfaces; %K urban %K vision; %K windowing; %X We present an approach to update and refine coarse 3D models of urban environments from a sequence of intensity images using surface parallax. This generalizes the plane-parallax recovery methods to surface-parallax using arbitrary surfaces. A coarse and potentially incomplete depth map of the scene obtained from a digital elevation map (DEM) is used as a reference surface which is refined and updated using this approach. The reference depth map is used to estimate the camera motion and the motion of the 3D points on the reference surface is compensated. The resulting parallax, which is an epipolar field, is estimated using an adaptive windowing technique and used to obtain the refined depth map. %B Acoustics, Speech, and Signal Processing, 2004. Proceedings. (ICASSP '04). IEEE International Conference on %V 3 %P iii - 285-8 vol.3 - iii - 285-8 vol.3 %8 2004/05// %G eng %R 10.1109/ICASSP.2004.1326537 %0 Conference Paper %B Pattern Recognition, 2004. ICPR 2004. Proceedings of the 17th International Conference on %D 2004 %T Iterative figure-ground discrimination %A Zhao, L. %A Davis, Larry S. %K algorithm; %K analysis; %K Bandwidth %K calculation; %K Color %K colour %K Computer %K density %K dimensional %K discrimination; %K distribution; %K distributions; %K Estimation %K estimation; %K expectation %K figure %K Gaussian %K ground %K image %K initialization; %K iterative %K Kernel %K low %K methods; %K mixture; %K model %K model; %K nonparametric %K parameter %K parametric %K processes; %K sampling %K sampling; %K segmentation %K segmentation; %K statistics; %K theory; %K vision; %X Figure-ground discrimination is an important problem in computer vision. Previous work usually assumes that the color distribution of the figure can be described by a low dimensional parametric model such as a mixture of Gaussians. However, such approach has difficulty selecting the number of mixture components and is sensitive to the initialization of the model parameters. In this paper, we employ non-parametric kernel estimation for color distributions of both the figure and background. We derive an iterative sampling-expectation (SE) algorithm for estimating the color, distribution and segmentation. There are several advantages of kernel-density estimation. First, it enables automatic selection of weights of different cues based on the bandwidth calculation from the image itself. Second, it does not require model parameter initialization and estimation. The experimental results on images of cluttered scenes demonstrate the effectiveness of the proposed algorithm. %B Pattern Recognition, 2004. ICPR 2004. Proceedings of the 17th International Conference on %V 1 %P 67 - 70 Vol.1 - 67 - 70 Vol.1 %8 2004/08// %G eng %R 10.1109/ICPR.2004.1334006 %0 Conference Paper %B Image Processing, 2004. ICIP '04. 2004 International Conference on %D 2004 %T Multi-level fast multipole method for thin plate spline evaluation %A Zandifar,A. %A Lim,S. %A Duraiswami, Ramani %A Gumerov, Nail A. %A Davis, Larry S. %K (mathematics); %K Computer %K deformation; %K evaluation; %K fast %K image %K MATCHING %K matching; %K metal %K method; %K multilevel %K multipole %K nonrigid %K pixel; %K plate %K plate; %K processing; %K registration; %K resolution; %K spline %K splines %K thin %K vision; %X Image registration is an important problem in image processing and computer vision. Much recent work in image registration is on matching non-rigid deformations. Thin plate splines are an effective image registration method when the deformation between two images can be modeled as the bending of a thin metal plate on point constraints such that the topology is preserved (non-rigid deformation). However, because evaluating the computed TPS model at all the image pixels is computationally expensive, we need to speed it up. We introduce the use of multi-level fast muitipole method (MLFMM) for this purpose. Our contribution lies in the presentation of a clear and concise MLFMM framework for TPS, which will be useful for future application developments. The achieved speedup using MLFMM is an improvement from O(N2) to O(N log N). We show that the fast evaluation outperforms the brute force method while maintaining acceptable error bound. %B Image Processing, 2004. ICIP '04. 2004 International Conference on %V 3 %P 1683 - 1686 Vol. 3 - 1683 - 1686 Vol. 3 %8 2004/10// %G eng %R 10.1109/ICIP.2004.1421395 %0 Book Section %B Mathematical Foundations of Computer Science 2004Mathematical Foundations of Computer Science 2004 %D 2004 %T PRAM-On-Chip: A Quest for Not-So-Obvious Non-obviousness %A Vishkin, Uzi %E Fiala,Jirí %E Koubek,Václav %E Kratochvíl,Jan %K Computer %K Science %X Consider situations where once you were told about a new technical idea you reacted by saying: “but this is so obvious, I wonder how I missed it”. I found out recently that the US patent law has a nice formal way of characterizing such a situation. The US patent law protects inventions that meet three requirements: utility, novelty and non-obviousness. Non-obviousness is considered the most challenging of the three to establish. The talk will try to argue that a possible virtue for a technical contribution is when, in restrospect, its non-obviousness is not too obvious; and since hindsight is always 20/20, one may often need to resort to various types of circumstantial evidence in order to establish non-obviousness. There are two reasons for bringing this issue up in my talk: (i) seeking such a virtue has been an objective of my work over the years, and (ii) issues of taste in research are more legitimate for invited talks; there might be merit in reminding younger researchers that not every “result” is necessarily also a “contribution”; perhaps the criterion of not-so-obvious non-obviousness could be helpful in some cases to help recognize a contribution. The focus of the second focal point for my talk, the PRAM-On-Chip approach, meets at least one of the standard legal ways to support non-obviousness: “Expressions of disbelief by experts constitute strong evidence of non-obviousness”. It is well documented that the whole PRAM algorithmic theory was considered “unrealistic” by numerous experts in the field, prior to the PRAM-On-Chip project. In fact, I needed recently to use this documentation in a reply to the U.S. patent office. An introduction of the PRAM-On-Chip approach follows. Many parallel computer systems architectures have been proposed and built over the last several decades. The outreach of the few that survived has been severely limited due to their programmability problems. The question of how to think algorithmically in parallel has been the fundamental problem for which these architectures did not have an adequate answer. A computational model, the Parallel Random Access Model (PRAM), has been developed by numerous (theoretical computer science) algorithm researchers to address this question during the 1980s and 1990s and is considered by many as the easiest known approach to parallel programming. Despite the broad interest the PRAM generated, it had not been possible to build parallel machines that adequately support it using multi-chip multiprocessors, the only multiprocessors that were buildable in the 1990s since low-overhead coordination was not possible. Our main insight is that this is becoming possible with the increasing amounts of hardware that can be placed on a single chip. From the PRAM, as a starting point, a highly parallel explicit multi-threaded (XMT) on-chip processor architecture that relies on new low-overhead coordination mechanisms and whose performance objective is reducing single task completion time has been conceived and developed. Simulated program executions have shown dramatic performance gains over conventional processor architectures. Namely, in addition to the unique parallel programmability features, which set XMT apart from any other current approach, XMT also provides very competitive performance. If XMT will meet expectations, its introduction would greatly enhance the normal rate of improvement of conventional processor architectures leading to new applications. %B Mathematical Foundations of Computer Science 2004Mathematical Foundations of Computer Science 2004 %S Lecture Notes in Computer Science %I Springer Berlin / Heidelberg %V 3153 %P 104 - 105 %8 2004/// %@ 978-3-540-22823-3 %G eng %U http://dx.doi.org/10.1007/978-3-540-28629-5_5 %0 Conference Paper %B Mixed and Augmented Reality, 2004. ISMAR 2004. Third IEEE and ACM International Symposium on %D 2004 %T Recording and reproducing high order surround auditory scenes for mixed and augmented reality %A Zhiyun Li %A Duraiswami, Ramani %A Davis, Larry S. %K array; %K audio %K auditory %K augmented %K Computer %K graphics; %K high %K loudspeaker %K microphone %K mixed %K order %K processing; %K reality %K reality; %K scene; %K signal %K surround %K system; %K technology; %K virtual %K VISION %K vision; %X Virtual reality systems are largely based on computer graphics and vision technologies. However, sound also plays an important role in human's interaction with the surrounding environment, especially for the visually impaired people. In this paper, we develop the theory of recording and reproducing real-world surround auditory scenes in high orders using specially designed microphone and loudspeaker arrays. It is complementary to vision-based technologies in creating mixed and augmented realities. Design examples and simulations are presented. %B Mixed and Augmented Reality, 2004. ISMAR 2004. Third IEEE and ACM International Symposium on %P 240 - 249 %8 2004/11// %G eng %R 10.1109/ISMAR.2004.51 %0 Conference Paper %B Computer Vision and Pattern Recognition, 2004. CVPR 2004. Proceedings of the 2004 IEEE Computer Society Conference on %D 2004 %T Role of shape and kinematics in human movement analysis %A Veeraraghavan,A. %A Chowdhury, A.R. %A Chellapa, Rama %K activity %K algorithm; %K algorithms; %K analysis; %K autoregressive %K average %K based %K classification; %K community; %K Computer %K definition; %K dynamical %K extraction; %K feature %K Gait %K hidden %K human %K identification %K image %K Kendall %K linear %K manifold; %K Markov %K modeling; %K models; %K MOTION %K Movement %K moving %K processes; %K recognition %K sequences; %K SHAPE %K spherical %K system; %K VISION %K vision; %X Human gait and activity analysis from video is presently attracting a lot of attention in the computer vision community. In this paper we analyze the role of two of the most important cues in human motion-shape and kinematics. We present an experimental framework whereby it is possible to evaluate the relative importance of these two cues in computer vision based recognition algorithms. In the process, we propose a new gait recognition algorithm by computing the distance between two sequences of shapes that lie on a spherical manifold. In our experiments, shape is represented using Kendall's definition of shape. Kinematics is represented using a Linear Dynamical system We place particular emphasis on human gait. Our conclusions show that shape plays a role which is more significant than kinematics in current automated gait based human identification algorithms. As a natural extension we study the role of shape and kinematics in activity recognition. Our experiments indicate that we require models that contain both shape and kinematics in order to perform accurate activity classification. These conclusions also allow us to explain the relative performance of many existing methods in computer-based human activity modeling. %B Computer Vision and Pattern Recognition, 2004. CVPR 2004. Proceedings of the 2004 IEEE Computer Society Conference on %V 1 %P I-730 - I-737 Vol.1 - I-730 - I-737 Vol.1 %8 2004/07/02/june %G eng %R 10.1109/CVPR.2004.1315104 %0 Book Section %B Trust ManagementTrust Management %D 2004 %T Using Trust in Recommender Systems: An Experimental Analysis %A Massa,Paolo %A Bhattacharjee, Bobby %E Jensen,Christian %E Poslad,Stefan %E Dimitrakos,Theo %K Computer %K Science %X Recommender systems (RS) have been used for suggesting items (movies, books, songs, etc.) that users might like. RSs compute a user similarity between users and use it as a weight for the users’ ratings. However they have many weaknesses, such as sparseness, cold start and vulnerability to attacks. We assert that these weaknesses can be alleviated using a Trust-aware system that takes into account the “web of trust” provided by every user. Specifically, we analyze data from the popular Internet web site epinions.com . The dataset consists of 49290 users who expressed reviews (with rating) on items and explicitly specified their web of trust, i.e. users whose reviews they have consistently found to be valuable. We show that any two users have usually few items rated in common. For this reason, the classic RS technique is often ineffective and is not able to compute a user similarity weight for many of the users. Instead exploiting the webs of trust, it is possible to propagate trust and infer an additional weight for other users. We show how this quantity can be computed against a larger number of users. %B Trust ManagementTrust Management %S Lecture Notes in Computer Science %I Springer Berlin / Heidelberg %V 2995 %P 221 - 235 %8 2004/// %@ 978-3-540-21312-3 %G eng %U http://dx.doi.org/10.1007/978-3-540-24747-0_17 %0 Journal Article %J Multimedia, IEEE Transactions on %D 2004 %T Wide baseline image registration with application to 3-D face modeling %A Roy-Chowdhury, A.K. %A Chellapa, Rama %A Keaton, T. %K 2D %K 3D %K algorithm; %K baseline %K biometrics; %K Computer %K configuration; %K correspondence %K doubly %K error %K extraction; %K Face %K feature %K holistic %K image %K matching; %K matrix; %K minimization; %K modeling; %K models; %K normalization %K probability %K probability; %K procedure; %K processes; %K processing; %K recognition; %K registration; %K representation; %K sequences; %K shapes; %K Sinkhorn %K spatial %K statistics; %K Stochastic %K video %K vision; %K wide %X Establishing correspondence between features in two images of the same scene taken from different viewing angles is a challenging problem in image processing and computer vision. However, its solution is an important step in many applications like wide baseline stereo, three-dimensional (3-D) model alignment, creation of panoramic views, etc. In this paper, we propose a technique for registration of two images of a face obtained from different viewing angles. We show that prior information about the general characteristics of a face obtained from video sequences of different faces can be used to design a robust correspondence algorithm. The method works by matching two-dimensional (2-D) shapes of the different features of the face (e.g., eyes, nose etc.). A doubly stochastic matrix, representing the probability of match between the features, is derived using the Sinkhorn normalization procedure. The final correspondence is obtained by minimizing the probability of error of a match between the entire constellation of features in the two sets, thus taking into account the global spatial configuration of the features. The method is applied for creating holistic 3-D models of a face from partial representations. Although this paper focuses primarily on faces, the algorithm can also be used for other objects with small modifications. %B Multimedia, IEEE Transactions on %V 6 %P 423 - 434 %8 2004/06// %@ 1520-9210 %G eng %N 3 %R 10.1109/TMM.2004.827511 %0 Conference Paper %B Computer Vision and Pattern Recognition, 2003. Proceedings. 2003 IEEE Computer Society Conference on %D 2003 %T Activity recognition using the dynamics of the configuration of interacting objects %A Vaswani, N. %A RoyChowdhury, A. %A Chellapa, Rama %K 2D %K abnormal %K abnormality %K abnormality; %K acoustic %K activity %K analysis; %K change; %K Computer %K configuration %K configuration; %K data; %K DETECTION %K detection; %K distribution; %K drastic %K dynamics; %K event; %K filter; %K hand-picked %K image %K infrared %K interacting %K learning; %K location %K low %K mean %K model; %K monitoring; %K MOTION %K moving %K noise; %K noisy %K object %K object; %K observation %K observation; %K particle %K pattern %K plane; %K point %K polygonal %K probability %K probability; %K problem; %K processing; %K radar %K recognition; %K resolution %K sensor; %K sensors; %K sequence; %K SHAPE %K shape; %K signal %K slow %K statistic; %K strategy; %K Surveillance %K surveillance; %K target %K test %K tracking; %K video %K video; %K visible %K vision; %X Monitoring activities using video data is an important surveillance problem. A special scenario is to learn the pattern of normal activities and detect abnormal events from a very low resolution video where the moving objects are small enough to be modeled as point objects in a 2D plane. Instead of tracking each point separately, we propose to model an activity by the polygonal 'shape' of the configuration of these point masses at any time t, and its deformation over time. We learn the mean shape and the dynamics of the shape change using hand-picked location data (no observation noise) and define an abnormality detection statistic for the simple case of a test sequence with negligible observation noise. For the more practical case where observation (point locations) noise is large and cannot be ignored, we use a particle filter to estimate the probability distribution of the shape given the noisy observations up to the current time. Abnormality detection in this case is formulated as a change detection problem. We propose a detection strategy that can detect both 'drastic' and 'slow' abnormalities. Our framework can be directly applied for object location data obtained using any type of sensors - visible, radar, infrared or acoustic. %B Computer Vision and Pattern Recognition, 2003. Proceedings. 2003 IEEE Computer Society Conference on %V 2 %P II - 633-40 vol.2 - II - 633-40 vol.2 %8 2003/06// %G eng %R 10.1109/CVPR.2003.1211526 %0 Journal Article %J Theory of Computing Systems %D 2003 %T Deterministic Resource Discovery in Distributed Networks %A Kutten,Shay %A Peleg,David %A Vishkin, Uzi %K Computer %K Science %X The resource discovery problem was introduced by Harchol-Balter, Leighton, and Lewin. They developed a number of algorithms for the problem in the weakly connected directed graph model. This model is a directed logical graph that represents the vertices’ knowledge about the topology of the underlying communication network. The current paper proposes a deterministic algorithm for the problem in the same model, with improved time, message, and communication complexities. Each previous algorithm had a complexity that was higher at least in one of the measures. Specifically, previous deterministic solutions required either time linear in the diameter of the initial network, or communication complexity $O(n^3)$ (with message complexity $O(n^2)$), or message complexity $O(|E_0| łog n)$ (where $E_0$ is the arc set of the initial graph $G_0$). Compared with the main randomized algorithm of Harchol-Balter, Leighton, and Lewin, the time complexity is reduced from $O(łog^2n)$ to\pagebreak[4] $O(łog n )$, the message complexity from $O(n łog^2 n)$ to $O(n łog n )$, and the communication complexity from $O(n^2 łog^3 n)$ to $O(|E_0|łog ^2 n )$. \par Our work significantly extends the connectivity algorithm of Shiloach and Vishkin which was originally given for a parallel model of computation. Our result also confirms a conjecture of Harchol-Balter, Leighton, and Lewin, and addresses an open question due to Lipton. %B Theory of Computing Systems %V 36 %P 479 - 495 %8 2003/// %@ 1432-4350 %G eng %U http://dx.doi.org/10.1007/s00224-003-1084-8 %N 5 %0 Journal Article %J Pattern Analysis and Machine Intelligence, IEEE Transactions on %D 2003 %T Efficient kernel density estimation using the fast gauss transform with applications to color modeling and tracking %A Elgammal,A. %A Duraiswami, Ramani %A Davis, Larry S. %K algorithms; %K Color %K Computer %K density %K estimation; %K fast %K function; %K Gauss %K image %K Kernel %K modeling; %K segmentation; %K tracking; %K transform; %K transforms; %K VISION %K vision; %X Many vision algorithms depend on the estimation of a probability density function from observations. Kernel density estimation techniques are quite general and powerful methods for this problem, but have a significant disadvantage in that they are computationally intensive. In this paper, we explore the use of kernel density estimation with the fast Gauss transform (FGT) for problems in vision. The FGT allows the summation of a mixture of ill Gaussians at N evaluation points in O(M+N) time, as opposed to O(MN) time for a naive evaluation and can be used to considerably speed up kernel density estimation. We present applications of the technique to problems from image segmentation and tracking and show that the algorithm allows application of advanced statistical techniques to solve practical vision problems in real-time with today's computers. %B Pattern Analysis and Machine Intelligence, IEEE Transactions on %V 25 %P 1499 - 1504 %8 2003/11// %@ 0162-8828 %G eng %N 11 %R 10.1109/TPAMI.2003.1240123 %0 Conference Paper %B Computer Vision and Pattern Recognition, 2003. Proceedings. 2003 IEEE Computer Society Conference on %D 2003 %T Learning dynamics for exemplar-based gesture recognition %A Elgammal,A. %A Shet,V. %A Yacoob,Yaser %A Davis, Larry S. %K arbitrary %K body %K by %K Computer %K constraint; %K detection; %K discrete %K distribution %K dynamics; %K edge %K estimation; %K example; %K exemplar %K exemplar-based %K extraction; %K feature %K framework; %K gesture %K gesture; %K hidden %K HMM; %K human %K image %K learning %K Markov %K matching; %K model; %K models; %K motion; %K nonparametric %K pose %K probabilistic %K recognition; %K sequence; %K space; %K state; %K statistics; %K system %K temporal %K tool; %K view-based %K vision; %X This paper addresses the problem of capturing the dynamics for exemplar-based recognition systems. Traditional HMM provides a probabilistic tool to capture system dynamics and in exemplar paradigm, HMM states are typically coupled with the exemplars. Alternatively, we propose a non-parametric HMM approach that uses a discrete HMM with arbitrary states (decoupled from exemplars) to capture the dynamics over a large exemplar space where a nonparametric estimation approach is used to model the exemplar distribution. This reduces the need for lengthy and non-optimal training of the HMM observation model. We used the proposed approach for view-based recognition of gestures. The approach is based on representing each gesture as a sequence of learned body poses (exemplars). The gestures are recognized through a probabilistic framework for matching these body poses and for imposing temporal constraints between different poses using the proposed non-parametric HMM. %B Computer Vision and Pattern Recognition, 2003. Proceedings. 2003 IEEE Computer Society Conference on %V 1 %P I-571 - I-578 vol.1 - I-571 - I-578 vol.1 %8 2003/06// %G eng %R 10.1109/CVPR.2003.1211405 %0 Conference Paper %B Intelligent Vehicles Symposium, 2003. Proceedings. IEEE %D 2003 %T Modelling pedestrian shapes for outlier detection: a neural net based approach %A Nanda,H. %A Benabdelkedar,C. %A Davis, Larry S. %K (artificial %K complex %K Computer %K computing; %K custom %K design; %K detection; %K engineering %K intelligence); %K layer %K learning %K method; %K modelling; %K net; %K nets; %K neural %K object %K outlier %K pedestrian %K pedestrians %K rate; %K recognition %K recognition; %K SHAPE %K shapes; %K traffic %K two %K vision; %X In this paper we present an example-based approach to learn a given class of complex shapes, and recognize instances of that shape with outliers. The system consists of a two-layer custom-designed neural network. We apply this approach to the recognition of pedestrians carrying objects from a single camera. The system is able to capture and model an ample range of pedestrian shapes at varying poses and camera orientations, and achieves a 90% correct recognition rate. %B Intelligent Vehicles Symposium, 2003. Proceedings. IEEE %P 428 - 433 %8 2003/06// %G eng %R 10.1109/IVS.2003.1212949 %0 Conference Paper %B Computer Vision and Pattern Recognition, 2003. Proceedings. 2003 IEEE Computer Society Conference on %D 2003 %T Probabilistic tracking in joint feature-spatial spaces %A Elgammal,A. %A Duraiswami, Ramani %A Davis, Larry S. %K analysis; %K appearance %K appearance; %K color; %K colour %K Computer %K constraint; %K deformation; %K detection; %K distribution; %K edge %K estimation; %K extraction; %K feature %K feature-spatial %K feature; %K function %K gradient; %K image %K intensity; %K joint %K likelihood %K local %K maximization; %K maximum %K nonparametric %K object %K objective %K occlusion; %K optical %K partial %K probabilistic %K probability; %K region %K representation; %K row %K similarity-based %K small %K space; %K structure; %K target %K tracker; %K tracking; %K transformation %K vision; %X In this paper, we present a probabilistic framework for tracking regions based on their appearance. We exploit the feature-spatial distribution of a region representing an object as a probabilistic constraint to track that region over time. The tracking is achieved by maximizing a similarity-based objective function over transformation space given a nonparametric representation of the joint feature-spatial distribution. Such a representation imposes a probabilistic constraint on the region feature distribution coupled with the region structure, which yields an appearance tracker that is robust to small local deformations and partial occlusion. We present the approach for the general form of joint feature-spatial distributions and apply it to tracking with different types of image features including row intensity, color and image gradient. %B Computer Vision and Pattern Recognition, 2003. Proceedings. 2003 IEEE Computer Society Conference on %V 1 %P I-781 - I-788 vol.1 - I-781 - I-788 vol.1 %8 2003/06// %G eng %R 10.1109/CVPR.2003.1211432 %0 Conference Paper %B Computer Vision and Pattern Recognition, 2003. Proceedings. 2003 IEEE Computer Society Conference on %D 2003 %T Simultaneous pose and correspondence determination using line features %A David,P. %A DeMenthon,D. %A Duraiswami, Ramani %A Samet, Hanan %K algorithm; %K algorithms; %K annealing; %K clutter; %K cluttered %K Computer %K correspondence %K detection; %K determination; %K deterministic %K environment; %K extraction; %K feature %K feature; %K image %K image; %K imagery; %K images; %K joint %K line %K local %K man-made %K MATCHING %K matching; %K measurement; %K model-to-image %K noise; %K occlusion; %K optimum; %K perspective %K point %K pose %K position %K problem; %K processing; %K real %K realistic %K registration %K simulated %K softassign; %K SoftPOSIT %K stereo %K synthetic %K vision; %X We present a new robust line matching algorithm for solving the model-to-image registration problem. Given a model consisting of 3D lines and a cluttered perspective image of this model, the algorithm simultaneously estimates the pose of the model and the correspondences of model lines to image lines. The algorithm combines softassign for determining correspondences and POSIT for determining pose. Integrating these algorithms into a deterministic annealing procedure allows the correspondence and pose to evolve from initially uncertain values to a joint local optimum. This research extends to line features the SoftPOSIT algorithm proposed recently for point features. Lines detected in images are typically more stable than points and are less likely to be produced by clutter and noise, especially in man-made environments. Experiments on synthetic and real imagery with high levels of clutter, occlusion, and noise demonstrate the robustness of the algorithm. %B Computer Vision and Pattern Recognition, 2003. Proceedings. 2003 IEEE Computer Society Conference on %V 2 %P II-424 - II-431 vol.2 - II-424 - II-431 vol.2 %8 2003/06// %G eng %R 10.1109/CVPR.2003.1211499 %0 Conference Paper %B Multimedia and Expo, 2002. ICME '02. Proceedings. 2002 IEEE International Conference on %D 2002 %T 3D face reconstruction from video using a generic model %A Chowdhury, A.R. %A Chellapa, Rama %A Krishnamurthy, S. %A Vo, T. %K 3D %K algorithm; %K algorithms; %K analysis; %K Carlo %K chain %K Computer %K Face %K from %K function; %K generic %K human %K image %K Markov %K MCMC %K methods; %K model; %K Monte %K MOTION %K optimisation; %K OPTIMIZATION %K processes; %K processing; %K recognition; %K reconstruction %K reconstruction; %K sampling; %K sequence; %K sequences; %K SfM %K signal %K structure %K surveillance; %K video %K vision; %X Reconstructing a 3D model of a human face from a video sequence is an important problem in computer vision, with applications to recognition, surveillance, multimedia etc. However, the quality of 3D reconstructions using structure from motion (SfM) algorithms is often not satisfactory. One common method of overcoming this problem is to use a generic model of a face. Existing work using this approach initializes the reconstruction algorithm with this generic model. The problem with this approach is that the algorithm can converge to a solution very close to this initial value, resulting in a reconstruction which resembles the generic model rather than the particular face in the video which needs to be modeled. We propose a method of 3D reconstruction of a human face from video in which the 3D reconstruction algorithm and the generic model are handled separately. A 3D estimate is obtained purely from the video sequence using SfM algorithms without use of the generic model. The final 3D model is obtained after combining the SfM estimate and the generic model using an energy function that corrects for the errors in the estimate by comparing local regions in the two models. The optimization is done using a Markov chain Monte Carlo (MCMC) sampling strategy. The main advantage of our algorithm over others is that it is able to retain the specific features of the face in the video sequence even when these features are different from those of the generic model. The evolution of the 3D model through the various stages of the algorithm is presented. %B Multimedia and Expo, 2002. ICME '02. Proceedings. 2002 IEEE International Conference on %V 1 %P 449 - 452 vol.1 - 449 - 452 vol.1 %8 2002/// %G eng %R 10.1109/ICME.2002.1035815 %0 Book Section %B Computational Logic: Logic Programming and BeyondComputational Logic: Logic Programming and Beyond %D 2002 %T Error-Tolerant Agents %A Eiter,Thomas %A Mascardi,Viviana %A Subrahmanian,V. %E Kakas,Antonis %E Sadri,Fariba %K Computer %K Science %X The use of agents in today’s Internet world is expanding rapidly. Yet, agent developers proceed largely under the optimistic assumption that agents will be error-free. Errors may arise in agents for numerous reasons — agents may share a workspace with other agents or humans and updates made by these other entities may cause an agent to face a situation that it was not explicitly programmed to deal with. Likewise, errors in coding agents may lead to inconsistent situations where it is unclear how the agent should act. In this paper, we define an agent execution model that allows agents to continue acting “reasonably” even when some errors of the above types occur. More importantly, in our framework, agents take “repair” actions automatically when confronted with such situations, but while taking such repair actions, they can often continue to engage in work and/or interactions with other agents that are unaffected by repairs. %B Computational Logic: Logic Programming and BeyondComputational Logic: Logic Programming and Beyond %S Lecture Notes in Computer Science %I Springer Berlin / Heidelberg %V 2407 %P 83 - 104 %8 2002/// %@ 978-3-540-43959-2 %G eng %U http://dx.doi.org/10.1007/3-540-45628-7_22 %0 Conference Paper %B Information Visualization, 2002. INFOVIS 2002. IEEE Symposium on %D 2002 %T Interactive information visualization of a million items %A Fekete,J.-D. %A Plaisant, Catherine %K animation %K animation; %K cards; %K Computer %K count; %K data %K diagrams; %K Graphics %K hardware-based %K information %K interactive %K interpolation; %K overlap %K plot %K scatter %K stereovision; %K systems; %K techniques; %K treemaps; %K visualisation; %K visualization; %X Existing information visualization techniques are usually limited to the display of a few thousand items. This article describes new interactive techniques capable of handling a million items (effectively visible and manageable on screen). We evaluate the use of hardware-based techniques available with newer graphics cards, as well as new animation techniques and non-standard graphical features such as stereovision and overlap count. These techniques have been applied to two popular information visualizations: treemaps and scatter plot diagrams; but are generic enough to be applied to other 2D representations as well. %B Information Visualization, 2002. INFOVIS 2002. IEEE Symposium on %P 117 - 124 %8 2002/// %G eng %R 10.1109/INFVIS.2002.1173156 %0 Journal Article %J Knowledge and Data Engineering, IEEE Transactions on %D 2002 %T Presentation planning for distributed VoD systems %A Hwang,Eenjun %A Prabhakaran,B. %A V.S. Subrahmanian %K Computer %K computing; %K databases; %K demand; %K distributed %K local %K multimedia %K network; %K on %K optimal %K plan; %K plans; %K presentation %K presentation; %K server; %K servers; %K video %K video-on-demand; %K VoD; %X A distributed video-on-demand (VoD) system is one where a collection of video data is located at dispersed sites across a computer network. In a single site environment, a local video server retrieves video data from its local storage device. However, in distributed VoD systems, when a customer requests a movie from the local server, the server may need to interact with other servers located across the network. In this paper, we present different types of presentation plans that a local server can construct in order to satisfy a customer request. Informally speaking, a presentation plan is a temporally synchronized sequence of steps that the local server must perform in order to present the requested movie to the customer. This involves obtaining commitments from other video servers, obtaining commitments from the network service provider, as well as making commitments of local resources, while keeping within the limitations of available bandwidth, available buffer, and customer data consumption rates. Furthermore, in order to evaluate the quality of a presentation plan, we introduce two measures of optimality for presentation plans: minimizing wait time for a customer and minimizing access bandwidth which, informally speaking, specifies how much network/disk bandwidth is used. We develop algorithms to compute three different optimal presentation plans that work at a block level, or at a segment level, or with a hybrid mix of the two, and compare their performance through simulation experiments. We have also mathematically proven effects of increased buffer or bandwidth and data replications for presentation plans which had previously been verified experimentally in the literature. %B Knowledge and Data Engineering, IEEE Transactions on %V 14 %P 1059 - 1077 %8 2002/10//sep %@ 1041-4347 %G eng %N 5 %R 10.1109/TKDE.2002.1033774 %0 Conference Paper %B Software Metrics, 2002. Proceedings. Eighth IEEE Symposium on %D 2002 %T What we have learned about fighting defects %A Shull, F. %A Basili, Victor R. %A Boehm,B. %A Brown,A. W %A Costa,P. %A Lindvall,M. %A Port,D. %A Rus,I. %A Tesoriero,R. %A Zelkowitz, Marvin V %K based %K Center %K Computer %K defect %K development; %K education; %K electronic %K Empiric %K engineering %K engineering; %K eWorkshops; %K for %K heuristics; %K reduction; %K Science %K software %K workshops; %X The Center for Empirically Based Software Engineering helps improve software development by providing guidelines for selecting development techniques, recommending areas for further research, and supporting software engineering education. A central activity toward achieving this goal has been the running of "e- Workshops" that capture expert knowledge with a minimum of overhead effort to formulate heuristics on a particular topic. The resulting heuristics are a useful summary of the current state of knowledge in an area based on expert opinion. This paper discusses the results to date of a series of e-Workshops on software defect reduction. The original discussion items are presented along with an encapsulated summary of the expert discussion. The reformulated heuristics can be useful both to researchers (for pointing out gaps in the current state of the knowledge requiring further investigation) and to practitioners (for benchmarking or setting expectations about development practices). %B Software Metrics, 2002. Proceedings. Eighth IEEE Symposium on %P 249 - 258 %8 2002/// %G eng %R 10.1109/METRIC.2002.1011343 %0 Conference Paper %B Multimedia Signal Processing, 2002 IEEE Workshop on %D 2002 %T Wide baseline image registration using prior information %A Chowdhury, AM %A Chellapa, Rama %A Keaton, T. %K 2D %K 3D %K algorithm; %K alignment; %K angles; %K baseline %K Computer %K configuration; %K constellation; %K correspondence %K creation; %K doubly %K error %K extraction; %K Face %K feature %K global %K holistic %K image %K images; %K matching; %K matrix; %K model %K models; %K normalization %K panoramic %K probability; %K procedure; %K processes; %K processing; %K registration; %K robust %K sequences; %K SHAPE %K signal %K Sinkhorn %K spatial %K statistics; %K stereo; %K Stochastic %K video %K view %K viewing %K vision; %K wide %X Establishing correspondence between features in two images of the same scene taken from different viewing angles in a challenging problem in image processing and computer vision. However, its solution is an important step in many applications like wide baseline stereo, 3D model alignment, creation of panoramic views etc. In this paper, we propose a technique for registration of two images of a face obtained from different viewing angles. We show that prior information about the general characteristics of a face obtained from video sequences of different faces can be used to design a robust correspondence algorithm. The method works by matching 2D shapes of the different features of the face. A doubly stochastic matrix, representing the probability of match between the features, is derived using the Sinkhorn normalization procedure. The final correspondence is obtained by minimizing the probability of error of a match between the entire constellations of features in the two sets, thus taking into account the global spatial configuration of the features. The method is applied for creating holistic 3D models of a face from partial representations. Although this paper focuses primarily on faces, the algorithm can also be used for other objects with small modifications. %B Multimedia Signal Processing, 2002 IEEE Workshop on %P 37 - 40 %8 2002/12// %G eng %R 10.1109/MMSP.2002.1203242 %0 Journal Article %J Empirical Software Engineering %D 1996 %T The empirical investigation of Perspective-Based Reading %A Basili, Victor R. %A Green,Scott %A Laitenberger,Oliver %A Lanubile,Filippo %A Shull, Forrest %A Sørumgård,Sivert %A Zelkowitz, Marvin V %K Computer %K Science %X We consider reading techniques a fundamental means of achieving high quality software. Due to the lack of research in this area, we are experimenting with the application and comparison of various reading techniques. This paper deals with our experiences with a family of reading techniques known as Perspective-Based Reading (PBR), and its application to requirements documents. The goal of PBR is to provide operational scenarios where members of a review team read a document from a particular perspective, e.g., tester, developer, user. Our assumption is that the combination of different perspectives provides better coverage of the document, i.e., uncovers a wider range of defects, than the same number of readers using their usual technique. %B Empirical Software Engineering %V 1 %P 133 - 164 %8 1996/// %@ 1382-3256 %G eng %U http://dx.doi.org/10.1007/BF00368702 %N 2 %0 Conference Paper %B Computer Vision, 1995. Proceedings., Fifth International Conference on %D 1995 %T Stochastic completion fields: a neural model of illusory contour shape and salience %A Williams,L. R %A Jacobs, David W. %K boundary %K completion %K computational %K Computer %K contour %K contours; %K convolutions; %K cortex; %K curves %K detection; %K distribution; %K edge %K energy; %K estimation; %K fields; %K fragments; %K geometry; %K illusory %K image %K lattice; %K least %K likelihood %K mammalian %K maximum %K model; %K nets; %K neural %K of %K paths; %K plane; %K probability %K probability; %K random %K recognition; %K shape; %K stimuli; %K Stochastic %K vector-field %K visual %K walk; %X We describe an algorithm and representation level theory of illusory contour shape and salience. Unlike previous theories, our model is derived from a single assumption-namely, that the prior probability distribution of boundary completion shape can be modeled by a random walk in a lattice whose points are positions and orientations in the image plane (i.e. the space which one can reasonably assume is represented by neurons of the mammalian visual cortex). Our model does not employ numerical relaxation or other explicit minimization, but instead relies on the fact that the probability that a particle following a random walk will pass through a given position and orientation on a path joining two boundary fragments can be computed directly as the product of two vector-field convolutions. We show that for the random walk we define, the maximum likelihood paths are curves of least energy, that is, on average, random walks follow paths commonly assumed to model the shape of illusory contours. A computer model is demonstrated on numerous illusory contour stimuli from the literature %B Computer Vision, 1995. Proceedings., Fifth International Conference on %P 408 - 415 %8 1995/06// %G eng %R 10.1109/ICCV.1995.466910 %0 Book Section %B Algorithms and ComplexityAlgorithms and Complexity %D 1994 %T On a parallel-algorithms method for string matching problems (overview) %A Sahinalp,Suleyman %A Vishkin, Uzi %E Bonuccelli,M. %E Crescenzi,P. %E Petreschi,R. %K Computer %K Science %B Algorithms and ComplexityAlgorithms and Complexity %S Lecture Notes in Computer Science %I Springer Berlin / Heidelberg %V 778 %P 22 - 32 %8 1994/// %@ 978-3-540-57811-6 %G eng %U http://dx.doi.org/10.1007/3-540-57811-0_3 %0 Journal Article %J Computers, IEEE Transactions on %D 1991 %T VLSI architectures for multidimensional transforms %A Chakrabarti,C. %A JaJa, Joseph F. %K architecture; %K architectures; %K arithmetic; %K complexity; %K computational %K Computer %K digital %K fixed-precision %K linear %K multidimensional %K separable %K transforms; %K VLSI %X The authors propose a family of VLSI architectures with area-time tradeoffs for computing (N times;N times; . . . times;N) d-dimensional linear separable transforms. For fixed-precision arithmetic with b bits, the architectures have an area A=O(Nd+2a) and computation time T=O(dNd/2-ab ), and achieve the AT2 bound of AT2=O(n2b 2) for constant d, where n=Nd and O lt;a les;d/2 %B Computers, IEEE Transactions on %V 40 %P 1053 - 1057 %8 1991/09// %@ 0018-9340 %G eng %N 9 %R 10.1109/12.83648