Results 1  10
of
15,158
Actions as spacetime shapes
 In ICCV
, 2005
"... Human action in video sequences can be seen as silhouettes of a moving torso and protruding limbs undergoing articulated motion. We regard human actions as threedimensional shapes induced by the silhouettes in the spacetime volume. We adopt a recent approach [14] for analyzing 2D shapes and genera ..."
Abstract

Cited by 642 (4 self)
 Add to MetaCart
Human action in video sequences can be seen as silhouettes of a moving torso and protruding limbs undergoing articulated motion. We regard human actions as threedimensional shapes induced by the silhouettes in the spacetime volume. We adopt a recent approach [14] for analyzing 2D shapes and generalize it to deal with volumetric spacetime action shapes. Our method utilizes properties of the solution to the Poisson equation to extract spacetime features such as local spacetime saliency, action dynamics, shape structure and orientation. We show that these features are useful for action recognition, detection and clustering. The method is fast, does not require video alignment and is applicable in (but not limited to) many scenarios where the background is known. Moreover, we demonstrate the robustness of our method to partial occlusions, nonrigid deformations, significant changes in scale and viewpoint, high irregularities in the performance of an action, and low quality video. Index Terms Action representation, action recognition, spacetime analysis, shape analysis, poisson equation
Graphical models, exponential families, and variational inference
, 2008
"... The formalism of probabilistic graphical models provides a unifying framework for capturing complex dependencies among random variables, and building largescale multivariate statistical models. Graphical models have become a focus of research in many statistical, computational and mathematical fiel ..."
Abstract

Cited by 800 (26 self)
 Add to MetaCart
The formalism of probabilistic graphical models provides a unifying framework for capturing complex dependencies among random variables, and building largescale multivariate statistical models. Graphical models have become a focus of research in many statistical, computational and mathematical fields, including bioinformatics, communication theory, statistical physics, combinatorial optimization, signal and image processing, information retrieval and statistical machine learning. Many problems that arise in specific instances — including the key problems of computing marginals and modes of probability distributions — are best studied in the general setting. Working with exponential family representations, and exploiting the conjugate duality between the cumulant function and the entropy for exponential families, we develop general variational representations of the problems of computing likelihoods, marginal probabilities and most probable configurations. We describe how a wide varietyof algorithms — among them sumproduct, cluster variational methods, expectationpropagation, mean field methods, maxproduct and linear programming relaxation, as well as conic programming relaxations — can all be understood in terms of exact or approximate forms of these variational representations. The variational approach provides a complementary alternative to Markov chain Monte Carlo as a general source of approximation methods for inference in largescale statistical models.
The STATEMATE Semantics of Statecharts
, 1996
"... This article describes the semantics of the language of statecharts as implenented in the STATEMATE system [Harel et al. 1990; Harel and Politi 1996]. The initial version of this semantics was developed by a team about.10 years ago. With the added experience of the users of the system it has since b ..."
Abstract

Cited by 651 (12 self)
 Add to MetaCart
This article describes the semantics of the language of statecharts as implenented in the STATEMATE system [Harel et al. 1990; Harel and Politi 1996]. The initial version of this semantics was developed by a team about.10 years ago. With the added experience of the users of the system it has since been extended and modified. This executable semantics has been in operation in driving the simulation, dynamic tests, and code generation tDols of STATEMATE since 1987, and a technical report describing it has been available from iLogix, Inc. since 1989. We have now decided to revise and publish the report so as to make it more widely accessible, to alleviate some of the confusion about the "official semantics of the language, and to counter a number of incorrect comments made in the literature about the way statecharts have been implemented. For example, the survey [yon der Beek 1994] does not mention the STATEMATE implementation of statecharts or the semantics adopted for it at all, although this semantics is different from the ones surveyed therein (and was developed earlier than all of them except for Harel et al. [1987]). As another example, Leveson et al. [1995] describe a case that exhibits an unacceptable kind of behavior in a statechart, which they say is what the "semantics of statecharts" leads to (pp. 695697). Unfortunately, they base their discussion of statechart semantics on one of the many semantics proposed by various authors (that of Pnueli and Shalev [1991]) and give the reader the impression that this is the official semantics of the language
KSVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation
, 2006
"... In recent years there has been a growing interest in the study of sparse representation of signals. Using an overcomplete dictionary that contains prototype signalatoms, signals are described by sparse linear combinations of these atoms. Applications that use sparse representation are many and inc ..."
Abstract

Cited by 930 (41 self)
 Add to MetaCart
In recent years there has been a growing interest in the study of sparse representation of signals. Using an overcomplete dictionary that contains prototype signalatoms, signals are described by sparse linear combinations of these atoms. Applications that use sparse representation are many and include compression, regularization in inverse problems, feature extraction, and more. Recent activity in this field has concentrated mainly on the study of pursuit algorithms that decompose signals with respect to a given dictionary. Designing dictionaries to better fit the above model can be done by either selecting one from a prespecified set of linear transforms or adapting the dictionary to a set of training signals. Both of these techniques have been considered, but this topic is largely still open. In this paper we propose a novel algorithm for adapting dictionaries in order to achieve sparse signal representations. Given a set of training signals, we seek the dictionary that leads to the best representation for each member in this set, under strict sparsity constraints. We present a new method—the KSVD algorithm—generalizing the umeans clustering process. KSVD is an iterative method that alternates between sparse coding of the examples based on the current dictionary and a process of updating the dictionary atoms to better fit the data. The update of the dictionary columns is combined with an update of the sparse representations, thereby accelerating convergence. The KSVD algorithm is flexible and can work with any pursuit method (e.g., basis pursuit, FOCUSS, or matching pursuit). We analyze this algorithm and demonstrate its results both on synthetic tests and in applications on real image data.
STATEMATE: A Working Environment for the Development of Complex Reactive Systems
 IEEE Transactions on Software Engineering
, 1990
"... This paper provides an overview of the STATEMATE system, constructed over the past several years by the authors and their colleagues at Ad Cad Ltd., the R&D subsidiary of iLogix, Inc. STATEMATE is a set of tools, with a heavy graphical orientation, in tended for the specification, analysis, d ..."
Abstract

Cited by 483 (7 self)
 Add to MetaCart
This paper provides an overview of the STATEMATE system, constructed over the past several years by the authors and their colleagues at Ad Cad Ltd., the R&D subsidiary of iLogix, Inc. STATEMATE is a set of tools, with a heavy graphical orientation, in tended for the specification, analysis, design, and documentation of large and complex reactive systems, such as realtime embedded sys tems, control and communication systems, and interactive software or hardware. It enables a user to prepare, analyze, and debug diagram matic, yet precise, descriptions of the system under development from three interrelated points of view, capturing structure, functionality, and behavior. These views are represented by three graphical languages, the most intricate of which is the language of statecharts [4], used to depict reactive behavior over time. In addition to the use of statecharts, the main novelty of STATEMATE is in the fact that it "understands " the entire descriptions perfectly, to the point of being able to analyze them for crucial dynamic properties, to carry out rigorous ex ecutions and simulations of the described system, and to create run ning code automatically. These features are invaluable when it comes to the quality and reliability of the final outcome.
Michal Gregu s
"... . In this paper we shall study some oscillatory and nonoscillatory properties of solutions of a nonlinear third order differential equation, using the results and methods of the linear differential equation of the third order. The aim of this paper is to study the oscillatory or nonoscillatory prope ..."
Abstract
 Add to MetaCart
. In this paper we shall study some oscillatory and nonoscillatory properties of solutions of a nonlinear third order differential equation, using the results and methods of the linear differential equation of the third order. The aim of this paper is to study the oscillatory or nonoscillatory properties of solutions of the nonlinear differential equation (1) u 000 + q(t)u 0 + p(t) h(u) = 0 where q 0 (t) and p(t) are continuous function of t 2 (a; 1), \Gamma1 ! a ! 1; h(u) is continuous function of u 2 (\Gamma1; 1) and (i) h(u)u ? 0 for u 6= 0, (ii) lim u!0 h(u) u = \Theta, 0 \Theta ! 1. In this paper, a solution of equation (1) we will understand a nontrivial solution of (1) defined on the interval [T; 1], T ? a. A nontrivial solution of (1) is said to be oscillatory if it has zeros for arbitrarily large values of (the independent variable) t. Otherwise a solution is called nonoscillatory. The object of generalization are the results of the paper [1] concerning oscillatory ...
Enterprise restructuring in transition: A quantitative survey, Washington: The World Bank (mimeographed
, 2000
"... NOTE: We will make final revisions to this paper in July 2000, at which time we will make reference to all pertinent papers that have come to our attention by June 30, 2000. If anyone reading this survey knows of a pertinent paper not presently included in the list of references, please send a copy ..."
Abstract

Cited by 359 (10 self)
 Add to MetaCart
NOTE: We will make final revisions to this paper in July 2000, at which time we will make reference to all pertinent papers that have come to our attention by June 30, 2000. If anyone reading this survey knows of a pertinent paper not presently included in the list of references, please send a copy or a reference to one of us. *Djankov is Financial Economist at the World Bank. Murrell is Professor of Economics and Chair of the Academic Council of the IRIS Center, University of Maryland. We would like to thank Judy Hellerstein, John McMillan, John Nellis, and Jan Svejnar for helpful advice and Wooyoung Kim and Tatiana Nenova for research assistance. This research was made possible through support provided by the World Bank and by the U.S. Agency for International Development under Cooperative Agreement No. DHR0015A00003100 to the Center for Institutional Reform and the Informal Sector (IRIS). The findings, interpretations, and conclusions expressed in this paper are entirely those of the authors. They do not necessarily represent the views of the IRIS Center, US AID, the World Bank, its Executive Directors, or the countries they represent. Enterprise Restructuring in Transition: A Quantitative Survey Abstract. There are now over 125 empirical papers that analyze the process of enterprise restructuring in transition
*Michal Maimaran is Visiting Assistant Professor, Marketing Depart
"... tian Wheeler for their comments and the two anonymous JMR reviewers for their constructive feedback. Dilip Soman served as associate editor for this article. Michal MaiMaran and itaMar SiMonSon* Studies of consumer decision making often begin with the identification of a dimension on which options d ..."
Abstract
 Add to MetaCart
tian Wheeler for their comments and the two anonymous JMR reviewers for their constructive feedback. Dilip Soman served as associate editor for this article. Michal MaiMaran and itaMar SiMonSon* Studies of consumer decision making often begin with the identification of a dimension on which options
Reducing Number of Decision Rules by Joining Michal Mikolajczyk
"... Abstract. Sets of decision rules induced from data can often be very large. Such sets of rules cannot be processed efficiently. Moreover, too many rules may lead to overfitting. The number of rules can be reduced by methods like QualityBased Filtering [1,10] returning a subset of all rules. However ..."
Abstract
 Add to MetaCart
Abstract. Sets of decision rules induced from data can often be very large. Such sets of rules cannot be processed efficiently. Moreover, too many rules may lead to overfitting. The number of rules can be reduced by methods like QualityBased Filtering [1,10] returning a subset of all rules. However, such methods may produce decision models unable to match many new objects. In this paper we present a solution for reducing the number of rules by joining rules from some clusters. This leads to a smaller number of more general rules. 1
MICHAL GRUSZCZYRSKI HARDGROUNDS AND ECOLOGICAL SUCCESSION IN THE LIGHT
"... Benthic assemblages associated with Upper ' Jurassic hardgrounds in the Holy Cross Mts. display false, plausible, broken and real ecological succession. The breaks in the succession appear to be influenced by hydrodynamic activity, changes in salinity, pH, water chemistry, and rates of sediment ..."
Abstract
 Add to MetaCart
cemented by both calcite and aragonite which indicates conditions of cementation similar to those of Recent carbonate Sedimentary environments. K e y w o r d s: Paleoecology, biosedimentology, ecological succession, carbonate petrology, cementation, Jurassic, central Poland.
Results 1  10
of
15,158