Results 11  20
of
8,740
Threedimensional object recognition from single twodimensional images
 Artificial Intelligence
, 1987
"... A computer vision system has been implemented that can recognize threedimensional objects from unknown viewpoints in single grayscale images. Unlike most other approaches, the recognition is accomplished without any attempt to reconstruct depth information bottomup from the visual input. Instead, ..."
Abstract

Cited by 484 (7 self)
 Add to MetaCart
A computer vision system has been implemented that can recognize threedimensional objects from unknown viewpoints in single grayscale images. Unlike most other approaches, the recognition is accomplished without any attempt to reconstruct depth information bottomup from the visual input. Instead
NiagaraCQ: A Scalable Continuous Query System for Internet Databases
 In SIGMOD
, 2000
"... Continuous queries are persistent queries that allow users to receive new results when they become available. While continuous query systems can transform a passive web into an active environment, they need to be able to support millions of queries due to the scale of the Internet. No existing syste ..."
Abstract

Cited by 584 (9 self)
 Add to MetaCart
systems have achieved this level of scalability. NiagaraCQ addresses this problem by grouping continuous queries based on the observation that many web queries share similar structures. Grouped queries can share the common computation, tend to fit in memory and can reduce the I/O cost significantly
Loopy belief propagation for approximate inference: An empirical study. In:
 Proceedings of Uncertainty in AI,
, 1999
"... Abstract Recently, researchers have demonstrated that "loopy belief propagation" the use of Pearl's polytree algorithm in a Bayesian network with loops can perform well in the context of errorcorrecting codes. The most dramatic instance of this is the near Shannonlimit performanc ..."
Abstract

Cited by 676 (15 self)
 Add to MetaCart
the parents of each symptom were a random subset of the diseases. terior marginals of all other nodes. Again we found that loopy belief propagation always converged with the average number of iterations equal to 14.55. The results presented up until now show that loopy propagation performs well for a variety
RealTime Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations
"... A key challenge for neural modeling is to explain how a continuous stream of multimodal input from a rapidly changing environment can be processed by stereotypical recurrent circuits of integrateandfire neurons in realtime. We propose a new computational model for realtime computing on timevar ..."
Abstract

Cited by 469 (38 self)
 Add to MetaCart
A key challenge for neural modeling is to explain how a continuous stream of multimodal input from a rapidly changing environment can be processed by stereotypical recurrent circuits of integrateandfire neurons in realtime. We propose a new computational model for realtime computing on time
On the computation of the disjunctive wellfounded semantics
 Journal of Automated Reasoning
, 2001
"... Abstract. A characterisation of the disjunctive wellfounded semantics (DWFS) is given in terms of the GelfondLifschitz transformation. This characterisation is used to develop a topdown method of testing DWFS membership, employing a hyperresolutionlike operator and quasi cyclic trees to handle mi ..."
Abstract

Cited by 3 (1 self)
 Add to MetaCart
minimal model processing. A flexible bottomup method of computing the DWFS is also given which admits the use of a powerful reduction operator. For finite propositional databases, all of our methods run in polynomial space.
Computing with Membranes
 JOURNAL OF COMPUTER AND SYSTEM SCIENCES
, 1998
"... We introduce a new computability model, of a distributed parallel type, based on the notion of a membrane structure. Such a structure consists of several celllike membranes, recurrently placed inside a unique "skin" membrane. A plane representation is a Venn diagram without intersected se ..."
Abstract

Cited by 441 (5 self)
 Add to MetaCart
We introduce a new computability model, of a distributed parallel type, based on the notion of a membrane structure. Such a structure consists of several celllike membranes, recurrently placed inside a unique "skin" membrane. A plane representation is a Venn diagram without intersected
From Sparse Solutions of Systems of Equations to Sparse Modeling of Signals and Images
, 2007
"... A fullrank matrix A ∈ IR n×m with n < m generates an underdetermined system of linear equations Ax = b having infinitely many solutions. Suppose we seek the sparsest solution, i.e., the one with the fewest nonzero entries: can it ever be unique? If so, when? As optimization of sparsity is combin ..."
Abstract

Cited by 427 (36 self)
 Add to MetaCart
sparse solutions can be found by concrete, effective computational methods. Such theoretical results inspire a bold perspective on some important practical problems in signal and image processing. Several wellknown signal and image processing problems can be cast as demanding solutions of undetermined systems
Flexible Computation of the WellFounded Semantics of Normal Logic Programs
, 2001
"... The development and maintenance of modern information systems, that are getting more and more complex and, at the same time, require a high flexibility, is a great challenge for current information and communication technology. One contribution is the usage of a rulebased specification mechanism th ..."
Abstract
 Add to MetaCart
that allows the compact and declarative description of complex situations. One such rule language is given by normal logic programs. The wellfounded semantics has been accepted as the most relevant semantics for logicbased information systems. It assigns a unique (partial) model to every normal logic
MAC/FAC: A Model of Similaritybased Retrieval
 Cognitive Science
, 1991
"... We present a model of similaritybased retrieval which attempts to capture three psychological phenomena: (1) people are extremely good at judging similarity and analogy when given items to compare. (2) Superficial remindings are much more frequent than structural remindings. (3) People sometimes ex ..."
Abstract

Cited by 409 (111 self)
 Add to MetaCart
We present a model of similaritybased retrieval which attempts to capture three psychological phenomena: (1) people are extremely good at judging similarity and analogy when given items to compare. (2) Superficial remindings are much more frequent than structural remindings. (3) People sometimes
Computing The WellFounded Model Of Deductive Databases
 The International Journal of Uncertainty, Fuzziness and Knowledgebased Systems
, 1996
"... this paper, we show how paraconsistent relations can be used to capture a partial model of a general deductive database and how the associated algebra can be used to compute the wellfounded model of the database. The central idea in arriving at this model is to associate paraconsistent relations wi ..."
Abstract

Cited by 5 (2 self)
 Add to MetaCart
to iteratively construct the model. Computing the Wellfounded Model of Deductive Databases 3 The approach presented in this paper lays an algebraic foundation for query processing and optimization for general deductive databases. Query processing will proceed in a bottomup manner and will use popular
Results 11  20
of
8,740