Results 1 - 10 of 123

Building a Large Annotated Corpus of English: The Penn Treebank

by Mitchell P. Marcus, Beatrice Santorini, Mary Ann Marcinkiewicz - COMPUTATIONAL LINGUISTICS , 1993
"... There is a growing consensus that significant, rapid progress can be made in both text understanding and spoken language understanding by investigating those phenomena that occur most centrally in naturally occurring unconstrained materials and by attempting to automatically extract information abou ..."
Abstract - Cited by 2740 (10 self) - Add to MetaCart
There is a growing consensus that significant, rapid progress can be made in both text understanding and spoken language understanding by investigating those phenomena that occur most centrally in naturally occurring unconstrained materials and by attempting to automatically extract information

Fully constrained least squares linear mixture analysis for material quantification in hyperspectral imagery

by Daniel C. Heinz, Chein-i Chang - IEEE TRANS. ON GEOSCIENCE AND REMOTE SENSING , 2001
"... Linear spectral mixture analysis (LSMA) is a widely used technique in remote sensing to estimate abundance fractions of materials present in an image pixel. In order for an LSMA-based estimator to produce accurate amounts of material abundance, it generally requires two constraints imposed on the l ..."
Abstract - Cited by 169 (4 self) - Add to MetaCart
Linear spectral mixture analysis (LSMA) is a widely used technique in remote sensing to estimate abundance fractions of materials present in an image pixel. In order for an LSMA-based estimator to produce accurate amounts of material abundance, it generally requires two constraints imposed

Constrained Delaunay triangulations

by L. Paul Chew - Algorithmica , 1989
"... Given a set of n vertices in the plane together with a set of noncrossing edges, the constrained Delaunay triangulation (CDT) is the triangulation of the vertices with the following properties: (1) the prespecified edges are included in the triangulation, and (2) it is as close as possible to the De ..."
Abstract - Cited by 207 (4 self) - Add to MetaCart
to the Delaunay triangulation. We show that the CDT can be built in optimal O(n log n) time using a divide-and-conquer technique. This matches the time required to build an arbitrary (unconstrained) Delaunay triangulation and the time required to build an arbitrary constrained (nonDelaunay) triangulation. CDTs

Memetic Algorithms for the Unconstrained Binary Quadratic Programming Problem

by Peter Merz, Kengo Katayama - BioSystems , 2004
"... This paper presents a memetic algorithm, a highly eective evolutionary algorithm incorporating local search for solving the unconstrained binary quadratic programming problem (BQP). To justify the approach, a tness landscape analysis is conducted experimentally for several instances of the BQP. ..."
Abstract - Cited by 22 (4 self) - Add to MetaCart
This paper presents a memetic algorithm, a highly eective evolutionary algorithm incorporating local search for solving the unconstrained binary quadratic programming problem (BQP). To justify the approach, a tness landscape analysis is conducted experimentally for several instances of the BQP

Constrained Images Our work: Unconstrained Images

by Brian Heflin, Walter Scheirer, T. E. Boult
"... © 2012 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to ..."
Abstract - Add to MetaCart
© 2012 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution

LEARNING WEIGHTED SIMILARITY MEASUREMENTS FOR UNCONSTRAINED FACE RECOGNITION

by Andre Störmer, Gerhard Rigoll, Technische Universität München
"... Unconstrained face recognition is the problem of deciding if an image pair is showing the same individual or not, without having class specific training material or knowing anything about the image conditions. In this paper, an approach of learning suited similarity measurements is introduced. For t ..."
Abstract - Add to MetaCart
Unconstrained face recognition is the problem of deciding if an image pair is showing the same individual or not, without having class specific training material or knowing anything about the image conditions. In this paper, an approach of learning suited similarity measurements is introduced

Creating Texture Exemplars from Unconstrained Images

by Yitzchak David, Lockerman Su, Xue Julie Dorsey, Holly Rushmeier , 2013
"... Texture is an essential feature in modeling the appearance of ob-jects and is instrumental in making virtual objects appear interesting and/or realistic. Unfortunately, obtaining textures is a labor intensive task requiring parameter tuning for procedural methods or careful pho-tography and post-pro ..."
Abstract - Add to MetaCart
in unconstrained photographs, and extract exemplar tiles. The method requires the user to only specify a single point within the image containing the desired texture and the scale of the desired texture. The user may tune the result using simple interactions. The method is non-local, in the sense that the desired

Light Neutralinos as Dark Matter in the Unconstrained Minimal Supersymmetric Standard Model ∗

by A. Gabutti A, M. Olechowski B, S. Cooper A, S. Pokorski A, L. Stodolsky A
"... The allowed parameter space for the lightest neutralino as the dark matter is explored using the Minimal Supersymmetric Standard Model as the low-energy effective theory without further theoretical constraints such as GUT. Selecting values of the parameters which are in agreement with present experi ..."
Abstract - Add to MetaCart
of the selected neutralinos on 27 Al and on other materials for dark matter experiments is discussed.

2D Articulated Human Pose Estimation and Retrieval in (Almost) Unconstrained Still Images

by M. Eichner, M. Marin-jimenez, A. Zisserman, V. Ferrari, M. Eichner, A. Zisserman, V. Ferrari
"... Abstract We present a technique for estimating the spatial layout of humans in still images – the position of the head, torso and arms. The theme we explore is that once a person is localized using an upper body detector, the search for their body parts can be considerably simplified using weak cons ..."
Abstract - Cited by 30 (4 self) - Add to MetaCart
to be upright and seen from the front or the back (not side). We evaluate the stages of our approach experimentally using ground truth layout annotation on a variety of challenging material, such as images from the PASCAL VOC 2008 challenge and video frames from TV shows and feature films. We also propose

Well-posedness of the fundamental boundary value problems for constrained anisotropic elastic materials

by Douglas N. Arnold, Richard S. Falk - Arch. Rational Mech. Anal , 1987
"... Dedicated to Professor JOACHIM NITSCHE on the occasion of his sixtieth birthday. We consider the equations of linear homogeneous anisotropic elasticity admitting the possibility that the material is internally constrained, and formulate a simple necessary and sufficient condition for the fundamental ..."
Abstract - Cited by 14 (0 self) - Add to MetaCart
problems are well-posed in terms of their Young’s moduli, shear moduli, and Poisson ratios. Finally, we derive a reformulation of the elasticity system that is valid for both constrained and unconstrained materials and involves only one scalar unknown in addition to the displacements. For a two
Results 1 - 10 of 123