Sciweavers

576 search results - page 70 / 116
» Matching methodology to problem domain
Sort
View
CVPR
2011
IEEE
13 years 5 months ago
Learning to Recognize Objects in Egocentric Activities
This paper addresses the problem of learning object models from egocentric video of household activities, using extremely weak supervision. For each activity sequence, we know onl...
Alireza Fathi, Xiaofeng Ren, James Rehg
MOC
2011
13 years 3 months ago
Local energy estimates for the finite element method on sharply varying grids
Abstract. Local energy error estimates for the finite element method for elliptic problems were originally proved in 1974 by Nitsche and Schatz. These estimates show that the loca...
Alan Demlow, Johnny Guzmán, Alfred H. Schat...
GECCO
2008
Springer
114views Optimization» more  GECCO 2008»
13 years 9 months ago
Strategic positioning in tactical scenario planning
Capability planning problems are pervasive throughout many areas of human interest with prominent examples found in defense and security. Planning provides a unique context for op...
James M. Whitacre, Hussein A. Abbass, Ruhul A. Sar...
ICIP
2006
IEEE
14 years 10 months ago
A Profile Hidden Markov Model Framework for Modeling and Analysis of Shape
In this paper we propose a new framework for modeling 2D shapes. A shape is first described by a sequence of local features (e.g., curvature) of the shape boundary. The resulting ...
Rui Huang, Vladimir Pavlovic, Dimitris N. Metaxas
KDD
2002
ACM
144views Data Mining» more  KDD 2002»
14 years 9 months ago
Efficiently mining frequent trees in a forest
Mining frequent trees is very useful in domains like bioinformatics, web mining, mining semi-structured data, and so on. We formulate the problem of mining (embedded) subtrees in ...
Mohammed Javeed Zaki