Sciweavers

2925 search results - page 107 / 585
» Input Modeling Using Quantile Statistical Methods
Sort
View
CVPR
1999
IEEE
1104views Computer Vision» more  CVPR 1999»
15 years 12 months ago
Geodesic Active Contours for Supervised Texture Segmentation
This paper presents a variational method for supervised texture segmentation, which is based on ideas coming from the curve propagation theory. We assume that a preferable texture...
Nikos Paragios, Rachid Deriche
ACL
1998
14 years 11 months ago
Automatic Acquisition of Hierarchical Transduction Models for Machine Translation
We describe a method for the fully automatic learning of hierarchical finite state translation models. The input to the method is transcribed speech utterances and their correspon...
Hiyan Alshawi, Srinivas Bangalore, Shona Douglas
ITS
2004
Springer
124views Multimedia» more  ITS 2004»
15 years 3 months ago
Combining Competing Language Understanding Approaches in an Intelligent Tutoring System
When implementing a tutoring system that attempts a deep understanding of students’ natural language explanations, there are three basic approaches to choose between; symbolic, i...
Pamela W. Jordan, Maxim Makatchev, Kurt VanLehn
ICIP
2009
IEEE
15 years 11 months ago
Learning Local Models For 2d Human Motion Tracking
We present a novel approach to tracking 2D human motion in uncalibrated monocular videos. Human motion usually exhibits timevarying patterns, and we propose to use locally learnt ...
ICIP
2003
IEEE
15 years 11 months ago
Pixel classification through divergence-based integration of texture methods with conflict resolution
This paper presents a new technique for combining multiple texture feature extraction methods in order to classify the pixels of an input image into a set of texture models of int...
Domènec Puig, Miguel Angel García