Sciweavers

881 search results - page 81 / 177
» Training Deformable Models for Localization
Sort
View
ICCV
2009
IEEE
15 years 1 months ago
A Shape-Based Object Class Model for Knowledge Transfer
Object class models trained on hundreds or thousands of images have shown to enable robust detection. Transferring knowledge from such models to new object classes trained from ...
Michael Stark, Michael Goesele, Bernt Schiele
EUROGRAPHICS
2010
Eurographics
14 years 5 months ago
Multi-Scale Geometry Interpolation
Interpolating vertex positions among triangle meshes with identical vertex-edge graphs is a fundamental part of many geometric modelling systems. Linear vertex interpolation is ro...
Tim Winkler, J. Drieseberg, Marc Alexa, Kai Horman...
NECO
1998
168views more  NECO 1998»
13 years 8 months ago
Constructive Incremental Learning from Only Local Information
We introduce a constructive, incremental learning system for regression problems that models data by means of spatially localized linear models. In contrast to other approaches, t...
Stefan Schaal, Christopher G. Atkeson
FGR
2011
IEEE
198views Biometrics» more  FGR 2011»
12 years 12 months ago
The optimal camera arrangement by a performance model for gait recognition
— Recently, many gait recognition algorithms are proposed, and the optimal camera arrangement is necessary to maximize the performance. In this paper, we propose the optimal came...
Naoki Akae, Yasushi Makihara, Yasushi Yagi
NAACL
2007
13 years 9 months ago
Applying Many-to-Many Alignments and Hidden Markov Models to Letter-to-Phoneme Conversion
Letter-to-phoneme conversion generally requires aligned training data of letters and phonemes. Typically, the alignments are limited to one-to-one alignments. We present a novel t...
Sittichai Jiampojamarn, Grzegorz Kondrak, Tarek Sh...