Sciweavers

1516 search results - page 219 / 304
» On the Learnability of Vector Spaces
Sort
View
IVC
2007
124views more  IVC 2007»
14 years 9 months ago
Outlier rejection in high-dimensional deformable models
Deformable model tracking is a powerful methodology that allows us to track the evolution of high-dimensional parameter vectors from uncalibrated monocular video sequences. The co...
Christian Vogler, Siome Goldenstein, Jorge Stolfi,...
TSP
2008
117views more  TSP 2008»
14 years 9 months ago
A Theory for Sampling Signals From a Union of Subspaces
One of the fundamental assumptions in traditional sampling theorems is that the signals to be sampled come from a single vector space (e.g. bandlimited functions). However, in many...
Yue M. Lu, Minh N. Do
CORR
2002
Springer
99views Education» more  CORR 2002»
14 years 9 months ago
The Identification of Context-Sensitive Features: A Formal Definition of Context for Concept Learning
A large body of research in machine learning is concerned with supervised learning from examples. The examples are typically represented as vectors in a multi-dimensional feature ...
Peter D. Turney
PRESENCE
2007
167views more  PRESENCE 2007»
14 years 9 months ago
TimbreFields: 3D Interactive Sound Models for Real-Time Audio
We describe a methodology for Virtual Reality designers to capture and resynthesize the variations in sound made by objects when we interact with them through contact such as touc...
Richard Corbett, Kees van den Doel, John E. Lloyd,...
ICCV
2009
IEEE
14 years 7 months ago
Structural SVM for visual localization and continuous state estimation
We present an integrated model for visual object localization and continuous state estimation in a discriminative structured prediction framework. While existing discriminative `p...
Catalin Ionescu, Liefeng Bo, Cristian Sminchisescu