Sciweavers

881 search results - page 125 / 177
» Training Deformable Models for Localization
Sort
View
DAC
2005
ACM
13 years 10 months ago
Timing-driven placement by grid-warping
Grid-warping is a recent placement strategy based on a novel physical analogy: rather than move the gates to optimize their location, it elastically deforms a model of the 2-D chi...
Zhong Xiu, Rob A. Rutenbar
CVPR
2010
IEEE
14 years 4 months ago
Learning a Hierarchy of Discriminative Space-Time Neighborhood Features for Human Action Recognition
Recent work shows how to use local spatio-temporal features to learn models of realistic human actions from video. However, existing methods typically rely on a predefined spatial...
Adriana Kovashka, Kristen Grauman
ICCV
2009
IEEE
15 years 1 months ago
Automatic annotation of human actions in video
This paper addresses the problem of automatic temporal annotation of realistic human actions in video using mini- mal manual supervision. To this end we consider two asso- ciate...
Olivier Duchenne, Ivan Laptev, Josef Sivic, Franci...
IJON
2000
105views more  IJON 2000»
13 years 8 months ago
G-Prop: Global optimization of multilayer perceptrons using GAs
A general problem in model selection is to obtain the right parameters that make a model "t observed data. For a multilayer perceptron (MLP) trained with back-propagation (BP...
Pedro A. Castillo Valdivieso, Juan J. Merelo Guerv...
UAI
2003
13 years 9 months ago
Bayesian Hierarchical Mixtures of Experts
The Hierarchical Mixture of Experts (HME) is a well-known tree-structured model for regression and classification, based on soft probabilistic splits of the input space. In its o...
Christopher M. Bishop, Markus Svensén