Sciweavers

498 search results - page 35 / 100
» Layered Active Appearance Models
Sort
View
128
Voted
CVPR
2011
IEEE
14 years 9 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
CVPR
2012
IEEE
13 years 3 months ago
A flow model for joint action recognition and identity maintenance
We propose a framework that performs action recognition and identity maintenance of multiple targets simultaneously. Instead of first establishing tracks using an appearance mode...
Sameh Khamis, Vlad I. Morariu, Larry S. Davis
IJCNN
2007
IEEE
15 years 7 months ago
Character Recognition using Spiking Neural Networks
— A spiking neural network model is used to identify characters in a character set. The network is a two layered structure consisting of integrate-and-fire and active dendrite n...
Ankur Gupta, Lyle N. Long
102
Voted
JMLR
2010
151views more  JMLR 2010»
14 years 7 months ago
Understanding the difficulty of training deep feedforward neural networks
Whereas before 2006 it appears that deep multilayer neural networks were not successfully trained, since then several algorithms have been shown to successfully train them, with e...
Xavier Glorot, Yoshua Bengio
123
Voted
MICCAI
2006
Springer
16 years 1 months ago
Improving Segmentation of the Left Ventricle Using a Two-Component Statistical Model
Abstract. Quality of segmentations obtained by 3D Active Appearance Models (AAMs) crucially depends on underlying training data. MRI heart data, however, often come noisy, incomple...
Jirí Hladuvka, Katja Bühler, Sebastian...