914 search results - page 148 / 183 » Learning to Segment |
167
Voted
IJCV
2000
15 years 4 months ago
2000
We describe how to model the appearance of a 3-D object using multiple views, learn such a model from training images, and use the model for object recognition. The model uses pro...
155
click to vote
NN
2000
Springer
15 years 4 months ago
2000
Springer
Local minima and plateaus pose a serious problem in learning of neural networks. We investigate the hierarchical geometric structure of the parameter space of three-layer perceptr...
141
click to vote
MICCAI
2010
Springer
15 years 2 months ago
2010
Springer
Postprocedural analysis of gastrointestinal (GI) endoscopic videos is a difficult task because the videos often suffer from a large number of poor-quality frames due to the motion...
156
click to vote
CVPR
2010
IEEE
15 years 2 months ago
2010
IEEE
Our goal is to fit the multiple instances (or structures) of a generic model existing in data. Here we propose a novel model selection scheme to estimate the number of genuine str...
138
click to vote
INTERSPEECH
2010
14 years 11 months ago
2010
This paper reports our recent exploration of the layer-by-layer learning strategy for training a multi-layer generative model of patches of speech spectrograms. The top layer of t...