Sciweavers

5046 search results - page 238 / 1010
» Feature Selection from Huge Feature Sets
Sort
View
ICRA
2009
IEEE
160views Robotics» more  ICRA 2009»
16 years 1 months ago
Appearance-based loop detection from 3D laser data using the normal distributions transform
— We propose a new approach to appearance based loop detection from metric 3D maps, exploiting the NDT surface representation. Locations are described with feature histograms bas...
Martin Magnusson 0002, Henrik Andreasson, Andreas ...
ACL
2004
15 years 8 months ago
Discriminative Language Modeling with Conditional Random Fields and the Perceptron Algorithm
This paper describes discriminative language modeling for a large vocabulary speech recognition task. We contrast two parameter estimation methods: the perceptron algorithm, and a...
Brian Roark, Murat Saraclar, Michael Collins, Mark...
TNN
2010
168views Management» more  TNN 2010»
15 years 1 months ago
On the selection of weight decay parameter for faulty networks
The weight-decay technique is an effective approach to handle overfitting and weight fault. For fault-free networks, without an appropriate value of decay parameter, the trained ne...
Andrew Chi-Sing Leung, Hongjiang Wang, John Sum
CVPR
2007
IEEE
15 years 10 months ago
Improving Part based Object Detection by Unsupervised, Online Boosting
Detection of objects of a given class is important for many applications. However it is difficult to learn a general detector with high detection rate as well as low false alarm r...
Bo Wu, Ram Nevatia
MM
2005
ACM
178views Multimedia» more  MM 2005»
16 years 5 days ago
Attention region selection with information from professional digital camera
The attentive region extraction is a challenging issue for semantic interpretation of image and video content. The successful attentive region extraction greatly facilitates image...
Song Liu, Liang-Tien Chia, Deepu Rajan