Sciweavers

3467 search results - page 24 / 694
» Non-monotonic feature selection
Sort
View
SIGDIAL
2010
13 years 5 months ago
Discourse indicators for content selection in summarization
We present analyses aimed at eliciting which specific aspects of discourse provide the strongest indication for text importance. In the context of content selection for single doc...
Annie Louis, Aravind K. Joshi, Ani Nenkova
CVPR
2012
IEEE
11 years 10 months ago
Beyond spatial pyramids: Receptive field learning for pooled image features
In this paper we examine the effect of receptive field designs on classification accuracy in the commonly adopted pipeline of image classification. While existing algorithms us...
Yangqing Jia, Chang Huang, Trevor Darrell
INTERSPEECH
2010
13 years 2 months ago
Dynamic model selection for spectral voice conversion
Statistical methods for voice conversion are usually based on a single model selected in order to represent a tradeoff between goodness of fit and complexity. In this paper we ass...
Pierre Lanchantin, Xavier Rodet
TVCG
2012
180views Hardware» more  TVCG 2012»
11 years 10 months ago
Feature-Driven Data Exploration for Volumetric Rendering
Abstract—We have developed an intuitive method to semi-automatically explore volumetric data in a focus-region-guided or valuedriven way using a user defined ray through the 3D ...
Insoo Woo, Ross Maciejewski, Kelly P. Gaither, Dav...
ICMCS
2009
IEEE
215views Multimedia» more  ICMCS 2009»
13 years 5 months ago
Image trimming via saliency region detection and iterative feature matching
Detection of saliency regions in images is useful for object based image understanding and object localization. In our work, we investigate a saliency region detection algorithm b...
Jiawei Huang, Ze-Nian Li