Sciweavers

2820 search results - page 43 / 564
» Learning from Scarce Experience
Sort
View
CVPR
2010
IEEE
16 years 2 months ago
Learning from Interpolated Images using Neural Networks for Digital Forensics
Interpolated images have data redundancy, and special correlation exists among neighboring pixels, which is a crucial clue in digital forensics. We design a neural network based f...
Yizhen Huang, Na Fan
ICASSP
2009
IEEE
15 years 9 months ago
Improved lattice-based spoken document retrieval by directly learning from the evaluation measures
Lattice-based approaches have been widely used in spoken document retrieval to handle the speech recognition uncertainty and errors. Position Specific Posterior Lattices (PSPL) an...
Chao-hong Meng, Hung-yi Lee, Lin-shan Lee
TMM
2011
220views more  TMM 2011»
15 years 23 days ago
Learning Visual Contexts for Image Annotation From Flickr Groups
Abstract—We present an extension of automatic image annotation that takes the context of a picture into account. Our core assumption is that users do not only provide individual ...
Adrian Ulges, Marcel Worring, Thomas M. Breuel
EMNLP
2008
15 years 7 months ago
Discriminative Learning of Selectional Preference from Unlabeled Text
We present a discriminative method for learning selectional preferences from unlabeled text. Positive examples are taken from observed predicate-argument pairs, while negatives ar...
Shane Bergsma, Dekang Lin, Randy Goebel
AI
2001
Springer
15 years 10 months ago
A Case Study for Learning from Imbalanced Data Sets
We present our experience in applying a rule induction technique to an extremely imbalanced pharmaceutical data set. We focus on using a variety of performance measures to evaluate...
Aijun An, Nick Cercone, Xiangji Huang