Sciweavers

2512 search results - page 23 / 503
» Learning from Highly Structured Data by Decomposition
Sort
View
EMNLP
2011
13 years 9 months ago
Watermarking the Outputs of Structured Prediction with an application in Statistical Machine Translation
We propose a general method to watermark and probabilistically identify the structured outputs of machine learning algorithms. Our method is robust to local editing operations and...
Ashish Venugopal, Jakob Uszkoreit, David Talbot, F...
CVPR
2007
IEEE
15 years 4 months ago
High Distortion and Non-Structural Image Matching via Feature Co-occurrence
We propose a novel approach for determining if a pair of images match each other under the effect of a highdistortion transformation or non-structural relation. The co-occurrence ...
Xi Chen, Tat-Jen Cham
88
Voted
AAAI
2006
14 years 11 months ago
Performing Incremental Bayesian Inference by Dynamic Model Counting
The ability to update the structure of a Bayesian network when new data becomes available is crucial for building adaptive systems. Recent work by Sang, Beame, and Kautz (AAAI 200...
Wei Li 0002, Peter van Beek, Pascal Poupart
APCCAS
2006
IEEE
373views Hardware» more  APCCAS 2006»
15 years 1 months ago
A New High Precision Low Offset Dynamic Comparator for High Resolution High Speed ADCs
A new low offset dynamic comparator for high resolution high speed analog-to-digital application has been designed. Inputs are reconfigured from the typical differential pair compa...
Vipul Katyal, Randall L. Geiger, Degang Chen
ICDE
2012
IEEE
202views Database» more  ICDE 2012»
13 years 4 days ago
Differentially Private Spatial Decompositions
— Differential privacy has recently emerged as the de facto standard for private data release. This makes it possible to provide strong theoretical guarantees on the privacy and ...
Graham Cormode, Cecilia M. Procopiuc, Divesh Sriva...