Sciweavers

174 search results - page 21 / 35
» A new objective function for sequence labeling
Sort
View
DAGM
2008
Springer
14 years 11 months ago
MAP-Inference for Highly-Connected Graphs with DC-Programming
The design of inference algorithms for discrete-valued Markov Random Fields constitutes an ongoing research topic in computer vision. Large state-spaces, none-submodular energy-fun...
Jörg H. Kappes, Christoph Schnörr
ICML
2009
IEEE
15 years 10 months ago
Proximal regularization for online and batch learning
Many learning algorithms rely on the curvature (in particular, strong convexity) of regularized objective functions to provide good theoretical performance guarantees. In practice...
Chuong B. Do, Quoc V. Le, Chuan-Sheng Foo
VCIP
2003
147views Communications» more  VCIP 2003»
14 years 11 months ago
An objective method for combining multiple subjective data sets
International recommendations for subjective video quality assessment (e.g., ITU-R BT.500-11) include specifications for how to perform many different types of subjective tests. I...
Margaret H. Pinson, Stephen Wolf
ICCV
2011
IEEE
13 years 9 months ago
Relative Attributes
Human-nameable visual “attributes” can benefit various recognition tasks. However, existing techniques restrict these properties to categorical labels (for example, a person ...
Devi Parikh, Kristen Grauman
NAR
2011
248views Computer Vision» more  NAR 2011»
14 years 18 days ago
NCBI GEO: archive for functional genomics data sets - 10 years on
A decade ago, the Gene Expression Omnibus (GEO) database was established at the National Center for Biotechnology Information (NCBI). The original objective of GEO was to serve as...
Tanya Barrett, Dennis B. Troup, Stephen E. Wilhite...