Нема описа

Alexander Freytag d9c0a6fbed updated interfaces for gphik classifier пре 9 година
algebra acb47ec1be fixes to novelty semseg пре 11 година
configs 72d211d8f0 init пре 12 година
doxy 72d211d8f0 init пре 12 година
kernels 72d211d8f0 init пре 12 година
matlab d9c0a6fbed updated interfaces for gphik classifier пре 9 година
parameterizedFunctions 50b61955bf stable support of new quantization techniques пре 9 година
progs 3ddc557830 stable support of new functionality, uint for indexing, clean-up, etc. пре 9 година
quantization b5e60b8f62 stable quantization for Raw version пре 9 година
tests 5ab4f6647b test case bugfix and no sparsity tolerance пре 9 година
tutorial 72d211d8f0 init пре 12 година
.gitignore abb7dfbd64 added .gitignore пре 11 година
CMakeLists.txt bda18d7c04 CMakeLists now uses new macro for MEX files пре 11 година
FMKGPHyperparameterOptimization.cpp d9c0a6fbed updated interfaces for gphik classifier пре 9 година
FMKGPHyperparameterOptimization.h d9c0a6fbed updated interfaces for gphik classifier пре 9 година
FastMinKernel.cpp 90337e9f64 merged latest version of raw classifier, corrected minor issues пре 9 година
FastMinKernel.h 4b4259ccbb removed obsolete files, comments by erik пре 9 година
FeatureMatrixT.h 7b2f3a96c7 bug-fixing in quantization, fixing of heisenbug пре 9 година
FeatureMatrixT.tcc 5d91a69c0a support for EV settings, bug fix for capu computation, clean-up пре 9 година
GMHIKernel.cpp 50b61955bf stable support of new quantization techniques пре 9 година
GMHIKernel.h e26c33948b OnlineLearnable added, GPHIK ready for IL with 1 example update, everything nice and clean пре 11 година
GMHIKernelRaw.cpp 6b50a4117d corrected index bug in Raw version, adapted old code to new layout пре 9 година
GMHIKernelRaw.h b5e60b8f62 stable quantization for Raw version пре 9 година
GPHIKClassifier.cpp d9c0a6fbed updated interfaces for gphik classifier пре 9 година
GPHIKClassifier.h d9c0a6fbed updated interfaces for gphik classifier пре 9 година
GPHIKRawClassifier.cpp 0bfcd565d8 removed annoying bug for test-set testing, still with debug outputs пре 9 година
GPHIKRawClassifier.h 90337e9f64 merged latest version of raw classifier, corrected minor issues пре 9 година
GPHIKRegression.cpp 37d92063a8 completed refactoring wrt new persistent layout пре 11 година
GPHIKRegression.h 37d92063a8 completed refactoring wrt new persistent layout пре 11 година
GPLikelihoodApprox.cpp 27f0611efc major bugfix пре 9 година
GPLikelihoodApprox.h 3ddc557830 stable support of new functionality, uint for indexing, clean-up, etc. пре 9 година
IKMLinearCombination.cpp 7fc06c0490 removed compiler warnings пре 11 година
IKMLinearCombination.h e26c33948b OnlineLearnable added, GPHIK ready for IL with 1 example update, everything nice and clean пре 11 година
IKMNoise.cpp e26c33948b OnlineLearnable added, GPHIK ready for IL with 1 example update, everything nice and clean пре 11 година
IKMNoise.h e26c33948b OnlineLearnable added, GPHIK ready for IL with 1 example update, everything nice and clean пре 11 година
ImplicitKernelMatrix.cpp 72d211d8f0 init пре 12 година
ImplicitKernelMatrix.h e26c33948b OnlineLearnable added, GPHIK ready for IL with 1 example update, everything nice and clean пре 11 година
License 72d211d8f0 init пре 12 година
Makefile 72d211d8f0 init пре 12 година
Makefile.inc 72d211d8f0 init пре 12 година
OnlineLearnable.h d755cd9501 better doxygen docu for main classes пре 11 година
README 72d211d8f0 init пре 12 година
SortedVectorSparse.h 9f26f5dc49 Merge branch 'raw_version' пре 9 година
VectorSorter.cpp 72d211d8f0 init пре 12 година
VectorSorter.h 72d211d8f0 init пре 12 година
doxyfile_gp_hik.txt 72d211d8f0 init пре 12 година
libdepend.inc 72d211d8f0 init пре 12 година
tools.h 72d211d8f0 init пре 12 година

README

This code requires the NICE-core library (available on github) and implements the ideas presented in the following papers:

Alexander Freytag and Erik Rodner and Paul Bodesheim and Joachim Denzler
"Rapid Uncertainty Computation with Gaussian Processes and Histogram Intersection Kernels"
Asian Conference on Computer Vision (ACCV). 2012.

Erik Rodner and Alexander Freytag and Paul Bodesheim and Joachim Denzler
"Large-Scale Gaussian Process Classification with Flexible Adaptive Histogram Kernels"
European Conference on Computer Vision (ECCV). 2012. pages 85--98

If you use this software in your research, you have to cite at least one of the two papers.

Problems, questions, and general feedback should be addressed to:

Alexander.Freytag uni-jena.de
Erik.Rodner uni-jena.de

Copyright (LGPL) Alexander Freytag and Erik Rodner