Projects supporting the none data format.
Showing Items 1-20 of 178 on page 1 of 9: 1 2 3 4 5 6 Next Last

Logo pattern recognition tool 1.0

by openpr_nlpr - January 19, 2016, 03:54:11 CET [ Project Homepage BibTeX Download ] 382 views, 132 downloads, 3 subscriptions

About: a tool for marking samples in images for database building, also including algorithm of LBP,HOG,and classifiers of SVM (six kernels), adaboost,BP and convolutional networks, extreme learning machine.

Changes:

Initial Announcement on mloss.org.


Logo NPD Face Detector Training 1.0

by openpr_nlpr - October 8, 2015, 04:22:36 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 1113 views, 227 downloads, 2 subscriptions

About: This MATLAB package provides the Deep Quadratic Tree (DQT) and the Normalized Pixel Difference (NPD) based face detector training method proposed in our PAMI 2015 paper. It is fast, and effective for unconstrained face detection. For more details, please visit http://www.cbsr.ia.ac.cn/users/scliao/projects/npdface/.

Changes:

Initial Announcement on mloss.org.


Logo WEKA 3.7.13

by mhall - September 11, 2015, 04:55:02 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 53895 views, 8008 downloads, 4 subscriptions

Rating Whole StarWhole StarWhole StarWhole StarEmpty Star
(based on 6 votes)

About: The Weka workbench contains a collection of visualization tools and algorithms for data analysis and predictive modelling, together with graphical user interfaces for easy access to this [...]

Changes:

In core weka:

  • Numerically stable implementation of variance calculation in core Weka classes - thanks to Benjamin Weber
  • Unified expression parsing framework (with compiled expressions) is now employed by filters and tools that use mathematical/logical expressions - thanks to Benjamin Weber
  • Developers can now specify GUI and command-line options for their Weka schemes via a new unified annotation-based mechanism
  • ClassConditionalProbabilities filter - replaces the value of a nominal attribute in a given instance with its probability given each of the possible class values
  • GUI package manager's available list now shows both packages that are not currently installed, and those installed packages for which there is a more recent version available that is compatible with the base version of Weka being used
  • ReplaceWithMissingValue filter - allows values to be randomly (with a user-specified probability) replaced with missing values. Useful for experimenting with methods for imputing missing values
  • WrapperSubsetEval can now use plugin evaluation metrics

In packages:

  • alternatingModelTrees package - alternating trees for regression
  • timeSeriesFilters package, contributed by Benjamin Weber
  • distributedWekaSpark package - wrapper for distributed Weka on Spark
  • wekaPython package - execution of CPython scripts and wrapper classifier/clusterer for Scikit Learn schemes
  • MLRClassifier in RPlugin now provides access to almost all classification and regression learners in MLR 2.4

About: Jie Gui et al., "How to estimate the regularization parameter for spectral regression discriminant analysis and its kernel version?", IEEE Transactions on Circuits and Systems for Video Technology, vol. 24, no. 2, pp. 211-223, 2014

Changes:

Initial Announcement on mloss.org.


About: Jie Gui, Zhenan Sun, Guangqi Hou, Tieniu Tan, "An optimal set of code words and correntropy for rotated least squares regression", International Joint Conference on Biometrics, 2014, pp. 1-6

Changes:

Initial Announcement on mloss.org.


Logo RFD 1.0

by openpr_nlpr - April 28, 2014, 10:34:57 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 2329 views, 498 downloads, 1 subscription

About: This is an unoptimized implementation of the RFD binary descriptor, which is published in the following paper. B. Fan, et al. Receptive Fields Selection for Binary Feature Description. IEEE Transaction on Image Processing, 2014. doi: http://dx.doi.org/10.1109/TIP.2014.2317981

Changes:

Initial Announcement on mloss.org.


About: Kaiye Wang, Ran He, Wei Wang, Liang Wang, Tiuniu Tan. Learning Coupled Feature Spaces for Cross-modal Matching. In ICCV, 2013.

Changes:

Initial Announcement on mloss.org.


Logo Two dimensional relaxed representation 1.0

by openpr_nlpr - November 4, 2013, 05:48:12 CET [ Project Homepage BibTeX Download ] 1888 views, 441 downloads, 1 subscription

About: Q. Dong, Two-dimensional relaxed representation, Neurocomputing, 121:248-253, 2013, http://dx.doi.org/10.1016/j.neucom.2013.04.044

Changes:

Initial Announcement on mloss.org.


Logo Evaluation toolkit 1.0

by openpr_nlpr - August 13, 2013, 08:58:25 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 2375 views, 530 downloads, 1 subscription

About: This evaluation toolkit provides a unified framework for evaluating bag-of-words based encoding methods over several standard image classification datasets.

Changes:

Initial Announcement on mloss.org.


About: This letter proposes a new multiple linear regression model using regularized correntropy for robust pattern recognition. First, we motivate the use of correntropy to improve the robustness of the classicalmean square error (MSE) criterion that is sensitive to outliers. Then an l1 regularization scheme is imposed on the correntropy to learn robust and sparse representations. Based on the half-quadratic optimization technique, we propose a novel algorithm to solve the nonlinear optimization problem. Second, we develop a new correntropy-based classifier based on the learned regularization scheme for robust object recognition. Extensive experiments over several applications confirm that the correntropy-based l1 regularization can improve recognition accuracy and receiver operator characteristic curves under noise corruption and occlusion.

Changes:

Initial Announcement on mloss.org.


About: Robust sparse representation has shown significant potential in solving challenging problems in computer vision such as biometrics and visual surveillance. Although several robust sparse models have been proposed and promising results have been obtained, they are either for error correction or for error detection, and learning a general framework that systematically unifies these two aspects and explore their relation is still an open problem. In this paper, we develop a half-quadratic (HQ) framework to solve the robust sparse representation problem. By defining different kinds of half-quadratic functions, the proposed HQ framework is applicable to performing both error correction and error detection. More specifically, by using the additive form of HQ, we propose an L1-regularized error correction method by iteratively recovering corrupted data from errors incurred by noises and outliers; by using the multiplicative form of HQ, we propose an L1-regularized error detection method by learning from uncorrupted data iteratively. We also show that the L1-regularization solved by soft-thresholding function has a dual relationship to Huber M-estimator, which theoretically guarantees the performance of robust sparse representation in terms of M-estimation. Experiments on robust face recognition under severe occlusion and corruption validate our framework and findings.

Changes:

Initial Announcement on mloss.org.


Logo JProGraM 13.2

by ninofreno - February 13, 2013, 20:29:38 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 14447 views, 2891 downloads, 1 subscription

About: JProGraM (PRObabilistic GRAphical Models in Java) is a statistical machine learning library. It supports statistical modeling and data analysis along three main directions: (1) probabilistic graphical models (Bayesian networks, Markov random fields, dependency networks, hybrid random fields); (2) parametric, semiparametric, and nonparametric density estimation (Gaussian models, nonparanormal estimators, Parzen windows, Nadaraya-Watson estimator); (3) generative models for random networks (small-world, scale-free, exponential random graphs, Fiedler random graphs/fields), subgraph sampling algorithms (random walk, snowball, etc.), and spectral decomposition.

Changes:

JProGraM 13.2 -- CHANGE LOG

Release date: February 13, 2012

New features: -- Support for Fiedler random graphs/random field models for large-scale networks (ninofreno.graph.fiedler package); -- Various bugfixes and enhancements (especially in the ninofreno.graph and ninofreno.math package).


Logo r-cran-predbayescor 1.1-4

by r-cran-robot - December 1, 2012, 00:00:07 CET [ Project Homepage BibTeX Download ] 4248 views, 1121 downloads, 1 subscription

About: Classification rule based on Bayesian naive Bayes models with feature selection bias corrected

Changes:

Fetched by r-cran-robot on 2012-12-01 00:00:07.510624


Logo Milk 0.5

by luispedro - November 7, 2012, 13:08:28 CET [ Project Homepage BibTeX Download ] 27565 views, 6872 downloads, 1 subscription

Rating Whole StarWhole StarWhole StarEmpty StarEmpty Star
(based on 2 votes)

About: Python Machine Learning Toolkit

Changes:

Added LASSO (using coordinate descent optimization). Made SVM classification (learning and applying) much faster: 2.5x speedup on yeast UCI dataset.


Logo UniverSVM 1.22

by fabee - October 16, 2012, 11:24:12 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 22639 views, 3420 downloads, 0 subscriptions

About: The UniverSVM is a SVM implementation written in C/C++. Its functionality comprises large scale transduction via CCCP optimization, sparse solutions via CCCP optimization and data-dependent [...]

Changes:

Minor changes: fix bug on set_alphas_b0 function (thanks to Ferdinand Kaiser - ferdinand.kaiser@tut.fi)


Logo MDP Modular toolkit for Data Processing 3.3

by otizonaizit - October 4, 2012, 15:17:33 CET [ Project Homepage BibTeX Download ] 21086 views, 5294 downloads, 1 subscription

Rating Whole StarWhole StarWhole StarWhole Star1/2 Star
(based on 3 votes)

About: MDP is a Python library of widely used data processing algorithms that can be combined according to a pipeline analogy to build more complex data processing software. The base of available algorithms includes signal processing methods (Principal Component Analysis, Independent Component Analysis, Slow Feature Analysis), manifold learning methods ([Hessian] Locally Linear Embedding), several classifiers, probabilistic methods (Factor Analysis, RBM), data pre-processing methods, and many others.

Changes:

What's new in version 3.3?

  • support sklearn versions up to 0.12
  • cleanly support reload
  • fail gracefully if pp server does not start
  • several bug-fixes and improvements

Logo SkyVoice TTS and SDK 1.0

by openpr_nlpr - September 10, 2012, 03:48:47 CET [ Project Homepage BibTeX Download ] 2541 views, 601 downloads, 1 subscription

About: Text-to-Speech (TTS) is a kind of speech processing technology that converts text into speech. It involves phonetics, linguistics, digital signal processing technology, computer technology, multimedia technology, and other technologies. It is a frontier technology in Chinese information processing field. With TTS technology, any text used to be read by eyes can also be listened by ears.

Changes:

Initial Announcement on mloss.org.


Logo Threshold Image for Small object 1.0

by openpr_nlpr - July 23, 2012, 11:25:46 CET [ Project Homepage BibTeX Download ] 2636 views, 716 downloads, 1 subscription

About: Including source code of Threshold Method,SVM,Play Scan and Play detection.

Changes:

Initial Announcement on mloss.org.


About: We study the problem of robust feature extraction based on L21 regularized correntropy in both theoretical and algorithmic manner. In theoretical part, we point out that an L21-norm minimization can be justified from the viewpoint of half-quadratic (HQ) optimization, which facilitates convergence study and algorithmic development. In particular, a general formulation is accordingly proposed to unify L1-norm and L21-norm minimization within a common framework. In algorithmic part, we propose an L21 regularized correntropy algorithm to extract informative features meanwhile to remove outliers from training data. A new alternate minimization algorithm is also developed to optimize the non-convex correntropy objective. In terms of face recognition, we apply the proposed method to obtain an appearance-based model, called Sparse-Fisherfaces. Extensive experiments show that our method can select robust and sparse features, and outperforms several state-of-the-art subspace methods on largescale and open face recognition datasets.

Changes:

Initial Announcement on mloss.org.


Logo Action Recognition by Dense Trajectories 1.0

by openpr_nlpr - June 6, 2012, 11:38:07 CET [ Project Homepage BibTeX BibTeX for corresponding Paper Download ] 5005 views, 916 downloads, 1 subscription

About: The code is for computing state-of-the-art video descriptors for action recognition. The most up-to-date information can be found at: http://lear.inrialpes.fr/people/wang/dense_trajectories

Changes:

Initial Announcement on mloss.org.


Showing Items 1-20 of 178 on page 1 of 9: 1 2 3 4 5 6 Next Last