@INPROCEEDINGS{1570919,
author={P. M. Roth and H. Grabner and H. Bischof and D. Skocaj and A. Leonardist},
booktitle={2005 IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance},
title={On-line Conservative Learning for Person Detection},
year={2005},
volume={},
number={},
pages={223-230},
keywords={image classification;learning (artificial intelligence);object detection;surveillance;discriminative classifiers;object detection system;on-line AdaBoost method;on-line conservative learning;person detection;reconstructive classifiers;Computer science education;Computer vision;Detectors;Educational programs;Educational technology;Layout;Object detection;Robustness;Surveillance;Visual system},
doi={10.1109/VSPETS.2005.1570919},
ISSN={},
month={Oct},}

@article{KRISTAN20112630,
title = "Multivariate online kernel density estimation with Gaussian kernels",
journal = "Pattern Recognition",
volume = "44",
number = "10",
pages = "2630 - 2642",
year = "2011",
note = "Semi-Supervised Learning for Visual Content Analysis and Understanding",
issn = "0031-3203",
doi = "https://doi.org/10.1016/j.patcog.2011.03.019",
url = "http://www.sciencedirect.com/science/article/pii/S0031320311001233",
author = "Matej Kristan and Aleš Leonardis and Danijel Skočaj",
keywords = "Online models, Probability density estimation, Kernel density estimation, Gaussian mixture models"
}
@ARTICLE{1580480,
author={S. Fidler and D. Skocaj and A. Leonardis},
journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
title={Combining reconstructive and discriminative subspace methods for robust classification and regression by subsampling},
year={2006},
volume={28},
number={3},
pages={337-350},
keywords={computer vision;image classification;image resolution;statistical analysis;canonical correlation analysis;computer vision;discriminative subspace methods;image pixels;linear discrimination analysis;linear subspace methods;principal component analysis;reconstructive subspace methods;regression tasks;robust classification;Computer vision;Electric breakdown;Image reconstruction;Independent component analysis;Linear discriminant analysis;Pattern recognition;Pixel;Principal component analysis;Robustness;Scattering;CCA;LDA;PCA;Subspace methods;discriminative methods;high-breakdown point classification;occlusion.;outlier detection;reconstructive methods;robust classification;robust regression;subsampling;Algorithms;Artificial Intelligence;Cluster Analysis;Computer Simulation;Discriminant Analysis;Face;Humans;Image Enhancement;Image Interpretation, Computer-Assisted;Information Storage and Retrieval;Models, Biological;Models, Statistical;Pattern Recognition, Automated;Principal Component Analysis;Regression Analysis;Reproducibility of Results;Sample Size;Sensitivity and Specificity;Signal Processing, Computer-Assisted},
doi={10.1109/TPAMI.2006.46},
ISSN={0162-8828},
month={March},}

@INPROCEEDINGS{1238667,
author={D. Skocaj and A. Leonardis},
booktitle={Proceedings Ninth IEEE International Conference on Computer Vision},
title={Weighted and robust incremental method for subspace learning},
year={2003},
volume={},
number={},
pages={1494-1501 vol.2},
keywords={computer vision;image representation;learning (artificial intelligence);visual perception;incremental method;principal subspace;robust process;subspace learning;visual learning;Computer vision;Humans;Information science;Layout;Machine learning;Pixel;Principal component analysis;Robustness;Singular value decomposition;Visual system},
doi={10.1109/ICCV.2003.1238667},
ISSN={},
month={Oct},}