This repository is for Multimodal Subspace Support Vector Data Description. The codes are provided as .m (matlab) files to be executed in matlab. The codes are provided without any warranty or gurantee. see demo.m for example usage of the code. Please contact fahad.sohrab@tuni.fi for any issues.
MS-SVDD requires LIBSVM for SVDD. Before executing the codes, make sure that correct version (3.22) of LIBSVM for SVDD is installed already. In order to install LIBSVM for SVDD Please download zip file from HERE, put sources into libsvm-3.22 available HERE, and make the code. For more details about how to install libsvm, please refer HERE
If you find this work useful in your research, please consider citing the following papers:
@inproceedings{sohrab2018subspace,
title={Subspace support vector data description},
author={Sohrab, Fahad and Raitoharju, Jenni and Gabbouj, Moncef and Iosifidis, Alexandros},
booktitle={2018 24th International Conference on Pattern Recognition (ICPR)},
pages={722--727},
year={2018},
organization={IEEE}
}
@article{sohrab2020multimodal,
title={Multimodal subspace support vector data description},
author={Sohrab, Fahad and Raitoharju, Jenni and Iosifidis, Alexandros and Gabbouj, Moncef},
journal={Pattern Recognition},
year={2020}
}