Výsledky vyhledávání - "Hosseini, Babak"

Report

Deep-Aligned Convolutional Neural Network for Skeleton-based Action Recognition and Segmentation

Autor: Hosseini, Babak, Montagne, Romain, Hammer, Barbara

Convolutional neural networks (CNNs) are deep learning frameworks which are well-known for their notable performance in classification tasks. Hence, many skeleton-based action recognition and segmentation (SBARS) algorithms benefit from them in their

Externí odkaz: http://arxiv.org/abs/1911.04969

Zobrazit plný text záznamu

Report

Interpretable Multiple-Kernel Prototype Learning for Discriminative Representation and Feature Selection

Autor: Hosseini, Babak, Hammer, Barbara

Prototype-based methods are of the particular interest for domain specialists and practitioners as they summarize a dataset by a small set of representatives. Therefore, in a classification setting, interpretability of the prototypes is as significan

Externí odkaz: http://arxiv.org/abs/1911.03949

Zobrazit plný text záznamu

Report

Interpretable Discriminative Dimensionality Reduction and Feature Selection on the Manifold

Autor: Hosseini, Babak, Hammer, Barbara

Dimensionality reduction (DR) on the manifold includes effective methods which project the data from an implicit relational space onto a vectorial space. Regardless of the achievements in this area, these algorithms suffer from the lack of interpreta

Externí odkaz: http://arxiv.org/abs/1909.09218

Zobrazit plný text záznamu

Report

Non-Negative Local Sparse Coding for Subspace Clustering

Autor: Hosseini, Babak, Hammer, Barbara

Subspace sparse coding (SSC) algorithms have proven to be beneficial to clustering problems. They provide an alternative data representation in which the underlying structure of the clusters can be better captured. However, most of the research in th

Externí odkaz: http://arxiv.org/abs/1903.05239

Zobrazit plný text záznamu

Report

Confident Kernel Sparse Coding and Dictionary Learning

Autor: Hosseini, Babak, Hammer, Barbara

In recent years, kernel-based sparse coding (K-SRC) has received particular attention due to its efficient representation of nonlinear data structures in the feature space. Nevertheless, the existing K-SRC methods suffer from the lack of consistency

Externí odkaz: http://arxiv.org/abs/1903.05219

Zobrazit plný text záznamu

Report

Non-Negative Kernel Sparse Coding for the Classification of Motion Data

Autor: Hosseini, Babak, Hülsmann, Felix, Botsch, Mario, Hammer, Barbara

We are interested in the decomposition of motion data into a sparse linear combination of base functions which enable efficient data processing. We combine two prominent frameworks: dynamic time warping (DTW), which offers particularly successful pai

Externí odkaz: http://arxiv.org/abs/1903.03891

Zobrazit plný text záznamu

Report

Large-Margin Multiple Kernel Learning for Discriminative Features Selection and Representation Learning

Autor: Hosseini, Babak, Hammer, Barbara

Multiple kernel learning (MKL) algorithms combine different base kernels to obtain a more efficient representation in the feature space. Focusing on discriminative tasks, MKL has been used successfully for feature selection and finding the significan

Externí odkaz: http://arxiv.org/abs/1903.03364

Zobrazit plný text záznamu

Report

Multiple-Kernel Dictionary Learning for Reconstruction and Clustering of Unseen Multivariate Time-series

Autor: Hosseini, Babak, Hammer, Barbara

There exist many approaches for description and recognition of unseen classes in datasets. Nevertheless, it becomes a challenging problem when we deal with multivariate time-series (MTS) (e.g., motion data), where we cannot apply the vectorial algori

Externí odkaz: http://arxiv.org/abs/1903.01867

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání