Three-dimensional face recognition
An expression-invariant 3D face recognition approach is presented. Our basic assumption is
that facial expressions can be modelled as isometries of the facial surface. This allows to …
that facial expressions can be modelled as isometries of the facial surface. This allows to …
Improved Time-Series Clustering with UMAP dimension reduction method
Clustering is an unsupervised machine learning method giving insights on data without
early knowledge. Classes of data are return by assembling similar elements together. Giving …
early knowledge. Classes of data are return by assembling similar elements together. Giving …
[图书][B] Crítica de la antropología perspectivista: Viveiros de Castro–Philippe Descola–Bruno Latour
C Reynoso - 2015 - books.google.com
Bajo el nombre de “perspectivismo amerindio” se han popularizado tanto el
multinaturalismo del antropólogo brasilero Eduardo Viveiros de Castro como el animismo …
multinaturalismo del antropólogo brasilero Eduardo Viveiros de Castro como el animismo …
On non-linear operators for geometric deep learning
G Sergeant-Perthuis, J Maier… - Advances in Neural …, 2022 - proceedings.neurips.cc
This work studies operators mapping vector and scalar fields defined over a manifold
$\mathcal {M} $, and which commute with its group of diffeomorphisms $\text {Diff}(\mathcal …
$\mathcal {M} $, and which commute with its group of diffeomorphisms $\text {Diff}(\mathcal …
Improved time series clustering based on new geometric frameworks
Most existing methods for time series clustering rely on distances calculated from the entire
raw data using the Euclidean distance or Dynamic Time Warping distance. In this work, we …
raw data using the Euclidean distance or Dynamic Time Warping distance. In this work, we …
Wireless link scheduling over recurrent Riemannian manifolds
R Shelim, AS Ibrahim - IEEE Transactions on Vehicular …, 2022 - ieeexplore.ieee.org
Deep learning models for scheduling of potentially-interfering communication pairs, in
device-to-device (D2D) settings, require large training samples in the order of hundreds to …
device-to-device (D2D) settings, require large training samples in the order of hundreds to …
Geometric machine learning over riemannian manifolds for wireless link scheduling
R Shelim, AS Ibrahim - IEEE Access, 2022 - ieeexplore.ieee.org
In this paper, we propose two novel geometric machine learning (G-ML) methods for the
wireless link scheduling problem in device-to-device (D2D) networks. In dynamic D2D …
wireless link scheduling problem in device-to-device (D2D) networks. In dynamic D2D …
Learning wireless power allocation through graph convolutional regression networks over Riemannian manifolds
R Shelim, AS Ibrahim - IEEE Transactions on Vehicular …, 2023 - ieeexplore.ieee.org
Optimum power allocation is a key enabler for maximizing data rate in wireless networks.
Recently, various deep neural network models have been introduced for predicting power …
Recently, various deep neural network models have been introduced for predicting power …
Millimeter wave beamforming codebook design via learning channel covariance matrices over riemannian manifolds
I Nasim, AS Ibrahim - IEEE Access, 2022 - ieeexplore.ieee.org
Covariance matrices of spatially-correlated wireless channels in millimeter wave (mmWave)
vehicular networks can be employed to design environment-aware beamforming …
vehicular networks can be employed to design environment-aware beamforming …
Minimal Submanifolds of the Classical Compact Riemannian Symmetric Spaces
JM Gegenfurtner - arXiv preprint arXiv:2406.11294, 2024 - arxiv.org
Minimal submanifolds constitute a central area within the realm of differential geometry, due
to their many applications in various branches of physics. In this thesis we will employ a …
to their many applications in various branches of physics. In this thesis we will employ a …