Related papers: A different view on the vector-valued empirical mo…

A non-parametric complementary ensemble empirical mode decomposition (NPCEEMD) is proposed for identifying bearing defects using weak features. NPCEEMD is non-parametric because, unlike existing decomposition methods such as ensemble…

Tactile Internet (TI) requires ultra-low latency and high reliability to ensure stability and transparency in touch-enabled teleoperation. However, variable delays and packet loss present significant challenges to maintaining immersive…

In multivariate extreme value theory (MEVT), the focus is on analysis outside of the observable sampling zone, which implies that the region of interest is associated to high risk levels. This work provides tools to include directional…

A state transition model (STM) based on chunk-wise classification was proposed for end-point detection (EPD). In general, EPD is developed using frame-wise voice activity detection (VAD) with additional STM, in which the state transition is…

We introduce the concept of a Modular Autoencoder (MAE), capable of learning a set of diverse but complementary representations from unlabelled data, that can later be used for supervised tasks. The learning of the representations is…

Despite the great progress in 3D human pose estimation from videos, it is still an open problem to take full advantage of a redundant 2D pose sequence to learn representative representations for generating one 3D pose. To this end, we…

Despite recent advances in Large Vision Language Models (LVLMs), these models still suffer from generating hallucinatory responses that do not align with the visual input provided. To mitigate such hallucinations, we introduce Efficient…

Latent Video Diffusion Models (LVDMs) rely on Variational Autoencoders (VAEs) to compress videos into compact latent representations. For continuous Variational Autoencoders (VAEs), achieving higher compression rates is desirable; yet, the…

Vector Error Correction Model (VECM) is a classic method to analyse cointegration relationships amongst multivariate non-stationary time series. In this paper, we focus on high dimensional setting and seek for sample-size-efficient…

Extracting information from complex data is a challenge shared by multiple frontiers of modern astrophysical research. Among those, analyzing spectra cubes, where the emission is mapped in the position-position-velocity space is a difficult…

In this work we report some results, obtained within the framework of the ERC Project CHANGE, on the impact on the performance of the virtual element method of the shape of the polygonal elements of the underlying mesh. More in detail,…

We propose a new embedding method for a single vector and for a pair of vectors. This embedding method enables: a) efficient classification and regression of functions of single vectors; b) efficient approximation of distance functions; and…

The EM training algorithm of the classical i-vector extractor is often incorrectly described as a maximum-likelihood method. The i-vector model is however intractable: the likelihood itself and the hidden-variable posteriors needed for the…

We introduce the harmonic virtual element method (harmonic VEM), a modification of the virtual element method (VEM) for the approximation of the 2D Laplace equation using polygonal meshes. The main difference between the harmonic VEM and…

Effective resource allocation is a crucial requirement to achieve the stringent performance targets of ultra-reliable low-latency communication (URLLC) services. Predicting future interference and utilizing it to design efficient…

In this paper, we address the unsupervised speech enhancement problem based on recurrent variational autoencoder (RVAE). This approach offers promising generalization performance over the supervised counterpart. Nevertheless, the involved…

Embedding is a useful technique to project a high-dimensional feature into a low-dimensional space, and it has many successful applications including link prediction, node classification and natural language processing. Current approaches…

An extreme-point symmetric mode decomposition (ESMD) method is proposed to improve the Hilbert-Huang Transform (HHT) through the following prospects: (1) The sifting process is implemented by the aid of 1, 2, 3 or more inner interpolating…

Learning to represent three dimensional (3D) human pose given a two dimensional (2D) image of a person, is a challenging problem. In order to make the problem less ambiguous it has become common practice to estimate 3D pose in the camera…

Vector beams (VBs) are fully polarized beams with spatially varying polarization distributions, and they have found widespread use in numerous applications such as microscopy, metrology, optical trapping, nano-photonics, and communications.…