Audio-visual probabilistic tracking of multiple speakers in meetings

Chattez avec Graph Search

Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.

AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.

Modern integrated circuits are tiny yet incredibly complex technological artifacts, composed of millions and billions of individual structures working in unison. Managing their complexity and facilitating their design drove part of the co-evolution of mode ...

In inverse problems, the task is to reconstruct an unknown signal from its possibly noise-corrupted measurements. Penalized-likelihood-based estimation and Bayesian estimation are two powerful statistical paradigms for the resolution of such problems. They ...

End-to-end learning methods like deep neural networks have been the driving force in the remarkable progress of machine learning in recent years. However, despite their success, the deployment process of such networks in safety-critical use cases, such as ...

Higher-order asymptotics provide accurate approximations for use in parametric statistical modelling. In this thesis, we investigate using higher-order approximations in two-specific settings, with a particular emphasis on the tangent exponential model. ...

Learning-based outlier (mismatched correspondence) rejection for robust 3D registration generally formulates the outlier removal as an inlier/outlier classification problem. The core for this to be successful is to learn the discriminative inlier/outlier f ...

Speech recognition-based applications upon the advancements in artificial intelligence play an essential role to transform most aspects of modern life. However, speech recognition in real-life conditions (e.g., in the presence of overlapping speech, varyin ...

Accurately estimating 3D human pose (3D HPE) and joint locations using only 2D keypoints is challenging. The noise in the predictions produced by conventional 2D human pose estimators often impeded the accuracy. In this paper, we present a diffusion-based ...

This paper introduces a new modeling and inference framework for multivariate and anisotropic point processes. Building on recent innovations in multivariate spatial statistics, we propose a new family of multivariate anisotropic random fields, and from th ...

A central question of machine learning is how deep nets manage to learn tasks in high dimensions. An appealing hypothesis is that they achieve this feat by building a representation of the data where information irrelevant to the task is lost. For image da ...

Magnetic resonance spectroscopy is a powerful, non-invasive, quantitative imaging technique that allows for the measurement of brain metabolites that has demonstrated utility in diagnosing and characterizing a broad range of neurological diseases. Its impa ...

In the field of choice modeling, the availability of ever-larger datasets has the potential to significantly expand our understanding of human behavior, but this prospect is limited by the poor scalability of discrete choice models (DCMs): as sample sizes ...

As an emerging technology in the era of Industry 4.0, digital twin is gaining unprecedented attention because of its promise to further optimize process design, quality control, health monitoring, decision- and policy-making, and more, by comprehensively m ...

Fault diagnosis plays an essential role in reducing the maintenance costs of rotating machinery manufacturing systems. In many real applications of fault detection and diagnosis, data tend to be imbalanced, meaning that the number of samples for some fault ...

The identification of accident hot spots is a central task of road safety management. Bayesian count data models have emerged as the workhorse method for producing probabilistic rankings of hazardous sites in road networks. Typically, these methods assume ...

The largest source of systematic errors in the time-delay cosmography method likely arises from the lens model mass distribution, where an inaccurate choice of model could in principle bias the value of H-0. A Bayesian hierarchical framework has been propo ...

In motor-related brain regions, movement intention has been successfully decoded from invivo spike train by isolating a lower-dimension manifold that the high-dimensional spiking activity is constrained to. The mechanism enforcing this constraint remains u ...

The spectral distribution plays a key role in the statistical modelling of multivariate extremes, as it defines the dependence structure of multivariate extreme-value distributions and characterizes the limiting distribution of the relative sizes of the co ...

Learning from demonstration (LfD) is an intuitive framework allowing non-expert users to easily (re-)program robots. However, the quality and quantity of demonstrations have a great influence on the generalization performances of LfD approaches. In this pa ...

The blockage of weirs or bridges by in-stream wood can reduce the flood discharge capacity, leading to hazardous situations. To assess the related risk, blocking probabilities quantifications are needed. However, large wood has a random behaviour and it is ...

Statistical models for extreme values are generally derived from non-degenerate probabilistic limits that can be used to approximate the distribution of events that exceed a selected high threshold. If convergence to the limit distribution is slow, then th ...

Audio-visual probabilistic tracking of multiple speakers in meetings

Chattez avec Graph Search

Graph generative deep learning models with an application to circuit topologies

Statistical Inference for Inverse Problems: From Sparsity-Based Methods to Neural Networks

Estimating and Improving the Robustness of Attributions in Text

Higher Order Asymptotics: Applications to Satellite Conjunction and Boundary Problems

Robust Outlier Rejection for 3D Registration with Variational Bayes

Sparse Autoencoders for Speech Modeling and Recognition

Diff3DHPE: A Diffusion Model for 3D Human Pose Estimation

Multivariate geometric anisotropic Cox processes

How deep convolutional neural networks lose spatial information with training

Harmonization of multi-scanner in vivo magnetic resonance spectroscopy: ENIGMA consortium task group considerations

Stochastic adaptive resampling for the estimation of discrete choice models

A comprehensive review of digital twin-part 2: roles of uncertainty quantification and optimization, a battery digital twin, and perspectives

Fault Detection and Diagnosis with Imbalanced and Noisy Data: A Hybrid Framework for Rotating Machinery

A new spatial count data model with Bayesian additive regression trees for accident hot spot identification

TOCOSMO VIII. A key test of systematics in the hierarchical method of time-delay cosmography

Topology of synaptic connectivity constrains neuronal stimulus representation, predicting two complementary coding strategies

Inference on the Angular Distribution of Extremes

Active Improvement of Control Policies with Bayesian Gaussian Mixture Model

Statistical accuracy for estimations of large wood blockage in a reservoir environment

Sub‐asymptotic motivation for new conditional multivariate extreme models