Publication

Learning Multi-Modal Dictionaries: Application to Audiovisual Data

Pierre Vandergheynst, Gianluca Monaci, Rémi Gribonval, Philippe Jost
2006
Conference Papers

Résumé

This paper presents a methodology for extracting meaningful synchronous structures from multi-modal signals. Simultaneous processing of multi-modal data can reveal information that is unavailable when handling the sources separately. However, in natural high-dimensional data, the statistical dependencies between modalities are, most of the time, not obvious. Learning fundamental multi-modal patterns is an alternative to classical statistical methods. Typically, recurrent patterns are shift invariant, thus the learning should try to find the best matching filters. We present a new algorithm for iteratively learning multi-modal generating functions that can be shifted at all positions in the signal. The proposed algorithm is applied to audiovisual sequences and it demonstrates to be able to discover underlying structures in the data.

Source officielle

https://infoscience.epfl.ch/entities/publication/3fb333ea-751f-4e60-9077-6d2e22972ddf

À propos de ce résultat

Cette page est générée automatiquement et peut contenir des informations qui ne sont pas correctes, complètes, à jour ou pertinentes par rapport à votre recherche. Il en va de même pour toutes les autres pages de ce site. Veillez à vérifier les informations auprès des sources officielles de l'EPFL.

Pierre Vandergheynst, Gianluca Monaci, Rémi Gribonval, Philippe Jost
2006
Conference Papers

Résumé

Source officielle

https://infoscience.epfl.ch/entities/publication/3fb333ea-751f-4e60-9077-6d2e22972ddf

À propos de ce résultat

Concepts associés (24)

Entropy (statistical thermodynamics)

The concept entropy was first developed by German physicist Rudolf Clausius in the mid-nineteenth century as a thermodynamic property that predicts that certain spontaneous processes are irreversible or impossible. In statistical mechanics, entropy is formulated as a statistical property using probability theory. The statistical entropy perspective was introduced in 1870 by Austrian physicist Ludwig Boltzmann, who established a new field of physics that provided the descriptive linkage between the macroscopic observation of nature and the microscopic view based on the rigorous treatment of large ensembles of microstates that constitute thermodynamic systems.

Statistical mechanics

In physics, statistical mechanics is a mathematical framework that applies statistical methods and probability theory to large assemblies of microscopic entities. It does not assume or postulate any natural laws, but explains the macroscopic behavior of nature from the behavior of such ensembles. Sometimes called statistical physics or statistical thermodynamics, its applications include many problems in the fields of physics, biology, chemistry, and neuroscience.

Fonction de partition

En physique statistique, la fonction de partition Z est une grandeur fondamentale qui englobe les propriétés statistiques d'un système à l'équilibre thermodynamique. C'est une fonction de la température et d'autres paramètres, tels que le volume contenant un gaz par exemple. La plupart des variables thermodynamiques du système, telles que l'énergie totale, l'entropie, l'énergie libre ou la pression peuvent être exprimées avec cette fonction et ses dérivées.

Afficher plus

Publications associées (30)

Topics in statistical physics of high-dimensional machine learning

Hugo Chao Cui

In the past few years, Machine Learning (ML) techniques have ushered in a paradigm shift, allowing the harnessing of ever more abundant sources of data to automate complex tasks. The technical workhorse behind these important breakthroughs arguably lies in ...

EPFL2024

Random matrix methods for high-dimensional machine learning models

Antoine Philippe Michel Bodin

In the rapidly evolving landscape of machine learning research, neural networks stand out with their ever-expanding number of parameters and reliance on increasingly large datasets. The financial cost and computational resources required for the training p ...

EPFL2024

Incorporating Projective Geometry into Deep Learning

Michal Jan Tyszkiewicz

In this thesis we explore the applications of projective geometry, a mathematical theory of the relation between 3D scenes and their 2D images, in modern learning-based computer vision systems. This is an interesting research question which contradicts the ...

EPFL2024

Afficher plus