Learning Multimodal Dictionaries
Authors:
- Gianluca MonaciGMGianluca Monaci
- Philippe JostPJPhilippe Jost
- Pierre VandergheynstPVPierre Vandergheynst
- Boris MailheBMBoris Mailhe
- Sylvain LesageSLSylvain Lesage
- Rémi GribonvalRGRémi Gribonval
- 13 August 2007
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 16 (9) , 2272-2283
Abstract
Real-world phenomena involve complex interactions between multiple signal modalities. As a consequence, humans are used to integrate at each instant perceptions from all their senses in order to enrich their understanding of the surrounding world. This paradigm can be also extremely useful in many signal processing and computer vision problems involving mutually related signals. The simultaneous processing of multimodal data can, in fact, reveal information that is otherwise hidden when considering the signals independently. However, in natural multimodal signals, the statistical dependencies between modalities are in general not obvious. Learning fundamental multimodal patterns could offer deep insight into the structure of such signals. In this paper, we present a novel model of multimodal signals based on their sparse decomposition over a dictionary of multimodal structures. An algorithm for iteratively learning multimodal generating functions that can be shifted at all positions in the signal is proposed, as well. The learning is defined in such a way that it can be accomplished by iteratively solving a generalized eigenvector problem, which makes the algorithm fast, flexible, and free of user-defined parameters. The proposed algorithm is applied to audiovisual sequences and it is able to discover underlying structures in the data. The detection of such audio-video patterns in audiovisual clips allows to effectively localize the sound source on the video in presence of substantial acoustic and visual distractors, outperforming state-of-the-art audiovisual localization algorithms.Keywords
This publication has 31 references indexed in Scilit:
- Cross-Modal Localization via SparsityIEEE Transactions on Signal Processing, 2007
- Audiovisual Gestalts2006
- Learning sparse, overcomplete representations of time-varying natural images2004
- Speaker Association With Signal-Level Audiovisual FusionIEEE Transactions on Multimedia, 2004
- Speaker Localisation Using Audio-Visual Synchrony: An Empirical StudyLecture Notes in Computer Science, 2003
- Dictionary Learning Algorithms for Sparse RepresentationNeural Computation, 2003
- Probabilistic framework for the adaptation and comparison of image codesJournal of the Optical Society of America A, 1999
- The “independent components” of natural scenes are edge filtersVision Research, 1997
- Sparse coding with an overcomplete basis set: A strategy employed by V1?Vision Research, 1997
- Temporal decorrelation: a theory of lagged and nonlagged responses in the lateral geniculate nucleusNetwork: Computation in Neural Systems, 1995