The Sound of an Album Cover: A Probabilistic Approach to Multimedia

Eric Brochu, Nando de Freitas, Kejie Bao
Proceedings of the Ninth International Workshop on Artificial Intelligence and Statistics, PMLR R4:49-56, 2003.

Abstract

We present a novel, flexible, statistical approach to modeling music, images and text jointly. The technique is based on multi-modal mixture models and efficient computation using online EM. The learned models can be used to browse multimedia databases, to query on a multimedia database using any combination of music, images and text (lyrics and other contextual information), to annotate documents with music and images, and to find documents in a database similar to input text, music and/or graphics files.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR4-brochu03a, title = {The Sound of an Album Cover: A Probabilistic Approach to Multimedia}, author = {Brochu, Eric and de Freitas, Nando and Bao, Kejie}, booktitle = {Proceedings of the Ninth International Workshop on Artificial Intelligence and Statistics}, pages = {49--56}, year = {2003}, editor = {Bishop, Christopher M. and Frey, Brendan J.}, volume = {R4}, series = {Proceedings of Machine Learning Research}, month = {03--06 Jan}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/r4/brochu03a/brochu03a.pdf}, url = {https://proceedings.mlr.press/r4/brochu03a.html}, abstract = {We present a novel, flexible, statistical approach to modeling music, images and text jointly. The technique is based on multi-modal mixture models and efficient computation using online EM. The learned models can be used to browse multimedia databases, to query on a multimedia database using any combination of music, images and text (lyrics and other contextual information), to annotate documents with music and images, and to find documents in a database similar to input text, music and/or graphics files.}, note = {Reissued by PMLR on 01 April 2021.} }
Endnote
%0 Conference Paper %T The Sound of an Album Cover: A Probabilistic Approach to Multimedia %A Eric Brochu %A Nando de Freitas %A Kejie Bao %B Proceedings of the Ninth International Workshop on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2003 %E Christopher M. Bishop %E Brendan J. Frey %F pmlr-vR4-brochu03a %I PMLR %P 49--56 %U https://proceedings.mlr.press/r4/brochu03a.html %V R4 %X We present a novel, flexible, statistical approach to modeling music, images and text jointly. The technique is based on multi-modal mixture models and efficient computation using online EM. The learned models can be used to browse multimedia databases, to query on a multimedia database using any combination of music, images and text (lyrics and other contextual information), to annotate documents with music and images, and to find documents in a database similar to input text, music and/or graphics files. %Z Reissued by PMLR on 01 April 2021.
APA
Brochu, E., de Freitas, N. & Bao, K.. (2003). The Sound of an Album Cover: A Probabilistic Approach to Multimedia. Proceedings of the Ninth International Workshop on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research R4:49-56 Available from https://proceedings.mlr.press/r4/brochu03a.html. Reissued by PMLR on 01 April 2021.

Related Material