PicSOM—content-based image retrieval with self-organizing maps
Pattern Recognition Letters - Selected papers from the 11th scandinavian conference on image analysis
Using Smoothed Data Histograms for Cluster Visualization in Self-Organizing Maps
ICANN '02 Proceedings of the International Conference on Artificial Neural Networks
Proceedings of the 3rd ACM/IEEE-CS joint conference on Digital libraries
An innovative three-dimensional user interface for exploring music collections enriched
MULTIMEDIA '06 Proceedings of the 14th annual ACM international conference on Multimedia
Music retrieval: a tutorial and review
Foundations and Trends in Information Retrieval
Analytic Comparison of Self-Organising Maps
WSOM '09 Proceedings of the 7th International Workshop on Advances in Self-Organizing Maps
Visualising class distribution on self-organising maps
ICANN'07 Proceedings of the 17th international conference on Artificial neural networks
Evaluating Color Descriptors for Object and Scene Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
Hi-index | 0.00 |
Digital audio has become an ubiquitously available medium, and for many consumers, it is the major distribution and storage form of music, accounting for a growing share of record sales. However, handling the ever growing size of both private and commercial collections becomes increasingly difficult. Users are often overwhelmed by the seemingly countless number of music tracks available. Computer algorithms that can understand and interpret characteristics of music, and organise and recommend them for and to their users can thus be of great assistance. Therefore, a magnitude of research projects has been devoted in the last decade to automatically to make the sound characteristics of music machine interpretable, to e.g. allow for automatic categorisation of music, or to recommend track which are similar to the ones a user likes. However, music is an inherently multi-modal type of data, and increasingly also other modalities of music have attracted interest from the community. The analysis of song lyrics and other textual data, such as websites or biographies associated with artists, together with social network data, has probably attracted most research in this area. Album covers are another dimensionality characteristic to the music - they are often carefully designed by artists to convey a message consistent with the music and image of a band. Studies have shown that customers use album cover art as a visual cue when browsing music in regular record stores. We thus present a study on similarities in album covers, and their relations to certain styles and genres of bands. To this end, we employ Self-Organising Maps together with various visualisation techniques to automatically organise a music collection, and compare the results obtained when using both features from the music and the album covers.