Recently the ‘Million Song Dataset’, containing audio features and metadata for one million songs, was made available. In this paper, we build a convolutional network that is then trained to perform artist recognition, genre recognition and key detection. The network is tailored to summarize the audio features over musically significant timescales. It is infeasible to train the network on all a...

This paper is an investigation of theoretical issues pertaining to art and design graduates as they embark upon their training as teachers. The expressive, ‘confessional’ nature of selected forum posts in their virtual learning environment are analysed in relation to the students’ identity transformation into teachers. This transition is profound in the case of artist teachers, for whom the con...

Users in different countries may have different music preferences, possibly due to geographical, economic, linguistic, and cultural factors. Revealing the relationship between music preference and cultural socio-economic differences across countries is of great importance for music information retrieval in a cross-country or cross-cultural context. Existing works are usually based on small samp...

Takahiro Yamaguchi,a1 Dong Yeon Lee,b Akio Miyao,c Hikohiko Hirochika,c Gynheung An,b and Hiro-Yuki Hiranoad2 a Graduate School of Agricultural and Life Sciences, University of Tokyo, Bunkyo-ku, Tokyo 113-8657, Japan b Division of Molecular and Life Sciences, Pohang University of Science and Technology, Pohang 790-784, Republic of Korea c National Institute of Agrobiological Sciences, Kannondai...

This paper presents a system searching for semantic relations between web resources, in our case historical persons. The system is based on the ULAN metadata of some 100,000 persons and organizations.

In this paper, we analyze various methods used for semantic annotation and search in a collection of art and architecture images. We discuss the Art and Architecture Thesaurus, WordNet, ULAN and Iconclass ontology. Systems for searching and retrieval art and architecture image collections are presented. We explore if the MPEG 7 descriptors are useful for art and architecture image annotations. ...

In audio based music recommendation, a well known effect is the dominance of songs from the same artist as the query song in recommendation lists. We verify that this effect also exists in a very large data set at the scale of the world wide web (> 250000). Since our data set contains multiple albums from individual artists, we can also show that the album effect is relatively bigger than the a...

Linked Data has emerged as the preferred method for publishing and sharing cultural heritage data. One of the main challenges for museums is that the defacto standard ontology (CIDOC CRM) is complex and museums lack expertise in semantic web technologies. In this paper we describe the methodology and tools we used to create 5-star Linked Data for 14 American art museums with a team of 12 comput...

We work on converting the metadata of 13 American art museums and archives into Linked Data, to be able to integrate and query the resulting data. While there are many good sources of artist data, no single source covers all artists. We thus address the challenge of building a comprehensive knowledge graph of artists that we can then use to link the data from each of the individual museums. We ...

We discuss tools for calculating divergence-free fields for artistic particle simulations. We introduce a simple, fast divergence-free noise function which can be used for turbulence. We also describe how the interpolation technique used by the noise function can be used for calculating artist-controlled divergence-free fields. The artist can create realistic unbounded flow fields without the c...