From classifying handwritten digits to generating strings of text, the datasets which have received long-time focus from the machine learning community vary greatly in their subject matter. This has motivated a renewed interest in building datasets which are socially and culturally relevant, so that algorithmic research may have a more direct and immediate impact on society. One such area is in history and the humanities, where better and relevant machine learning models can accelerate research across various fields. To this end, newly released benchmarks [3] and models [4] have been proposed for transcribing historical Japanese cursive writing, yet for the field as a whole using machine learning for historical Japanese artworks still remains largely uncharted. To bridge this gap, in this work we propose a new dataset KaoKore 1 which consists of faces extracted from pre-modern Japanese artwork. We demonstrate its value as both a dataset for image classification as well as a creative and artistic dataset, which we explore using generative models.

No abstract

The present paper aims at designing a monitoring framework for a yet new interdisciplinary research and education program in Japan, "Cultural Resources Studies.", "Bunkashigengaku" in Japanese. We analyze the linkage between a university, an academic association, and the practitioners' institutions closely related with cultural resources through the mining of the principal texts produced by them. Our findings reveal the complicated relations among these stakeholder institutions, and attest to the importance of the revision cycle for the advance of interdisciplinary studies.