Seminars and Events
Understanding Japanese Humanities through the Lens of Machine Intelligence
Event Details
From classifying handwritten digits to generating strings of text, the advances in data-driven machine intelligence 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 lead to interdisciplinary works including collections of artworks, quantitative approaches, and machine learning-based creativities. They, however, sometimes lack sufficient attention to certain humanities research topics, and it remains challenging to integrate these works into a comprehensive view.
In this talk, I’m going to present to you our works to bridge this gap in the direction of understanding humanities through the lens of machine intelligence. Particularly, we are focusing on Japanese humanities in our study as it is an important topic of culture study, calling for more effort in studying. We will be talking about two works, one is KaoKore: A Pre-modern Japanese Art Facial Expression Dataset, and another is Ukiyo-e Analysis and Creativity with Attribute and Geometry Annotation. Both works apply Machine Intelligence to traditional Japanese humanities topics
In this first work we propose a new dataset KaoKore which consists of faces extracted from pre-modern Japanese artwork,with its value both in quantitative and qualitative study. In the second work, we propose a holistic approach, with a large-scale Ukiyo-e dataset with coherent semantic labels and geometric annotations, and show its value in a quantitative study of Ukiyo-e paintings’ objects and styles. I hope this talk could shed some light on this interdisciplinary topic and provide some inspiration for future works.