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.
Yingtao Tian is a Research Software Engineer in Google Brain Tokyo. He obtained his PhD in Computer Science at Stony Brook University and B.S. in Computer Science and Technology at Fudan University. His research interests lie in generative models and representation learning, as well as their applications in image generation, natural language processing, knowledge base modeling, social network modeling, bioinformatics. He is also interested in evolution strategies and the interdisciplinary research of machine intelligence and humanities research.
YOU ONLY NEED TO REGISTER ONCE TO ATTEND THE ENTIRE SERIES - We will send you email announcements with details of the upcoming speakers.
Register in advance for this webinar: https://usc.zoom.us/webinar/register/WN__0VhakI6Q6i3JsasdmNWcA
After registering, you will receive an email confirmation containing information about joining the Zoom webinar.
The recording for this AI Seminar talk will be posted on our USC/ISI YouTube page within 1-2 business days: https://www.youtube.com/user/USCISI
Host: Muhao Chen, POC: Alma Nava