EventDr. Toshihiko Yamasaki

Attractiveness Computing using Artificial Intelligence

We have been trying to predict and even enhance the subjective attractiveness of images and videos by using deep neural networks (DNNs). DNNs are now being used not only for image recognition tasks but also for predicting attractiveness of the images such as image aesthetics, face attractiveness scores, etc. Our research focuses on more general and advanced problems by extending such researches: clarifying what contributes to the attractiveness score and how much they contribute to the attractiveness, and enhancing the attractiveness score by DNN-based processing. In our talk, we will introduce some successful cases such as presentation analysis, TV advertisement assessment, hash tag recommendation.

Bio: He received the B.S. degree, the M.S. degree, and the Ph.D. degree from The University of Tokyo in 1999, 2001, and 2004, respectively. He is currently an Associate Professor at Department of Information and Communication Engineering, Graduate School of Information Science and Technology, The University of Tokyo. He was a JSPS Fellow for Research Abroad and a visiting scientist at Cornell University from Feb. 2011 to Feb. 2013.His current research interests include multimedia big data analysis, pattern recognition, machine learning, and so on.