JST Presto Project
JST Presto Project
Summary. The development of measurement technology makes it possible to record multi-agent motions in various domains. However, it has been difficult to explain, manipulate, and make decisions for the experts in the real world (e.g, biology researchers and sports coaches). In this research, we will develop an artificial intelligence (AI) technology that can achieve the above requirements.
Keisuke Fujii, Naoya Takeishi, Kazushi Tsutsui, Emyo Fujioka, Nozomi Nishiumi, Ryoya Tanaka, Mika Fukushiro, Kaoru Ide, Hiroyoshi Kohno, Ken Yoda, Susumu Takahashi, Shizuko Hiryu, Yoshinobu Kawahara, Learning interaction rules from multi-animal trajectories via augmented behavioral models, Advances in Neural Information Processing Systems (NeurIPS'21), 34, 2021.12. [arXiv] [slide][openreview][code][Press EN/JP]
Tatsuya Yoshikawa, Kazushi Tsutsui, Kazuya Takeda, Keisuke Fujii, Extraction of swing motion contributing to prediction of shuttle drop position in badminton, 30th International Joint Conference on Artificial Intelligence (IJCAI-21) workshop on AI for Sports Analytics (AISA), 2021.8
Keisuke Fujii, Data-driven Analysis for Understanding Team Sports Behaviors (survey paper), Journal of Robotics and Mechatronics, 33(3) 505-514, 2021.6 [arXiv]