I am a first-year PhD student at Aoki lab in Keio University in Japan.

My specialties are computer vision, wireless sensing, and deep learning. Especially, I have a strong interest in building privacy-conscious ML systems, such as non-image-based human sensing.

I am primarily advised by Prof. Yoshimitsu Aoki and Dr. Mariko Isogawa.

I will be staying at Carnegie Mellon University for one year starting in June 2025, under the supervision of Prof. Katerina Fragkiadaki. There, I plan to conduct research on human motion and physics engines.

I'm currently working part-time job at Tenchijin and engaged in geospatial data analysis. Previously, I was doing research internship at Preferred Networks where I conducted research on communication-efficient federated learning in healthcare.

Research opportunities: I am looking for research internships in Japan or abroad. I am also happy to answer questions about my research. If you are interested, please send me an email.

CV | E-Mail | Google Scholar | Github | Twitter |

Formula-Supervised Sound Event Detection: Pre-Training Without Real Data
Yuto Shibata, Keitaro Tanaka, Yoshiaki Bando, Hirokatsu Kataoka, Yoshimitsu Aoki
ICASSP2025
project | paper |

Anatomical Three-Dimensional Style Transfer Enabling Efficient Federated Learning with Extremely Low Communication Costs
Yuto Shibata, Yasunori Kudo, Yohei Sugawara
NeurIPS2024, AIM-FM Workshop
arxiv |

Acoustic-based 3D Human Pose Estimation Robust to Human Position
Yusuke Oumi, Yuto Shibata, Go Irie, Akisato Kimura, Yoshimitsu Aoki, Mariko Isogawa
BMVC 2024
arxiv |

Listening Human Behavior: 3D Human Pose Estimation With Acoustic Signals
Yuto Shibata, Yutaka Kawashima, Mariko Isogawa, Go Irie, Akisato Kimura, Yoshimitsu Aoki
CVPR2023
project | paper | code

Template credits: Unnat, Jon