Ryo Fujii

Ryo Fujii

Data Scientist | Ph.D. Student

IBM | Keio University

About me

Ryo Fujii is a data scientist at IBM. His focus at IBM lies in applying natural language processing algorithms including generative models and mathematical optimization to customer’s businesses to solve their problems. He also works with Hideo Saito and Ryo Hachiuma at Keio University as a Ph.D. student. His research interest lies in trajectory prediction for autonomous systems and surgical video analysis.

Interests
  • Computer Vision
  • Machine Learning
  • Autonomous Driving
  • Surgical Video Analysis
Education

  • Ph.D. in Computer Science and Engineering, 2023-Present

    Keio University

  • M.S. in Computer Science and Engineering, 2020-2022

    Keio University

  • B.S. in Computer Science and Engineering, 2016-2020

    Keio University

Seletcted Publications

Weakly Semi-supervised Tool Detection in Minimally Invasive Surgery Videos
Ryo Fujii, Ryo Hachiuma, Hideo Saito
ICASSP 2024
ArXiv Paper Website Poster
Weakly Semi-supervised Tool Detection in Minimally Invasive Surgery Videos
Neural Implicit Event Generator for Motion Tracking
Mana Masuda, Yusuke Sekikawa, Ryo Fujii, Hideo Saito
ICRA 2022
ArXiv Paper
Neural Implicit Event Generator for Motion Tracking
A Two-Block RNN-based Trajectory Prediction from Incomplete Trajectory
Ryo Fujii, Jayakorn Vongkulbhisal, Ryo Hachiuma, Hideo Saito
IEEE Access 2021
ArXiv Paper
A Two-Block RNN-based Trajectory Prediction from Incomplete Trajectory
Toward Unsupervised 3d Point Cloud Anomaly Detection Using Variational Autoencoder
Mana Masuda, Ryo Hachiuma, Ryo Fujii, Hideo Saito, Yusuke Sekikawa
ICIP 2021
Code ArXiv Paper
Toward Unsupervised 3d Point Cloud Anomaly Detection Using Variational Autoencoder
Joint Inpainting of RGB and Depth Images by Generative Adversarial Network with a Late Fusion approach
Ryo Fujii, Ryo Hachiuma, Hideo Saito
ISMAR 2019
Paper Extented Paper Arxiv
Joint Inpainting of RGB and Depth Images by Generative Adversarial Network with a Late Fusion approach