Masashi Hatano

I am a PhD student at Keio University under the guidance of Prof. Hideo Saito. Starting from this May, I conduct research at the University of Bristol as a visiting PhD student and working with Prof. Dima Damen.

My research interests span the broad area of machine learning, computer vision, egocentric vision, future forecasting, multimodal learning, and action recognition.

In 2023, I obtained a Master’s degree in computer science from Keio University, Japan, and an engineering degree from CentraleSupélec, France, as part of a double degree program.

News

Nov 2024	Visited VGG at the University of Oxford and presented my research!
Aug 2024	One paper accepted at HANDS@ECCV’24.
Aug 2024	One co-authored paper accepted at MMSports@ACMMM’24.
Jul 2024	One paper accepted at ECCV’24.
May 2024	Selected as a student eligible for support of BOOST: Broadening Opportunities for Outstanding young researchers and doctoral students in STrategic areas.
May 2024	Started a 1-year research visiting at the University of Bristol.
May 2024	One co-authored paper accepted at MICCAI’24 (early acceptance top 11%).
Dec 2023	Selected as a scholarship reciepient of Amano Institute of Technology Scholarships for Doctoral Programs in Graduate Schools.
Dec 2023	Received the acceptance for the JSPS Overseas Challenge Program for Young Researchers.
Jun 2023	J’ai assisté à la cérémonie de remise des diplômes ingénieurs à CentraleSupélec à Gif-sur-Yvette.

Publications

2024

Occlusion Free Multi-Object Tracking Extention using Multi-Camera for Sport

Momoe Yamane, Akimasa Kondo, Masashi Hatano, Ryosuke Hori, and 1 more author

In ACM International Workshop on Multimedia Content Analysis in Sports MMSports, 2024

[Paper]
Multimodal Cross-Domain Few-Shot Learning for Egocentric Action Recognition

Masashi Hatano, Ryo Hachiuma, Ryo Fujii, and Hideo Saito

In European Conference on Computer Vision, ECCV, 2024

[Paper] [Supplementary] [Code] [Project Page]
EgoSurgery-Phase: A Dataset of Surgical Phase Recognition from Egocentric Open Surgery Videos

Ryo Fujii, Masashi Hatano, Hideo Saito, and Hiroki Kajita

In International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI, 2024

[Paper] [Code]
EMAG: Ego-motion Aware and Generalizable 2D Hand Forecasting from Egocentric Videos

Masashi Hatano, Ryo Hachiuma, and Hideo Saito

In European Conference on Computer Vision Workshops, ECCVW, 2024

[Paper] [Supplementary] [Code] [Project Page]

2023

Trajectory Prediction in First-Person Video: Utilizing a Pre-Trained Bird’s-Eye View Model

Masashi Hatano, Ryo Hachiuma, and Hideo Saito

In International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP, 2023

[Paper]

Miscellaneous

Invited Talks

Multimodal Cross-Domain Few-Shot Learning for Egocentric Action Recognition @ VGG, University of Oxford
Multimodal Cross-Domain Few-Shot Learning for Egocentric Action Recognition @ MaVi, University of Bristol

Conference Reviewer

CVPR 2025

Journal Reviewer

International Journal of Computer Vision (IJCV)