舘野 将寿
Masatoshi Tateno
I am a second-year Ph.D. student at the Graduate School of Information Science and Technology, The University of Tokyo, advised by Prof. Yoichi Sato.
Before that, I graduated from the same department in 2022 and got Master’s Degree of Information Science and Technology. I also worked as Research Assistant at AIST (2023-2024).
Email: masatate[at]iis.u-tokyo.ac.jp
News
-
(July 2026)
My new paper Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues? is released on arxiv.
-
(June 2026)
Our new paper YUBI: Yielding Universal Bidigital Interface for Bimanual Dexterous Manipulation at Scale is released on arxiv.
-
(April 2026)
🔥 CVPR 2026 — My paper in CVPR 2026 is selected as a highlight paper ✨
-
(Feb 2026)
🔥 CVPR 2026 — My new paper HanDyVQA: A Video QA Benchmark for Fine-Grained Hand-Object Interaction Dynamics got accepted to CVPR 2026 🎊. See you in Denver!
-
(Dec 2025)
My new paper HanDyVQA: A Video QA Benchmark for Fine-Grained Hand-Object Interaction Dynamics is released on arxiv.
-
(Oct 2024)
🔥 WACV 2025 — My new paper Learning Multiple Object States from Actions via Large Language Models has been accepted by WACV 2025 🎉. See you in Arizona!
-
(Sept 2024)
I started a one-year visit to University of Bristol, collaborating with Prof. Dima Damen.
- (July 2024)
Research Interest
- Human action and object state recognition in videos
- Vision and language
- First-person vision
Publication
Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
Masatoshi Tateno, Alexandros Stergiou, Risa Shinoda, Yoichi Sato, Dima Damen
arXiv 2026
YUBI: Yielding Universal Bidigital Interface for Bimanual Dexterous Manipulation at Scale
Takehiko Ohkawa, Jumpei Arima, Yuki Noguchi, Masatoshi Tateno, ..., Kei Ota
Beyond Teleoperation Workshop @ ICRA 2026
HanDyVQA: A Video QA Benchmark for Fine-Grained Hand-Object Interaction Dynamics
Masatoshi Tateno, Gido Kato, Hirokatsu Kataoka, Yoichi Sato, Takuma Yagi
CVPR 2026 - Highlight ✨
Learning Multiple Object States from Actions via Large Language Models
Masatoshi Tateno, Takuma Yagi, Ryosuke Furuta, Yoichi Sato
WACV 2025
Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives
Kristen Grauman, Andrew Westbry, Lorenzo Torresani, Kris Kitani, Jitendra Malik, ..., Masatoshi Tateno, ..., Michael Wray
CVPR 2024