Ryosuke Furuta

The University of Tokyo, Advanced Institute of Industrial Technology

Papers

Total Citations

H-Index

About

Ryosuke Furuta is a researcher specializing in computer vision, with a particular focus on 3D hand pose estimation and hand-object interaction analysis. His work sits at the intersection of human motion understanding, efficient machine learning, and egocentric video analysis — areas with far-reaching implications for augmented and virtual reality, robotics, and video understanding systems. Furuta's most notable contribution is his comprehensive survey on 3D hand pose estimation, which has garnered 19 citations since its publication in 2023. This work systematically examines the field through the lens of efficient annotation and learning strategies, offering researchers a structured roadmap for advancing the domain while reducing the often prohibitive costs of data labeling. His second prominent work addresses fine-grained affordance annotation in egocentric hand-object interaction videos, accumulating 12 citations and tackling a nuanced challenge: defining and annotating object affordances in ways that meaningfully capture human motor capacity and physical object properties. This research has direct applications in action anticipation and robot imitation learning. Together, Furuta's contributions reflect a commitment to bridging foundational computer vision challenges with practical, real-world applications, making him a valuable voice in the growing community of researchers advancing human-centric AI systems.