Yoichi Sato

6

Papers

34

Total Citations

Papers (6)

Single-to-Dual-View Adaptation for Egocentric 3D Hand Pose Estimation

Gazing Into Missteps: Leveraging Eye-Gaze for Unsupervised Mistake Detection in Egocentric Videos of Skilled Human Activities

ActionVOS: Actions as Prompts for Video Object Segmentation

Generative Modeling of Shape-Dependent Self-Contact Human Poses

Egocentric Action-aware Inertial Localization in Point Clouds with Vision-Language Guidance

Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives