The University of Tokyo · Institute of Industrial Science · 特任助教

Research keywords3D human pose estimation・6D object pose estimation・test-time adaptation・gaze estimation・egocentric hand pose・robotic pick-and-place・implicit orientation learning・multimodal failure handling

This is a public-data preview. Personalized fit, contact angles, and saved workflows require sign-in.

• Hierarchical Temporal Transformer for 3D Hand Pose Estimation and Action Recognition from Egocentric RGB Videos.
• Generative Hierarchical Temporal Transformer for Hand Pose and Action Modeling.
• Data-driven Head Motion Generation through Natural Gaze-Head Coordination.
• DISP6D: Disentangled Implicit Shape and Pose Learning for Scalable 6D Pose Estimation.

• Official profile
• ORCID