Menghe Zhang

3D-AMTA: Occlusion-Aware Real-Time 3D Hand Pose Estimation with Auto Mask and Token-Specific Attention

Understanding hand motion from a single RGB image is challenging due to occlusions and high articulation. This paper presents 3D-AMTA, a transformer-based framework with Auto Mask and Token-specific Attention for occlusion-aware 3D hand pose estimation (HPE). We propose two novel architectural enhan