← Search

Dongfang Zhao

2 accepted papers

2026

Order-Preserving Dimension Reduction for Multimodal Semantic Embedding

AAAI 2026technical

Searching for the k-nearest neighbors in multimodal data retrieval is computationally expensive, particularly due to the inherent difficulty in comparing similarity measures across different modalities. Recent advances in multimodal machine learning address this issue by mapping data into a shared e

Cited by 0SourcePDFScholar
2025

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

IROS 2025

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

Cited by 0SourceScholar