Xuan-Tung Dinh
Papers
1
Total Citations
1
H-Index
1
About
Xuan-Tung Dinh is a computer vision researcher whose work centers on advancing object pose estimation, particularly for hand-held objects in interactive environments. His key research areas include multimodal fusion, robotic manipulation, and augmented reality. Dinh's most notable contribution is the development of a vote-based multimodal fusion framework that integrates RGB and depth data to robustly estimate the pose of objects held in human hands—a critical challenge for human-robot interaction and AR applications. This work, published in 2025, has already garnered attention with its first citation, signaling early impact in a rapidly evolving field. By addressing the inherent difficulties of occlusion and dynamic hand-object interactions, Dinh's approach offers a practical pathway for more intuitive robotic grasping and seamless augmented reality experiences. His research sits at the intersection of computer vision and robotics, promising to enhance how machines perceive and interact with the physical world. As his citation count grows, Dinh is establishing himself as an emerging voice in multimodal perception for real-world applications.
Research Focus
Key Achievements
Top Papers
- 1Vote-based multimodal fusion for hand-held object pose estimation1 citations · 2025