Fangjun Wang

University of Science and Technology of China

Papers

Total Citations

H-Index

About

Fangjun Wang is a researcher whose work lies at the intersection of computer vision and robotics, with a particular focus on 6D object pose estimation. His most-cited paper, "CMA: Cross-modal attention for 6D object pose estimation" (2021, 22 citations), introduces a novel cross-modal attention mechanism that significantly improves the accuracy of object pose estimation by effectively fusing RGB and depth data. This contribution addresses a critical challenge in enabling robots to interact with objects in cluttered, real-world environments. Wang's approach leverages attention-based learning to align visual and geometric features, setting a new standard for robustness in pose estimation tasks. While his citation count reflects a growing recognition in the field, his work is particularly notable for its practical implications in augmented reality, autonomous manipulation, and industrial automation. By bridging the gap between 2D image understanding and 3D spatial reasoning, Wang has laid important groundwork for more reliable and adaptable robotic systems. His research continues to inspire further exploration into multimodal learning and its applications in perception-driven robotics.