Xian Fang

Papers

Total Citations

H-Index

About

Xian Fang is a researcher whose work centers on advancing computer vision, particularly in the domain of salient object detection. His major contribution lies in the development of sophisticated deep learning architectures that fuse multimodal data for more accurate and robust visual understanding. Fang’s most-cited paper, "Boosting RGB-D salient object detection with adaptively cooperative dynamic fusion network" (2022), introduces a novel framework that dynamically integrates color (RGB) and depth (D) information. This approach addresses a critical challenge in the field: how to effectively leverage complementary cues from different modalities to highlight the most prominent objects in a scene, even under complex backgrounds or varying lighting conditions. By proposing an adaptively cooperative fusion mechanism, his work has provided a more flexible and powerful solution compared to static fusion methods. With 13 citations, this paper has already begun to influence subsequent research in RGB-D processing and attention-based models. Fang’s work is notable for its practical implications in areas like robotics, autonomous navigation, and augmented reality, where real-time, accurate object segmentation is essential. His contributions mark him as a promising voice in the evolving landscape of visual perception and deep learning.