Xiaoyu Yue

Papers

Total Citations

H-Index

About

Xiaoyu Yue is a rising researcher in computer vision, with a focus on advancing open-vocabulary and fine-grained visual understanding. Her most notable contribution is the introduction of **OV-PARTS**, a pioneering framework for **open-vocabulary part segmentation**—a task that enables models to segment and recognize diverse object parts using arbitrary text descriptions, rather than being limited to predefined categories. This work directly addresses a critical gap in the field, moving beyond object-level segmentation to the more granular and challenging domain of part-level recognition, which has direct applications in robotics, augmented reality, and fine-grained scene analysis. With her 2023 paper already garnering **5 citations** in its early stages, Yue’s research is quickly gaining traction for its practical impact. By tackling the intersection of open-vocabulary learning and part-level reasoning, she is helping to push the boundaries of how machines perceive and interact with the world, making her a promising voice in the next generation of vision research.