Jorge Calvo-Zaragoza
Papers
3
Total Citations
9
H-Index
2
About
Jorge Calvo-Zaragoza is a researcher at the forefront of computer vision and robotics, specializing in domain adaptation and generalization for visual recognition systems. His work addresses a critical challenge in deep learning: the performance drop that occurs when models trained on one dataset are applied to new, unseen environments. Calvo-Zaragoza’s major contributions center on developing robust algorithms that enable machines to recognize objects—particularly kitchen utensils—across varying contexts, lighting conditions, and robotic platforms. His most cited work, "Kurcuma: a kitchen utensil recognition collection for unsupervised domain adaptation" (2023, 5 citations), introduces a benchmark dataset that has become a key resource for advancing unsupervised domain adaptation in robotics. Complementing this, his studies on domain generalization (2023, 2 citations) and domain adaptation in robotics (2022, 2 citations) provide foundational insights into how models can maintain accuracy when faced with distribution shifts. By tackling the practical problem of utensil recognition—a critical skill for household robots—Calvo-Zaragoza’s research bridges the gap between theoretical domain adaptation and real-world deployment, making his work highly relevant for students and engineers developing resilient vision systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3Evaluating Domain Generalization in Kitchen Utensils Classification2 citations · 2023