Jose J. Valero-Mas
Papers
2
Total Citations
7
H-Index
2
About
Jose J. Valero-Mas is a researcher at the forefront of computer vision and robotics, specializing in domain adaptation and object recognition. His work addresses a critical challenge in deploying deep learning models in real-world robotic settings: the performance degradation caused by mismatched training and application data distributions. Valero-Mas’s major contributions center on developing robust recognition systems for kitchen utensils, a domain with high practical relevance for domestic robotics. His most-cited paper, "Kurcuma: a kitchen utensil recognition collection for unsupervised domain adaptation" (2023, 5 citations), introduces a benchmark dataset specifically designed to evaluate unsupervised domain adaptation techniques, enabling models to transfer knowledge across different visual environments without labeled target data. This work, alongside his earlier study on domain adaptation in robotics (2022, 2 citations), demonstrates his focus on bridging the gap between controlled lab conditions and messy, real-world scenarios. By tackling the domain shift problem in object recognition, Valero-Mas is helping to make robotic assistants more adaptable and reliable in everyday human environments, a key step toward practical home automation.
Research Focus
Key Achievements
Top Papers
- 1
- 2