Francisco Velasco Morente
Papers
2
Total Citations
12
H-Index
2
About
Francisco Velasco Morente is a researcher whose work bridges artificial intelligence and geometric modeling, with key contributions in deep-learning object detection and qualitative shape description. His most cited paper, "How efficient deep-learning object detectors are?" (2019, 10 citations), critically evaluates the performance and computational efficiency of modern object detection algorithms, offering insights that guide practitioners in selecting optimal models for real-world applications. This work reflects his interest in making AI systems more practical and resource-aware. Earlier, Velasco Morente developed a formal qualitative shape description scheme (2011, 2 citations) that enables the generation of new manufactured shapes from a set of given polygons through juxtaposition operations. This theoretical framework, applicable to both regular and non-regular polygons, provides a structured approach to computational design and manufacturing. While his citation counts are modest, his research demonstrates a thoughtful progression from foundational geometric theory to applied deep learning, showcasing versatility in tackling problems across computer vision and computational geometry. His work on shape description offers a unique tool for automated design, highlighting his potential for future impact in AI-driven manufacturing and object recognition.
Research Focus
Key Achievements
Top Papers
- 1How efficient deep-learning object detectors are?10 citations · 2019
- 2