Donna Roy

Title: Donna Roy - Innovator in Semantic Image Retrieval

Introduction

Donna Roy is a prominent inventor based in Santa Clara, CA. She has made significant contributions to the field of image retrieval technology. Her innovative work focuses on enhancing the capabilities of neural networks through advanced data matching techniques.

Latest Patents

Donna Roy holds a patent for "Scalable semantic image retrieval with deep template matching." This patent presents approaches that facilitate semantic data matching, which is essential for selecting data from large unlabeled datasets to train neural networks. The technology is particularly useful in object detection scenarios, allowing for the identification of images within an unlabeled set, even when the object of interest occupies a small portion of the image or is surrounded by numerous other objects. The process involves extracting image features from specific regions of interest in a query image and comparing these features with images in an unlabeled dataset. Similarity scores are calculated, enabling the selection of the highest-scored images as training examples that are semantically similar to the object in the query image.

Career Highlights

Donna Roy is currently employed at Nvidia Corporation, a leading company in the field of graphics processing and artificial intelligence. Her work at Nvidia has positioned her as a key player in the development of cutting-edge technologies that leverage deep learning and image processing.

Collaborations

Throughout her career, Donna has collaborated with talented individuals such as Suraj Kothawade and Elmar Haussmann. These collaborations have further enriched her work and contributed to advancements in the field.

Conclusion

Donna Roy's innovative contributions to semantic image retrieval demonstrate her expertise and commitment to advancing technology. Her patent and work at Nvidia Corporation highlight her role as a significant figure in the field of artificial intelligence and image processing.