Albert Gordo Soldevila

Title: Albert Gordo Soldevila: Innovator in Image Retrieval and Semantic Comparisons

Introduction

Albert Gordo Soldevila is a prominent inventor based in Grenoble, France. He has made significant contributions to the fields of image retrieval and semantic analysis through his innovative patents. With a total of 11 patents to his name, Soldevila continues to push the boundaries of technology.

Latest Patents

One of his latest patents is titled "Instance-level image retrieval with a region proposal network." This method involves detecting objects in input images by generating an input image vector through regional maximum activations of convolutions (R-MAC) using a convolutional neural network (CNN). The process includes applying a region proposal network (RPN) to the CNN's output. Another notable patent is "Latent embeddings for word images and their semantics." This system allows for semantic comparisons between word images and concepts without the need for transcribing text content. The neural network is trained to minimize ranking loss, ensuring relevant concepts are prioritized.

Career Highlights

Throughout his career, Albert Gordo Soldevila has worked with notable companies such as Xerox Corporation and Conduent Business Services, LLC. His experience in these organizations has contributed to his expertise in image processing and machine learning.

Collaborations

Some of his notable coworkers include Florent C Perronnin and Jon Almazan. Their collaboration has likely fostered innovative ideas and advancements in their respective fields.

Conclusion

Albert Gordo Soldevila is a distinguished inventor whose work in image retrieval and semantic comparisons has made a significant impact on technology. His innovative patents and collaborations highlight his dedication to advancing the field.