Jérôme Revaud

Title: Innovations of Inventor Jérôme Revaud

Introduction

Jérôme Revaud is a notable inventor based in Meylan, France. He has made significant contributions to the field of technology, particularly in the area of convolutional neural networks. With a total of 2 patents, his work focuses on advanced methods for image processing and action classification in videos.

Latest Patents

One of Jérôme Revaud's latest patents is titled "Systems and methods for detecting a point of interest change using a convolutional neural network." This innovative method involves detecting changes in points of interest (POI) by utilizing a convolutional neural network (CNN) of a three-stream Siamese type. The process includes generating triplets of training POI images, computing descriptors for input images, and selectively detecting changes based on similarity scores.

Another significant patent is "System and method for training a convolutional neural network and classifying an action performed by a subject in a video using the trained convolutional neural network." This method trains a CNN to classify actions in videos by generating heat maps for key points of subjects, colorizing these maps based on the relative time of frames, and aggregating them to represent the evolution of position estimations throughout the video.

Career Highlights

Jérôme Revaud is currently employed at Naver Corporation, where he continues to develop innovative technologies. His expertise in convolutional neural networks has positioned him as a key player in the advancement of image processing techniques.

Collaborations

Throughout his career, Jérôme has collaborated with talented individuals such as Vasileios Choutas and Philippe Weinzaepfel. These collaborations have further enhanced his research and development efforts in the field.

Conclusion

Jérôme Revaud's contributions to technology through his patents and work at Naver Corporation highlight his innovative spirit and dedication to advancing the field of convolutional neural networks. His work continues to influence the way we understand and process visual information.