ChairesIA_2019_1 - Chaires de recherche et d'enseignement en Intelligence Artificielle - vague 1 de l'édition 2019

DEEP-VISION – DEEP-VISION

Submission summary

The project is led by Frederic Jurie. Frederic Jurie has been full Professor (PRCE French grade) at the University of Caen Normandy, having been a researcher at CNRS from 1994 to 2004 at UMR LASMEA in Clermont-Ferrand, then from 2004 to 2007 at the INRIA Rhône-Alpes center affiliated with Cordelia Schmid's research group.

The research work of the applicant lies in the field of Computer Vision and Machine Learning. It is related to the interpretation of images and videos: image recognition, image classification and object detection in images. One of the greatest challenges of Computer Vision is the development of models that allow the learning and inference of image contents (objects, object relationships, actions, image descriptions in natural languages, etc.). The applicant has developed statistical models which have contributed to the rise of Machine Learning for Computer Vision.

He has authored or co-authored 27 articles in international journals and more than 140 articles in major international conferences. According to Google Scholar, these articles received more than 10k citations for an H-index of 45 (35 since 2014).

The work program of the Chair will be conducted in 4 directions, all applied to the domain of Computer Vision : i) privacy-aware federated learning ii) explainable deep learning iii) frugal and efficient deep learning algorithms iv) robust and trustable deep learning algorithms. For each direction, the objectives, the methodology, the originality and the feasibility of the work are given in the proposal. Detailed topics for 5 PhDs and 6 postdocs are also presented in the proposal. Regarding feasibility, computational resources will be provided by CRIANN. The candidate agrees to spend 80% of his research time on the project.

Regarding financial aspects, the requested funding is of 510k€ (including management fees), representing 35% of the total cost (1417k€). The Chair will be co-funded by Safran (33%), Région Normandie (14%) and the University of Caen Normandie (17%). The budget will be used mainly to fund 5 PhD students and 4 postdoctoral fellows.

Project coordination

Frédéric Jurie (Groupe de recherche en Informatique, Image, Automatique et Instrumentation de Caen Unité de recherche)

The author of this summary is the project coordinator, who is responsible for the content of this summary. The ANR declines any responsibility as for its contents.

Partner

GREYC Groupe de recherche en Informatique, Image, Automatique et Instrumentation de Caen Unité de recherche

Help of the ANR 509,760 euros
Beginning and duration of the scientific project: August 2020 - 48 Months

Useful links

Explorez notre base de projets financés

 

 

ANR makes available its datasets on funded projects, click here to find more.

Sign up for the latest news:
Subscribe to our newsletter