We are seeking an outstanding postdoctoral research fellow with experience in deep learning / machine learning to work with us at GREYC laboratory (Caen , France) on a project investigating the design of algorithms for 3D gesture recognition.
The postdoctoral position is funded under the research project IGIL supported by the Region Normandy (France). The IGIL project gathers companies, engineering schools and universities around the design of new generation human/computer interfaces using tactile and non tactile recognition of gestures.
The present post doc is focused on non tactile interactions by the recognition of gestures implying both hands and arms.
3D gesture recognition is becoming more and more popular and is now integrated in commercial solutions such as gesture control in cars like BMW. However, gesture recognition may be applied in a much wider set of applications where complex interactions (which can not be easily performed by voice) occur and where a tactile contact with the screen is not possible or not convenient. The IGIL project falls within that line of research and aims at developing a generic and innovative intelligent 3D gesture recognition system able to recognized complex gestures made by both hands with an identification of individual fingers.
Objectives and challenges:
The project will be based on available commercial tools to extract the skeleton of the arms / fingers. This point is thus not an objective of the post doc who will focus his work on the recognition step.
The first step will consist to assimilate the methods and algorithms for gesture recognition and prediction already developed by the team. Based on these methods, the postdoc will have to develop methods for online gesture recognition. This last step includes the conjoint recognition of gestures and the segmentation of the gesture stream.
As previously mentioned , the position will start by a state of the art and an understanding of the deep learning methods already developed by the team. This first step should take 2 months and will allow to provide first results to the other partners of the project. The second step, evaluated to 11 months will consist in designing a deep learning architecture and to train it in order to perform online recognition of gestures. The last step, evaluated to 1 month, will consists in designing a functional prototype and to evaluate its performances (in terms of size of the training set, precision and recall) to be distributed among the members of the project.
Caen, France in the GREYC UMR CNRS laboratory. Situated in the
Normandy region of France close to the sea and about 240km west
of Paris the city still has many old quarters, a population of
around 120,000 the city area has roughly 250,000 inhabitants.
Interested candidates should submit their application to
Please include in your application email one Curriculum Vitae, one statement of research letter explaining your interest and your skills for this position, and 2 reference letters (all in a single pdf file). Applications will be admitted until the position is filled.
(c) GdR 720 ISIS - CNRS - 2011-2019.