[visionlist] [jobs] Idiap/EPFL (Switzerland): PhD position in multimodal emotion and sentiment analysis.

Jean-Marc Odobez odobez at idiap.ch
Mon Mar 28 10:10:52 -04 2022


Please forward to anyone potentially interested. 


Jean-Marc Odobez, 
IDIAP Senior Researcher, Head of the Perception and Activity Understanding group
EPFL Senior Researcher  (EPFL MER)
IDIAP Research Institute (http://www.idiap.ch)
Tel: +41 (0)27 721 77 26
Web:  http://www.idiap.ch/~odobez


[jobs] Idiap/EPFL (Switzerland):  PhD position in multimodal emotion and sentiment analysis.
Position description

The Idiap Perception and Activity Understanding group seeks one highly motivated PhD candidate to work on the development of a multimodal non-verbal cue extraction platform (gaze, head gestures, emotion, speaking status) and its exploitation for different applications, like HCI, HRI, multimodal sentiment analysis, or mental health monitoring. The research will be focused on some of the above topics and will investigate deep learning models and methods (domain adaptation, unsupervised or weakly supervised learning; attention-based neural networks and transformers) to improve cue extraction or user state inference. Experiments will be conducted on project data (e.g. datasets of behaviors and robot-children interactions) as well as standard datasets from the computer vision and multimodal communities (gaze, emotion; sentiment analysis or health monitoring). 

The work will be primarily done in the context of the ePartner project, a swiss and dutch project aiming at developing and evaluating personalized child health (care) solutions contributing to the early detection of health problems in primary school children and providing effective tailored (preventive) interventions using digital tools (tablets; avatar and robot buddies). The role of Idiap in this project is to develop robust non-verbal cue extraction tools along with some analysis of children's behavior. The recruited student will work with a research associate on the project and in collaboration with project partners (Eyeware SA, Delft University of Technology).
Sought profile

The ideal PhD candidate should hold a MS degree in computer science, engineering, physics or applied mathematics. S/he should have a good background in statistics, linear algebra, machine learning. Experience in computer vision and deep learning are definitely a plus. Strong programming skills (Python, C/C++, and scripting in a Linux environment) are expected. The successful applicant will have good written and oral communication skills.

The candidate should have a genuine interest in human-centered computing and the desire to work towards effective solutions in this domain in collaboration with project partners. 

The selected candidate will become doctoral students at the Ecole Polytechnique Fédérale de Lausanne (EPFL) provided acceptance by the Electrical Engineering Doctoral School (EDEE) of EPFL (http://phd.epfl.ch/applicants <http://phd.epfl.ch/applicants>). 

The salary follows the EPFL standards and is internationally competitive. Starting date is immediate, and interviews will start upon reception of applications until the position is filled.

Interested candidates are invited to submit a cover letter explaining the suitability of their profile, a detailed CV, and the names of three references at


-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://visionscience.com/pipermail/visionlist_visionscience.com/attachments/20220328/b3bb887a/attachment-0001.html>

More information about the visionlist mailing list