PhD position in computer vision and machine learning for multimodal emotion and sentiment analysis at Idiap, Switzerland F/M

About Idiap

Idiap is an independent, not-for-profit, research institute recognized and funded by the Swiss Federal Government, the State of Valais, and the City of Martigny, and is academically affiliated with EPFL and University of Geneva.

Idiap offers competitive salaries and conditions at all levels in a young, high-quality, dynamic, and multicultural environment. Idiap is an equal opportunity employer and is actively involved in the "Advancement of Women in Science" European initiative. The Institute seeks to maintain a principle of open competition (on the basis of merit) to appoint the best candidate, provides equal opportunity for all candidates, and equally encourage both genders to apply. Employment at Idiap is thus based solely on a person's merit and qualifications directly related to professional competence. Idiap does not discriminate against any employee or applicant because of race, color, religion, gender, sexual orientation, gender identity/expression, national origin, disability, age, marital status, pregnancy, or any other basis protected by law.

Idiap is located in the town of Martigny in Valais, a scenic region in the south of Switzerland, surrounded by the highest mountains of Europe, and offering exceptional quality of life, exciting recreational activities, including hiking, climbing and skiing, as well as varied cultural activities. It is within close proximity to Lausanne and Geneva. Although Idiap is located in the French part of Switzerland, English is the official working language. Free French lessons are also provided on a complimentary basis.

For frequently asked questions (FAQs) about living in Switzerland, please go to https://www.idiap.ch/en/faq

Job 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).

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.

Required languages

• English - Level advanced
• French - Level beginner

Réf: 3911af4d-fabd-46ce-589d-08da01c9ff8a