Employer Active
Job Alert
You will be updated with latest job alerts via emailJob Alert
You will be updated with latest job alerts via emailNot Disclosed
Salary Not Disclosed
1 Vacancy
The Perception and Activity Understanding group seeks two highly motivated PhD students to join an innovative SNSF funded project focused on developing advanced AI models for real world social behavior understanding. While current computational attention models have traditionally focused on framing the task as a pure machine learning problem predicting the pixel 2D gaze target location of a scene person from an image this project aims to capture the broader phenomenological aspects of where and why people look integrating gaze with other social cues in natural dynamic environments. This contrasts with previous studies which had modeled gaze in tandem with other behavioral cues only in very restricted settings.
Leveraging cuttingedge deep learning methods including recent PAU team contributions the project will analyze complex social interactions in daily scenes. This includes both individuallevel cues (e.g. gaze target head gestures emotions attentiveness) and interpersonal dynamics (e.g. social gaze group identification conversational activities) through a unified multimodal multitask framework.
Successful candidates will work on key tasks such as dataset creation model design and benchmarking addressing these challenges in diverse unstructured settings. Main research areas include: 1 unified deep learning for head facial and upper body behavior recognition including humanobject interactions and audio processing; 2 models for attention states and social relations analysis; and 3 machine learning strategies such as multitask learning unsupervised learning and distillation to unify the modeling of these social behaviors.
The ideal PhD candidates will hold an MS degree in computer science engineering physics or applied mathematics. A solid foundation in statistics linear algebra signal processing machine learning and programming is essential with mandatory experience in deep learning. Successful applicants will demonstrate strong analytical abilities and excellent written and oral communication skills.
These PhD positions are fully funded for 4 years contingent on steady progress and are expected to lead to a PhD dissertation. Selected candidates will be enrolled as doctoral students at EPFL subject to acceptance by the Electrical Engineering Doctoral School (EDEE) at EPFL The anticipated start date is within the first semester of 2025 with salaries according to EPFL standards.
Screening of applications will begin on December 1 2024 and will continue until the positions are filled.
How to apply
Please provide the following information as two separate pdf files:
For information you can contact Dr JeanMarc Odobez .
Application deadline
Screening of applications will begin on December 1 2024 and will continue until the positions are filled.
Idiap is a research institute of national importance that engages in fundamental research education and technology transfer in artificial intelligence machine learning and signal processing. Idiap offers competitive salaries and conditions in a young highquality dynamic and multicultural environment. 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. English is the official working language.
At Idiap we place great emphasis on diversity and we know diversity fosters creativity and innovation. We are committed to equality of opportunity to being fair and inclusive and to being a place where we all belong. Employment at Idiap is based solely on a persons merit and qualifications. 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.
Rf: 284d85a8ec4e435d8eb47793bf7efd64
Full-Time