Postdoc Positions in Computer Vision/Deep Learning
26 Avril 2022
Catégorie : Post-doctorant
The Image Science and Computer Vision team of Hubert Curien laboratory (https://laboratoirehubertcurien.univ-st-etienne.fr/en/index.html) is looking for talents with skills and experience in video analysis and scene understanding, for two Postdoc positions (1 or 2 years) from October 1st 2022.
The first Postdoc will carry out research on developing tools and methods for scene understanding and 3D reconstruction from video recordings and multiple real-time captures. Several topics will be investigated: - pose and motion estimation, - tracking (and action parsing) from multi-view video recording, - body pose trajectories estimation, - analysis of movements and interactions between people, - transfer methods from sport activities to performing arts, - spatiotemporal 3D reconstruction and scene understanding, - reusable components for other use cases.
The second Postdoc will carry out research on developing tools and methods for human body pose and motion estimation, video summarization, and human sentiment analysis (facial expression analysis).
Both positions are offered in the frame of a Horizon Europe project PREMIERE (Performing arts in a new era: AI and XR tools for better understanding, preservation, enjoyment and accessibility) coordinated by Prof. KATSOUROS from Athena – Research and Innovation Center.
PREMIERE seeks to modernize the performing arts focusing on dance and theater by using advanced digital technologies to support the whole lifecycle of performances: from their production and curation by both amateurs and professionals, to their delivery and understanding from the audience, as well as their analysis and interpretation by art scholars. In doing so, PREMIERE will contribute to the following general goals: 1) Broaden accessibility to audiences that cannot attend live performances due to physical distance (international audience), health reasons (e.g. elderly, reduced mobility, immunocompromised), or economic reasons (low income), or environmental reasons (to limit the carbon impact of travel). 2) Enhance the understanding of present and past performances by audiences with diverse cultural, social, historical and educational backgrounds. 3) Enrich the creative process by adding new elements, dimensions and capabilities, offered by advanced digital technologies, while enabling international (and therefore inter-cultural) collaboration. 4) Increase the visibility of performances by supporting both spectators in searching for relevant content and producers/curators in communicating their work to the most relevant audiences. Accordingly, the overall objective of PREMIERE is to develop and validate a comprehensive ecosystem of digital applications, powered by leading edge AI, XR and 3D technologies, designed to fulfill the needs of diverse end-user communities involved in the main stages of the lifecycle of performing arts productions, including amateur and professional performers, performance art producers and curators, performance art spectators and scholars.
The recruited candidates will be responsible for conducting research within the PREMIERE project and for participating in the related Work Package activities. Starting from the analysis of the start-of-the-art models, the recruited candidates will be asked to study and design deep learning models tailored to tackle and solve problems related to domain adaptation and generalization, semi/self/un-supervised learning, learning with imbalance/few data or with (label) noisy data. We aim at tackling and validating proposed methods coping with performing arts datasets.
All the digital toolbox and other project outputs (such as training materials and capture protocols) done during the PREMIERE project will be open source and open access to reach the widest audience possible.
The ideal candidate has a PhD’s degree in computer vision, with excellent academic records and research experience. A strong background in machine learning, artificial intelligence, data mining, is desirable. Excellent programming skills, analytical problem solving and organizational abilities are required. Prior practical experience in computer vision is a plus. We are looking for passionate researchers who loves challenges and who are highly qualified and engaged to study, design, develop and validate video analysis methods based on deep learning approaches.
Students expecting to finalize their degree in the coming months are also welcome to apply.
Postdoctoral employees are full time employees of the University and paid a salary according to a uniform salary scale, adjusted in relation to the progress in education and professional experience.
Place of Work: Laboratory Hubert Curien, University Jean Monnet, Saint-Etienne, France
Applications should be sent by email to Prof. Alain Trémeau (firstname.lastname@example.org) and should include the following documents.
1. A cover letter stating the purpose of the application and a brief statement of why you believe that your background and goals are well-matched with the goals of this position
2. A Curriculum Vitae that includes at least a list of previous degrees, dates, and institution, transcripts for higher-education studies until most recent available
3. Copies of previous transcripts and degree certificates
4. A summary (1-2 pages) of the PhD’s and/or master’s thesis
5. A copy of previous publications and software samples, if any, and
6. Two reference letters and contact information for three reference persons
List of qualifications (eg. in Software development using Python, in development frameworks for machine learning such as TensorFlow/Keras and PyTorch, or for realtime image processing like OpenCV) and other documents that the applicant wishes to refer to should be enclosed with the application.
Very good English communication skills and reporting, autonomy and curiosity, ability to work in a highly collaborative environment, sense of initiative and rigour will be greatly appreciated.