Informations générales
Intitulé de l'offre : Postdoc position in Artificial Intelligence (M/W) (H/F)
Référence : UMR7357-HYESEO-011
Nombre de Postes : 1
Lieu de travail : STRASBOURG
Date de publication : vendredi 15 septembre 2023
Type de contrat : CDD Scientifique
Durée du contrat : 12 mois
Date d'embauche prévue : 1 novembre 2023
Quotité de travail : Temps complet
Rémunération : 2833€/month gross minimum depending on the work experience
Niveau d'études souhaité : Niveau 8 - (Doctorat)
Expérience souhaitée : 1 à 4 années
Section(s) CN : Information sciences: processing, integrated hardware-software systems, robots, commands, images, content, interactions, signals and languages
Missions
Prediction/generation model of dressed humans and clothing, conditioned by the image/video.
Activités
- Research and development on one or more of the aforementioned themes: Predictive/generative model of dressed humans, human model, and reconstruction of human model and clothing from a video.
- Technical management and collaboration with other researchers (engineer, post-doc, permanent researchers) participating in the project.
- Possible supervision of a doctoral student.
Compétences
− PhD in Computer Science, Electronic & Electrical Engineering or in Applied Mathematics (2020 or later).
− Skills in efficient programming, communication, and algorithm design.
− Solid knowledge and experience in deep learning.
Contexte de travail
ICube Laboratory (The Engineering science, computer science and imaging laboratory) at the University of Strasbourg is a leading research center in Computer Science, with more than 300 permanent researchers, with the recently opened AI graduate school supported by the French government. Within the framework of a bi-national (with South Korea) and tri-institutional project (CNRS, INRIA and ETRI), we aim to push the current limits of robot vision in human cognition by care-robots in the in-house situation. Our global goal is to enhance the performance of the vision intelligence, making it resilient to significant variations (such as body shapes and motions) and capable of understanding and participating in the interaction. To achieve this, our emphasis will be on developing predictive models which, based on realistic, physics-informed 4D human models as well as a differentiable cloth simulator, will be capable of analysing and of reconstructing the human and his/her cloths from video, even with in the presence of significant level of occlusion or deformation. This project will take place in MLMS (Machine Learning, Modélisation & Simulation) research team, located at the hospital site of the ICube laboratory.
Contraintes et risques
One or two mid-term visiting research at ETRI (Daejeon, South Korea) is envisaged for a collaboration.