Informations générales
Intitulé de l'offre : Postdoc position in Artificial Intelligence (M/W) (H/F)
Référence : UMR7357-HYESEO-006
Nombre de Postes : 1
Lieu de travail : STRASBOURG
Date de publication : mercredi 24 mai 2023
Type de contrat : CDD Scientifique
Durée du contrat : 12 mois
Date d'embauche prévue : 1 octobre 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
- Action-conditioned motion prediction / generation model of dressed human through deep learning over annotated motion datasets.
- End-to-end 4D human model reconstruction from 2D / 3D video input via optimal model fit.
Activités
- Research and development on one or more of the aforementioned themes: Predictive/generative model of dressed human, 4D human model reconstruction from 2D/3D video input.
- 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. Within the framework of a bi-national (with South Korea) and tri-institutional project HuMoCar (Photo-Realistic Human Modeling for Real-World Human Cognition by Care-Robots) between 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 specific goal is to make the performance of the vision-intelligence robust to large variations (in body shapes, motions,..) to occlusion (cloth, furniture, wall,..), and capable of understanding the interaction by developing a photo-realistic, physics-aware 4D human model.
The project will take place in MLMS (Machine Learning, Modélisation & Simulation, https://mlms.icube.unistra.fr) research team, located at the hospital site of the laboratory.
Contraintes et risques
One or two mid-term visiting research at ETRI (Daejeon, South Korea) is envisaged for a collaboration.
Informations complémentaires
http://igg.unistra.fr/People/seo/StudentsJoboffer_files/Postdoc_2023.pdf