ORGANISATION/COMPANYUniversité de Paris
RESEARCH FIELDComputer science
RESEARCHER PROFILEFirst Stage Researcher (R1)
APPLICATION DEADLINE15/02/2022 00:00 - Europe/Brussels
LOCATIONFrance › PARIS
TYPE OF CONTRACTTemporary
HOURS PER WEEK37.5
OFFER STARTING DATE15/02/2022
Post-doc – Digital Engineering for the Humanities/Computer Vision
The LARCA laboratory has one open post-doc position in computer vision, in the specific field of image analysis and pattern recognition
Duration: 16 months
Position available from: As soon as possible, to be discussed with the successful candidate ideally February 2022 and for up to 16 months.
• Candidates with a completed Phd: approximately 2100 € / month (net income)
Hardware and software will be paid for by the lab.
Place: LARCA/LIPADE, Université de Paris, France - Remote work complemented by regular meetings (both online and in Paris) can be discussed with the hiring committee.
Specialty: Computer Science/Image Processing/Document Analysis/Pattern Recognition/Deep Learning/ Digital Engineering for the Humanities
Contact: Karl Gosselet et Daniel Foliard
The LARCA Lab is leading a project in digital humanities with focus on the history of photography. The post-doc will join the EyCon project (Early Conflict Photography and Visual AI). The objective is to create innovative tools to index and interact with a large corpus of photographs documenting armed violence between 1890 and 1918. The project is supported by a consortium of archival institutions in France and in the UK. The EyCon team is made of 6 researchers and engineers. The project is funded by an Idex grant as well as by an AHRC/Labex Passés dans le Présent joint grant. The successful candidate will be co-supervised by members of the LIPADE computer science laboratory at the University of Paris (http://lipade.mi.parisdescartes.fr/?page_id=248&lang=fr). The successful candidate will join a team that includes one data architect and two other postdocs.
The successful candidate will apply automated algorithms from the field of Artificial Intelligence (AI) to support historical and archival investigation. They will design approaches to extract relevant information in early war pictures and to understand their content. They will have to experiment with transfer, semi-supervised and unsupervised learning to enrich EyCon’s photographic database with descriptive metadata and enable users to navigate a large visual data set. The candidate should be able to apply multimodal deep learning to the dataset (textual and visual). The candidate will work on improving:
- the detection and understanding of the scenery (naval/ground warfare, relief, interior/exterior scenes)
- the detection and understanding of the context of the scene (battle, before/after combat)
-object/person detection and recognition within an ethical AI framework (weaponry, women in conflicts, children in conflicts, colonial troops, animal in conflicts)
The candidate will implement dedicated tools to collect ground truth annotations from user partners of the project’s consortium. They will also design evaluation protocols.
Candidates must have an MA or a completed PhD as well as research experience in deep learning, image recognition and analysis, pattern recognition.
• Excellent programming skills mastering at Python and programming skills in other languages Java, C/C++
• Good teamwork skills
• Good writing skills and proficiency in written and spoken English (French is not a requirement)
Candidates should send a CV and a motivation letter to Karl Gosselet email@example.com
EURAXESS offer ID: 725873
The responsibility for the jobs published on this website, including the job description, lies entirely with the publishing institutions. The application is handled uniquely by the employer, who is also fully responsible for the recruitment and selection processes.
Please contact firstname.lastname@example.org if you wish to download all jobs in XML.