PhD student on Computer Vision algorithm and Interfaces for collaborations with Historians teams

École nationale des ponts et chaussées; France; Hybride; EUR 30 000 - 40 000; Plein temps

Résumé du poste

A leading French engineering school is offering a 3-year PhD position in Computer Vision and Machine Learning. The role involves developing algorithms to analyze visual structures in collaboration with historians. Applicants should have a Master's degree and relevant experience. The position is full-time, with options for remote work two days a week, based in CHAMPS-sur-MARNE, France.

Qualifications

• Track record of publications in top conferences/journals.
• Experience developing Computer Vision algorithms.
• Experience collaborating with non-experts, ideally historians.

Responsabilités

• Work independently and with external collaborators.
• Produce, publish, and present research results.

Connaissances

Computer Vision

Machine Learning

Digital Humanities

Team collaboration

Web Interface Design

Formation

Master degree in Computer Vision / Machine Learning / Digital Humanities

Description du poste

Organisation/Company École nationale des ponts et chaussées Research Field Computer science Researcher Profile First Stage Researcher (R1) Positions PhD Positions Country France Application Deadline 15 Nov 2025 - 00:00 (Europe/Paris) Type of Contract Temporary Job Status Full-time Hours Per Week 35 Offer Starting Date 1 Jan 2026 Is the job funded through the EU Research Framework Programme? Horizon Europe - ERC Reference Number 101076028 Is the Job related to staff position within a Research Infrastructure? No

Offer Description

Call for a 3-year PhD position, at École Nationale des Ponts et Chaussées, IP Paris, under the supervision of Mathieu Aubry , in the context of the DISCOVER ERC project on "Discovering and Analyzing Visual Structures".

This PhD project aims to develop Computer Vision algorithm and Interfaces for collaborations with Historians teams. Specifically, the research will focus on structured data with clear repeated patterns, such as characters in a text, or text structured in a table. Interdisciplinarity will be at the center of the work, and both interaction with historian teams and the design of web platform that enable the historians to leverage and provide feedback on the results of the algorithm will be critical.

1. Institution presentation

École des Ponts ParisTech is an institution of higher education and research in the field of science, engineering and economics. Under the supervision of the Ministry of Ecological and Solidarity Transition (MTES) and with an EPSCP status (Public Scientific, Cultural and Professional Establishment), its missions concern research, training and continuing education, the dissemination of knowledge, and the transfer to economic sectors and support for business creation. Its activities are national and international.

The research at École des Ponts ParisTech is characterized by a balanced effort in the following scientific activities:

• Outstanding academic research, evaluated at the highest level by the HCERES (highest council for research), with 5 ERC, more than 1000 publications of rank A per year, a hundred Ph.D. theses supported per year,
• Partnership research with companies, public entities and local authorities.

École des Ponts ParisTech, in accordance with its strategic plan, develops a long-term research activity in the field of Machine Learning and Computer Vision.

IMAGINE team

The IMAGINE team is a renowned research group in computer vision and machine learning, with seminal results in 3D reconstruction from images, scene understanding, deep learning, optimization, sparsity, etc. IMAGINE is part of the Laboratoire d’informatique Gaspard-Monge (LIGM), a top-ranked computer science lab.

The imagine team currently includes 7 permanent researchers and about 30 PhD students. It has strong ties with both academic and industrial partners.

Project objectives

The goal of this project is to develop approaches to assist experts in identifying and analyzing patterns. Indeed, while the success of deep learning on visual data is undeniable, applications are often limited to the supervised learning scenario where the algorithm tries to infer a label for a new image based on the annotations made by experts in a reference dataset. In contrast, we will take as input images without any annotation, automatically identify consistent patterns and model their variation and evolution, so that an expert can more easily analyze them.

The key concept it will develop is the one of visual structures. Their key features will be their interpretability, in terms of correspondences, deformations, or properties of the observed images, and their ability to incorporate prior knowledge about the data and expert feedback. It will explore two complementary approaches to formally define and identify visual structures: one based on analyzing correspondences, the other on learning interpretable image models.

We will develop visual structures in two domains: historical documents and Earth imagery. For example, from temporal series of multispectral Earth images, we will identify types of moving objects, areas with different types of vegetation or constructions, and model the evolution of their characteristics, which may correspond to changes in their activity or life cycle. Ultimately, experts will still be needed to select relevant visual structures and perform analysis, requiring to work closely with them, to design relevant features in our algorithms and adapted interfaces for interaction.

Responsibilities and requirements

The applicants should be able to work independently, in a team and with external collaborators to produce, publish, and present research results in top quality conferences and journals.

Application

The candidate should hold a Master degree in Computer Vision / Machine Learning / Digital Humanities. An ideal candidate would have a track record of publications, experience in developing Computer Vision algorithms, experience in collaborating with non-experts (ideally historians), and experience in designing web interfaces.

Please send a CV and a cover letter that specifies employment availability date, contact information of two academics who can provide reference letters upon request, and examples of past projects to [e-mail] with 'DISCOVER PhD application' as a topic.

Timeline

Applications will be treated as they come. The starting date is expected between December 1st 2024 and February 1st 2025.

Contract

1 or 2 year renewable contract. Part time position possible.

Location

Position based in CHAMPS-sur-MARNE (cité Descartes) - France Access: RER A, 25 minutes from Paris city center. Remote work possible 2 days per week.