Thesis: Structuring and intelligent navigation in heritage data corpora (M/F)
@French National Centre for Scientific Research posted 2 days agoJob Description
General information
Job title: Thesis: Structuring and intelligent navigation in heritage data corpora (M/F)
Reference: UPR2002-ADEMAN-001
Number of positions: 1
Work location: VILLEURBANNE
Publication date: Thursday, June 5, 2025
Type of contract: Fixed-term contract Doctoral student
Contract duration: 36 months
Thesis start date: October 1, 2025
Workload: Full
Remuneration: The remuneration is a minimum of €2,200.00 per month
CN Section(s): 07 – Information sciences: processing, integrated hardware-software systems, robots, commands, images, content, interactions, signals and languages
Description of the thesis subject
Title: Structuring and intelligent navigation in heritage data corpora: Development of a multidimensional and multiscalar information compression approach based on X-LOD
Description of the thesis subject:
Heritage data are massive and distinguished by their extraordinary diversity and multidimensional nature. They simultaneously refer to space (3D), time (3D + T), as well as a multitude of thematic dimensions, creating an informational fabric of exceptional richness. This thesis subject aims to address the complex challenges posed by the volume and heterogeneity of these documentary corpora, and to significantly improve their exploitation by developing innovative navigation and aggregation methods.
Recent initiatives in heritage sciences and data science, notably the work carried out as part of the Notre-Dame de Paris scientific project, demonstrate that it is possible to aggregate this data, whether in 3D representation environments, or in graph form by exploiting methods allowing the identification of the various relationships that link them together (semantic, spatial, temporal, provenance, etc.). However, these visualization methods often prove to be difficult to understand for users. Paradoxically, the richer the data representation, the less accessible it seems to be for analysis and understanding. To navigate such scenes, it is then necessary to find ways to simplify and compress the information, to offer navigation methods that make more sense for users according to their disciplinary profiles and research questions.
The main objective of this thesis is to develop methods to extract simplified views of the corpus, guided by some form of dimensional proximity, by the scale of representation, or by user interests. The proposed methodology includes an in-depth analysis of existing heritage data corpora, the design and implementation of projection and compression algorithms to build levels of detail adapted to the different dimensions of heritage data (X-LOD), as well as the creation of new navigation interfaces exploiting these new approaches.
Profile and skills sought:
Holder of an engineering or master’s degree in computer science.
Curiosity and appetite for multidisciplinary work.
Work context
This thesis is part of a multidisciplinary context within the framework of the 80PRIME TEATIME project “Territories in Evolution and Cross-Scale Interdisciplinary Analyses”. This project, which involves the LIRIS (Laboratory of Computer Science in Images and Information Systems) and MAP (Models and Simulations for Architecture and Heritage) laboratories, has obtained financial support from the CNRS through the interdisciplinary programs of the MITI.
The position is part of the TEATIME project coordinated by Violette Abergel within the MAP laboratory (UPR 2002 CNRS in Marseille), but the reception of the doctoral student (M/F) will be within the LIRIS laboratory (UMR 5205 CNRS / INSA Lyon / Université Claude Bernard Lyon 1 / Université Lumière Lyon 2 / École Centrale de Lyon) in VILLEURBANNE. Missions in Marseille will be expected.
This work will be based on the corpus of data produced as part of the Notre-Dame de Paris scientific project.
Thesis supervision:
Directors: Gilles Gesquière (PR, LIRIS), Livio De Luca (DR, MAP)
Supervisors: Violette Abergel (CR, MAP & LIRIS)
Doctoral school: ED 512 InfoMath (Université Lyon 2)
— About the Teatime project —
The TEATIME project focuses on the study of territories at different scales and their transformations, focusing on the built heritage that composes them. By relying on the semantic enrichment of spatialized representations, it aims to design mechanisms to better structure and connect heterogeneous multidimensional data corpora, notably associating spatial, temporal, and semantic characteristics, in order to produce new knowledge. This project focuses on the corpus of data from the Notre-Dame de Paris scientific project.
— About LIRIS —
LIRIS (Laboratoire d’InfoRmatique en Image et Systèmes d’information) is a joint research unit (UMR 5205) under the supervision of the CNRS, INSA Lyon, Université Claude Bernard Lyon 1, Université Lumière Lyon 2 and École Centrale de Lyon. With more than 300 members, it covers a wide range of computer science fields, including artificial intelligence, computer vision, cybersecurity and data science. Its research also extends to interfaces with the humanities, social sciences and environmental sciences.
— About MAP —
The MAP laboratory is a Research Unit (UPR 2002) of the CNRS Sciences Humaines & Sociales. Its activities are at the intersection of heritage sciences and data sciences, and focus on the design and development of digital methods and tools for heritage study and conservation.
The position is located in a sector covered by the protection of scientific and technical potential (PPST), and therefore requires, in accordance with regulations, that your arrival be authorized by the competent authority of the MESR.
Constraints and risks
Area covered by the protection of scientific and technical potential (ZRR):
This position is located in a “restricted regime zone” within the meaning of Article R.413-5-1 of the Penal Code. Taking up the position may only take place after access authorization has been issued by the head of the establishment, in accordance with the provisions of Article 20-4 of Decree No. 84-431 of June 6, 1984.
