Offre en lien avec l’Action/le Réseau : – — –/– — –

Laboratoire/Entreprise : LIFAT EA 6300 (lifat.univ-tours.fr)
Durée : 3 ans
Contact : donatello.conte@univ-tours.fr
Date limite de publication : 2022-02-24

Contexte :
The thesis will be part and funded (gross salary: 2 000 € approximately) under the ANR project CodeGNN (http://www.normastic.fr/projet-anr-codegnn/)
The PhD could start around October 2022

Supervisors and contact
Donatello Conte (University of Tours, France) donatello.conte@univ-tours.fr
Sébastien Bougleux (Université de Caen Normandie, France) bougleux@unicaen.fr
Nicolas Ragot (University of Tours, France) nicolas.ragot@univ-tours.fr

Ph.D. Position (10/2022): Learning Spatio-temporal data by graph representations

Sujet :
In many application domains like action recognition or prediction, video segmentation, traffic forecasting or anomaly detection in brain activity signals, time-varying data are frequently represented by graphs. Two main representations are commonly considered: a temporal sequence of graphs or a spatio-temporal graph connecting graph nodes through time. While there is a solid literature on data analysis based on such representations, the domain has strongly evolved over the last 5 years with the advances in deep learning on Graph Neural Networks.
Such methods have been less investigated for time-varying graphs, particularly when both the graph structure and the data attached to this structure are varying.
We can distinguish two main models: Recurrent Neural Networks (RNN) combined with spatial convolutions rely on the sequential representation [1, 2, 3]; or Graph Convolutional Networks alternating temporal and spatial convolutions [4, 5, 6].
The aim of this thesis is to:
1. Study new representations for spatio-temporal graphs: we want to investigate some new representations in two main directions: representing temporal data as attributes of nodes and edges, and representing temporal data as edge connections between spatial positions represented by nodes at different times.
2. Propose new Neural Network architectures for data represented by this kind of graphs: we want to propose adapted convolutions, decimation and pooling, and study the definition of a recurrent neural network that operates directly in the space of the graphs (for example generating new graphs). One direction of study will also be the Spatial- Temporal Graph Attention Networks (STGAT [7]) and Graph Transformer Networks (GTN [8]).
3. Program these models (in Python), and compare them to the state-of-the-art on standard datasets for different applications, in particular, skeleton-based gesture recognition.

References
[1] A. Jain, A. R. Zamir, S. Savarese, and A. Saxena, “Structural-rnn: Deep learning on spatio- temporal graphs,” CoRR, vol. abs/1511.05298, 2015
[2] C. Si, W. Chen, W. Wang, L. Wang, and T. Tan, “An attention enhanced graph convolutional lstm network for skeleton-based action recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1227–1236, 2019
[3] Li, M., Chen, S., Zhao, Y., Zhang, Y., Wang, Y., & Tian, Q. (2020). Dynamic multiscale graph neural networks for 3d skeleton based human motion prediction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 214-223).
[4] B. Yu, H. Yin, and Z. Zhu, “Spatio-temporal graph convolutional neural network: A deep learning framework for traffic forecasting,” CoRR, vol. abs/1709.04875, 2017.
[5] L. Shi, Y. Zhang, J. Cheng, and H. Lu, “Skeleton-based action recognition with directed graph neural networks,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7912–7921, 2019.
[6] Chen, T., Zhou, D., Wang, J., Wang, S., Guan, Y., He, X., & Ding, E. (2021). Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognition. arXiv preprint arXiv:2108.04536.
[7] Kong, X., Xing, W., Wei, X., Bao, P., Zhang, J., & Lu, W. (2020). STGAT: Spatial-temporal graph attention networks for traffic flow forecasting. IEEE Access, 8, 134363-134372.
[8] Yun, S., Jeong, M., Kim, R., Kang, J., & Kim, H. J. (2019). Graph transformer networks. Advances in neural information processing systems, 32.

Profil du candidat :
– Master degree in Computer Science, Applied Mathematics, Data Science, or similar.

Formation et compétences requises :
– strong background in computer science and maths
– experiences in neural networks, deep learning, Python programming,
numerical analysis will be privileged
– knowledge in video and image analysis would be appreciated
– good communication skills and reporting, autonomy and curiosity

Adresse d’emploi :
LIFAT, 64 Avenue Jean Portalis, 37200 Tours

Document attaché : 202202231030_PhD_Thesis_Proposal_SpatioTemporalGraphs.pdf

Offre en lien avec l’Action/le Réseau : – — –/Doctorants

Laboratoire/Entreprise : Institut Fresnel
Durée : 3 ans
Contact : andre@fresnel.fr
Date limite de publication : 2022-02-24

Contexte :
With the rise of Internet-of-Things (IoT) applications and the need for massive connectivity, future 6G networks should meet the demands for the global access to high-speed Internet [1]. One of the envisaged solutions consists in deploying non-terrestrial networks such as networks of satellites or microsatellites in the low Earth orbit (LEO). Such satellites have a much lower manufacturing and launch costs than the traditional satellites, such as those placed in the geostationary orbit. Such very high-throughput satellite (VHTS) networks will be able to meet the future substantial data traffic requirements [1,2]. The specificity of these satellites (or microsatellites) is that they have limited capacities and resources (energy, computing, etc.). However, they are more flexible in terms of resource management, such as power and bandwidth allocation. Another particularity of such networks is the irregular distribution of users (on the Ground) and the variability of connections and, therefore, the data traffic over time. This calls for energy efficient and high-speed connectivity solutions for inter-satellite and satellite-to-ground links. In particular, the use of laser communications or free-space optics (FSO) technology promises high rate and secure data transmission over very large distances [3].

Sujet :
In practice, the establishment of such links is associated with several challenges in terms of (a) link availability/reliability and (b) resource management at the satellite. Indeed, the irregular distribution of users (on the Ground) and the variability of data traffic during the day appeal for the design of efficient architectures with flexible resource allocation according to the requested traffic [6].

(a) The first objective is to propose advanced transmission techniques to establish high-speed communication links with high-reliability between microsatellites or between a microsatellite and a Ground station [7]. These solutions must in particular take into account the atmospheric
channel and the vibrations of the payloads, which can cause significant pointing errors (i.e., misalignment between the transmitter and the receiver) [4]. This first step includes the modeling of optical communication channels and will be carried out in collaboration with the
University of Edinburgh.

(b) In a second step, machine learning-based mechanisms will be designed for performing automated resource allocation in order to increase the capacity of satellite-Earth links [8-9]. This will exploit the flexibility of microsatellites in terms of resource management, such as
power and bandwidth allocation.

For more details, see the attached file.

Profil du candidat :
A solid background in signal processing is an important asset. An experience or training in digital communications is also very welcome. The candidate must have a very good English language proficiency (oral and written expression) and be keen for short-term stays in partner laboratories.

Formation et compétences requises :
Master/engineering school in signal processing, telecommunication, data sciences, statistics, mathematics, computer sciences …

Adresse d’emploi :
52 Av. Escadrille Normandie Niemen, 13013 Marseille

Document attaché : 202202221036_Thesis-SatCom-FSO-English(1).pdf

Offre en lien avec l’Action/le Réseau : – — –/– — –

Laboratoire/Entreprise : LaSTIG
Durée : 36 mois
Contact : valerie.gouet@ign.fr
Date limite de publication : 2022-04-08

Contexte :
Thesis proposal: Point cloud based large-scale place recognition – Application to the prevention against fake news

*** Subject of the thesis

The thesis project focuses on 3D point cloud based large-scale place recognition, with the application of geolocation of 3D image data. Without any extra information of the initial position, geolocalazing image content relies on the indexing and retrieval of content similarities in a geolocalized reference. This thesis proposes to study this type of approach by exploiting 3D maps based on acquisition campaigns (in particular LiDAR) that are becoming mainstream thanks to high quality geometry reconstruction which makes them attractive, but also complex to handle given their volume and diversity. Please consult the full text in PDF for the description of the subject thesis.

*** Context

The fields of application of place recognition from images are numerous, we will deal here with the case of the geolocation of amateur video sequences as a certification tool for the prevention against fake news. Massively spread on social networks and on the web, amateur videos relaying information or an event are now very important, with among them content that is fake news, i.e. taken outside of its original context, to express bad or false information. To fight against this form of misinformation, several media, such as the French public television channel “France TV”, have set up a fact checking unit of images and videos which analyzes, verifies and certifies these streams. This complex work is done by hand and would benefit from being automated by using artificial intelligence tools. The verification of geolocation was recognized as essential to best explain what is happening. It is in this collaborative context between IGN and France TV that we focus on this geolocation criterion with the desire to exploit the best georeferencing repositories of today to offer automatic large-scale geolocation solutions, which can, among other things, contribute to the fact checking of visual information.

Sujet :
Full description in English: https://www.umr-lastig.fr/vgouet/News/annonce_these_PlaceReco3D_2022-EN.pdf

Full description in French: https://www.umr-lastig.fr/vgouet/News/annonce_these_PlaceReco3D_2022-FR.pdf

Profil du candidat :
*** Candidate profile

Bac+5 in computer science, applied mathematics or geomatics (master or engineering school).

Please note the only students from the European Union, the United Kingdom or Switzerland are eligible for this thesis project.

*** How to apply

Before March 28, 2022, please send both contacts in a single PDF file the following documents:
– A detailed CV
– A topic-focused cover letter
– Grades and ranks over the last 3 years of study
– The contact details of 2 referents who can recommend you

*** Contacts

– Laurent Caraffa – Laurent.Caraffa@ign.fr, Researcher at LaSTIG (thesis supervisor), IGN, Gustave Eiffel University
– Valérie Gouet-Brunet – Valerie.Gouet@ign.fr, Research director at LaSTIG (director of the thesis), IGN, Gustave Eiffel University

Formation et compétences requises :
A good background in machine learning is required, and a knowledge on 3D computer vision or image indexing will be appreciated. The successful candidate must have good programming skills (Python, C/C++). Although fluency in French is not required, fluency in English is necessary. Curiosity, open-mindedness, creativity, perseverance and the ability to work in a team are also key personal skills in demand.

Adresse d’emploi :
*** Organization

* Start: last quarter of 2022

* Place: the thesis will be carried out in Paris area at the LaSTIG laboratory, located in Saint-Mandé (73 avenue de Paris, Saint-Mandé metro, line 1) in the premises of the IGN. The doctoral student will be attached to the MSTIC Doctoral School (ED 532).

The French mapping agency IGN (National Institute for Geographic and Forest Information) is a public administrative establishment attached to the French Ministry of Ecological Transition; it is the national reference operator for mapping the French territory. The LaSTIG Laboratory in Sciences and Technologies of Geographic Information for the smart city and sustainable territories, is a joint research unit attached to the Gustave Eiffel University, the IGN and the School of Engineering of the city of Paris (EIVP). It is a unique research structure in France and even in Europe, bringing together around 80 researchers, who cover the entire life cycle of geographic or spatial data, from its acquisition to its visualization, including its modeling, integration and analysis; among them about thirty researchers work in image analysis, computer vision, machine learning, photogrammetry and remote sensing. LaSTIG researchers can be involved in the teaching activities of the IGN engineering school, the ENSG (Ecole Nationale des Sciences Géographiques), which offers access to undergraduate and graduate students with excellent quality in fields related to geographic information sciences: geodesy, photogrammetry, computer vision, remote sensing, spatial analysis, cartography, etc.

Document attaché : 202202212218_annonce_these_PlaceReco3D_2022-EN.pdf