Complex data, machine learning and representations

Our research team focus on the problems raised by large-scale data management, with a strong orientation towards data whose structure, explicit or not, is complex and requires specific techniques of approximation, extraction and search. The type of data we are dealing with include images, videos, audio or musical documents, satellite imagery and data from multi-spectral sensors. We investigate techniques of statistical machine learning (with a specific focus on deep learning) to extract information, build efficient access techniques and propose new methods of data management based directly on content (as opposed to metadata describing this content). At the moment there are two research axis/directions in our team, described below.

Axis 1. Large image and video databases
We live today in a context characterized by an explosive growth in the production of digital content, doubled by a revolution in digital storage making it possible to keep and easily access large quantities of digital data, beyond the timeline for which it has been initially collected. On the other hand, the rapid development of digital transmission technologies makes possible the distributed distribution and remote sharing of large volumes of such a digital contents. We focus on the structuring, from visual content, of large image and video databases, as well as the search by content in such databases. Our recent work focus on deep learning for the detection of visual patterns and for semantic segmentation of images, the goal being the semantic analysis of scenes taking into account structural and global-local relationships between image components. These approaches also apply very well to data of a different nature, such as musical data, which combine structures at different scales and are generally characterized by a relatively small number of structural items labeled by class.

Axis 2. Music computing and music information retrieval
This axis of research aims to investigate the production of models of musical languages, characterizing homogeneous corpora of music available in symbolic form (scores). Our perspective is to enrich a statistical approach based on explicit data (notes) by a knowledge extraction process identifying the elements of musical language implicitly present in the notation: segmentation in phrases, presence and use of patterns, management of dissonances, cadences, instrumentation and texture. Another direction of research is the development of automatic transcription techniques, conversion of a musical performance to a score in traditional notation by a priori score models (independent of the performance to be transcribed), representing the language of possible musical notations. These techniques can be seen as language models, and are essential components of machine translation or pattern recognition procedures for music data (by analogy with natural language processing).

Team's Directory

Head of Team

Permanent

Non Permanent

Former members

Peer-reviewed conferences and journals

2024

Articles de revue

  1. Sun, R.; Masson, C.; Hénaff, G.; Thome, N. and Cord, M. Semantic augmentation by mixing contents for semi-supervised learning. In Pattern Recognition, 145: 109909, 2024. doi  www 
  1. Dalsasso, E.; Rambour, C.; Trouvé, N. and Thome, N. MERLIN-Seg: self-supervised despeckling for label-efficient semantic segmentation. In Computer Vision and Image Understanding, 241, 2024. doi  www 

2023

Articles de conférence

  1. Lafon, M.; Ramzi, E.; Rambour, C. and Thome, N. Hybrid Energy Based Model in the Feature Space for Out-of-Distribution Detection. In International Conference on Machine Learning, Honololu, Hawaii, United States, 2023. www 
  1. Aissa, W.; Ferecatu, M. and Crucianu, M. Curriculum Learning for Compositional Visual Reasoning. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, pages 888-897, Scitepress, Lisbon, Portugal, 2023. doi  www 
  1. Themyr, L.; Rambour, C.; Thome, N.; Collins, T. and Hostettler, A. Full Contextual Attention for Multi-resolution Transformers in Semantic Segmentation. In 2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), pages 3223-3232, IEE Computer Society, Waikoloa, United States, 2023. doi  www 

2022

Articles de revue

  1. Castillo-Navarro, J.; Le Saux, B.; Boulch, A.; Audebert, N. and Lefèvre, S. Semi-Supervised Semantic Segmentation in Earth Observation: The MiniFrance suite, dataset analysis and multi-task network study. In Machine Learning, 111: 3125-3160, 2022. doi  www 
  1. Le Guen, V. and Thome, N. Deep Time Series Forecasting with Shape and Temporal Criteria. In IEEE Transactions on Pattern Analysis and Machine Intelligence, 45 (1): 342-355, 2022. doi  www 
  1. Giraud, M. and Jacquemard, F. Weighted Automata Computation of Edit Distances with Consolidations and Fragmentations. In Information and Computation, 282: 104652, 2022. doi  www 
  1. Doubinsky, P.; Audebert, N.; Crucianu, M. and Le Borgne, H. Multi-attribute balanced sampling for disentangled GAN controls. In Pattern Recognition Letters, 162: 56-62, 2022. doi  www 
  1. Zhu, T.; Fournier-S'Niehotta, R.; Rigaux, P. and Travers, N. A Framework for Content-Based Search in Large Music Collections. In Big Data and Cognitive Computing, 6 (1): 23, 2022. doi  www 

Articles de conférence

  1. Le Guen, V.; Rambour, C. and Thome, N. Complementing Brightness Constancy with Deep Networks for Optical Flow Prediction. In ECCV 2022, Springer, Tel Aviv, Israel, Lecture Notes in Computer Science, vol 13681 , 2022. doi  www 
  1. Sun, R.; Ramé, A.; Masson, C.; Thome, N. and Cord, M. Towards efficient feature sharing in MIMO architectures. In 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pages 2696-2700, IEEE, New Orleans, United States, 2022. doi  www 
  1. Garczynski, L.; Giraud, M.; Leguy, E. and Rigaux, P. Modeling and Editing Cross-Modal Synchronization on a Label Web Canvas. In Music Encoding Conference (MEC 2022), Halifax, Canada, 2022. www 
  1. Jacquemard, F. and Rodriguez de La Nava, L. Symbolic Weighted Language Models, Quantitative Parsing and Automated Music Transcription. In CIAA 2022 - International Conference on Implementation and Application of Automata, pages 67-79, Springer, Rouen, France, Lecture Notes in Computer Science, vol 13266 , 2022. doi  www 
  1. Zhou, S.; Blanchart, P.; Crucianu, M. and Ferecatu, M. Why is the prediction wrong? Towards underfitting case explanation via meta-classification. In 2022 IEEE 9th International Conference on Data Science and Advanced Analytics (DSAA), pages 10032332, IEEE, Shenzhen, China, 2022. doi  www 
  1. Calem, L.; Ben-Younes, H.; Perez, P. and Thome, N. Diverse Probabilistic Trajectory Forecasting with Admissibility Constraints. In 2022 26th International Conference on Pattern Recognition (ICPR), pages 3478-3484, IEEE, Montreal, Canada, 2022. doi  www 
  1. Cheng, X.; Zayani, R.; Ferecatu, M. and Audebert, N. Efficient Autoprecoder-based deep learning for massive MU-MIMO Downlink under PA Non-Linearities. In IEEE Wireless Communications and Networking Conference, Austin, United States, 2022. www 
  1. Mali, J.; Ahvar, S.; Atigui, F.; Azough, A. and Travers, N. A Global Model-Driven Denormalization Approach for Schema Migration. In RCIS, pages 529-545, Barcelona, Spain, Lecture Notes in Business Information Processing 446, 2022. doi  www 
  1. Ramzi, E.; Audebert, N.; Thome, N.; Rambour, C. and Bitot, X. Hierarchical Average Precision Training for Pertinent Image Retrieval. In ECCV 2022, Tel-Aviv, Israel, 2022. www 
  1. Bavu, '.; Pujol, H.; Garcia, A.; Langrenne, C.; Hengy, S.; Rassy, O.; Thome, N.; Karmim, Y.; Schertzer, S. and Matwyschuk, A. Deeplomatics: A deep-learning based multimodal approach for aerial drone detection and localization. In QUIET DRONES Second International e-Symposium on UAV/UAS Noise, Paris, France, QUIET DRONES 2022 SECOND INTERNATIONAL SYMPOSIUM ON NOISE FROM UASs/UAVs and eVTOLs SYMPOSIUM PROCEEDINGS , 2022. www 

2021

Articles de revue

  1. Foscarin, F.; Rigaux, P. and Thion, V. Data Quality Assessment in Digital Score Libraries. The GioQoso Project. In International Journal on Digital Libraries, 22 (2): 159-173, 2021. doi  www 
  1. Petit, O.; Thome, N. and Soler, L. Iterative Confidence Relabeling with Deep ConvNets for Organ Segmentation with Partial Labels. In Computerized Medical Imaging and Graphics: 101938, 2021. doi  www 
  1. Grossetti, Q.; Du Mouza, C.; Travers, N. and Constantin, C. Reducing the filter bubble effect on Twitter by considering communities for recommendations. In International Journal of Web Information Systems, 17 (6): 728-752, 2021. doi  www 
  1. Corbière, C.; Thome, N.; Saporta, A.; Vu, T-H.; Cord, M. and Perez, P. Confidence Estimation via Auxiliary Models. In IEEE Transactions on Pattern Analysis and Machine Intelligence: 1-1, 2021. doi  www 

Articles de conférence

  1. Dang, C.; Randrianarivo, H.; Fournier-S'Niehotta, R. and Audebert, N. Web Image Context Extraction with Graph Neural Networks and Sentence Embeddings on the DOM tree. In GEM: Graph Embedding and Mining - ECML/PKDD Workshops, pages 258-267, IEEE, Bilbao, Spain, 2021. doi  www 
  1. Yin, Y.; Le Guen, V.; Dona, J.; Ayed, I.; de Bézenac, E.; Thome, N. and Gallinari, P. Augmenting physical models with deep networks for complex dynamics forecasting. In Ninth International Conference on Learning Representations ICLR 2021, Vienna (virtual), Austria, 2021. www 
  1. Corbière, C.; Lafon, M.; Thome, N.; Cord, M. and Pérez, P. Beyond First-Order Uncertainty Estimation with Evidential Models for Open-World Recognition. In ICML 2021 Workshop on Uncertainty and Robustness in Deep Learning, Virtual, Austria, 2021. www 
  1. Ramzi, E.; Thome, N.; Rambour, C.; Audebert, N. and Bitot, X. Robust and Decomposable Average Precision for Image Retrieval. In Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS 2021), Sydney, Australia, 2021. www 
  1. Foscarin, F.; Audebert, N. and Fournier-S'Niehotta, R. PKSpell: Data-Driven Pitch Spelling and Key Signature Estimation. In International Society for Music Information Retrieval Conference (ISMIR), Online, India, 2021. www 

2020

Articles de revue

  1. Rambour, C.; Audebert, N.; Koeniguer, E.; Le Saux, B.; Crucianu, M. and Datcu, M. Flood detection in time series of optical and sar images. In ISPRS International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLIII-B2-2020: 1343-1346, 2020. doi  www 
  1. Dupuis, D.; Du Mouza, C.; Travers, N. and Chareyron, G. Real-Time Influence Maximization in a RTB Setting. In Data Science and Engineering, 5 (3): 224-239, 2020. doi  www 
  1. Besedin, A.; Blanchart, P.; Crucianu, M. and Ferecatu, M. Deep online classification using pseudo-generative models. In Computer Vision and Image Understanding, 201: 103048, 2020. doi  www 
  1. Rosmorduc, S. Automated~Transliteration~of Late Egyptian Using Neural Networks. In Lingua Aegyptia - Journal of Egyptian Language Studies, 28: 233-257, 2020. doi  www 

Articles de conférence

  1. Rolland, J-F. c.; Castel, F.; Haugommard, A.; Aubrun, M.; Yao, W.; Dumitru, C. O.; Datcu, M.; Bylicki, M.; Tran, B-H.; Aussenac-Gilles, N.; Comparot, C. and Trojahn dos Santos, C. CANDELA: A Cloud Platform for Copernicus Earth Observation Data Analytics. In IEEE International Geoscience & Remote Sensing Symposium (IGARSS 2020), Waikoloa, Hawaii, United States, 2020. www 
  1. Le Cacheux, Y.; Le Borgne, H. and Crucianu, M. Using Sentences as Semantic Representations in Large Scale Zero-Shot Learning. In ECCV 2020 workshop Transferring and adapting source knowledge in computer vision (TASK-CV), Glasgow, United Kingdom, 2020. www 
  1. Le Guen, V. and Thome, N. Disentangling Physical Dynamics from Unknown Factors for Unsupervised Video Prediction. In Computer Vision and Pattern Recognition 2020 (CVPR), Seattle, United States, 2020. doi  www 
  1. Le Guen, V. and Thome, N. A Deep Physical Model for Solar Irradiance Forecasting with Fisheye Images. In CVPR OmniCV worshop 2020, Seattle, United States, 2020. doi  www 
  1. Mali, J.; Atigui, F.; Azough, A. and Travers, N. ModelDrivenGuide: An Approach for Implementing NoSQL Schemas. In International Conference, DEXA 2020, pages 141-151, Springer, Bratislava, Slovakia, DEXA 2020: Database and Expert Systems Applications , 2020. doi  www 
  1. Dubucq, D.; Audebert, N.; Achard, V.; Alakian, A.; Fabre, S.; Credoz, A.; Deliot, P. and Le Saux, B. A real-world hyperspectral image processing workflow for vegetation stress and hydrocarbon indirect detection. In XXIV ISPRS Congress, Nice, France, The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLIII-B3-2020, 2020. doi  www 
  1. Foscarin, F.; Mcleod, A.; Rigaux, P.; Jacquemard, F. and Sakai, M. ASAP: a dataset of aligned scores and performances for piano transcription. In ISMIR 2020 - 21st International Society for Music Information Retrieval, Montreal / Virtual, Canada, 2020. www 
  1. Le Guen, V. and Thome, N. Probabilistic Time Series Forecasting with Structured Shape and Temporal Diversity. In NeurIPS 2020, Vancouver, Canada, 2020. www 

2019

Articles de revue

  1. Viard, T. and Fournier-S'Niehotta, R. Augmenting content-based rating prediction with link stream features. In Computer Networks, 150: 127-133, 2019. doi  www 
  1. Lajaunie, C.; Renard, D.; Quentin, A.; Le Guen, V. and Caffari, Y. A non-homogeneous model for kriging dosimetric data. In Mathematical Geosciences, 52 (7): 847-863, 2019. doi  www 

Articles de conférence

  1. Foscarin, F.; Jacquemard, F. and Rigaux, P. Modeling and Learning Rhythm Structure. In Sound and Music Computing Conference (SMC), Malaga, Spain, 2019. www 
  1. Foscarin, F.; Jacquemard, F.; Rigaux, P. and Sakai, M. A Parse-based Framework for Coupled Rhythm Quantization and Score Structuring. In MCM 2019 - Mathematics and Computation in Music, Springer, Madrid, Spain, Proceedings of the Seventh International Conference on Mathematics and Computation in Music (MCM 2019) Lecture Notes in Computer Science, 2019. doi  www 
  1. Viard, T. and Fournier-S'Niehotta, R. Encoding temporal and structural information in machine learning models for recommendation. In LEG @ ECML-PKDD 2019, W"urzburg, Germany, 2019. www 
  1. Foscarin, F.; Fournier-S'Niehotta, R. and Jacquemard, F. A diff procedure for music score files. In 6th International Conference on Digital Libraries for Musicology (DLfM), pages 7, ACM, The Hague, Netherlands, 2019. www 
  1. Grossetti, Q.; Du Mouza, C. and Travers, N. Community-based Recommendations on Twitter: Avoiding The Filter Bubble. In Web Information Systems Engineering -- WISE 2019, Hong-Kong, China, 2019. doi  www 
  1. Le Cacheux, Y.; Le Borgne, H. and Crucianu, M. Modeling Inter and Intra-Class Relations in the Triplet Loss for Zero-Shot Learning. In IEEE International Conference on Computer Vision, IEEE, Séoul, South Korea, 2019. doi  www 
  1. Rigaux, P. and Travers, N. Scalable Searching and Ranking for Melodic Pattern Queries. In Intl. Conf. of the International Society for Music Information Retrieval (ISMIR), Delft, Netherlands, 2019. www 
  1. Dupuis, D.; Du Mouza, C.; Travers, N. and Chareyron, G. RTIM: a Real-Time Influence Maximization Strategy. In Web Information Systems Engineering -- WISE 2019, Hong-Kong, China, 2019. doi  www 

2018

Articles de revue

  1. Raftopoulos, K.; Kollias, S.; Sourlas, D. and Ferecatu, M. On the Beneficial Effect of Noise in Vertex Localization. In International Journal of Computer Vision, 126 (1): 111-139, 2018. doi  www 
  1. Fournier-S'Niehotta, R.; Rigaux, P. and Travers, N. Modeling Music as Synchronized Time Series: Application to Music Score Collections. In Information Systems, 73: 35-49, 2018. doi  www 

Articles de conférence

  1. Petit, O.; Thome, N.; Charnoz, A.; Hostettler, A. and Soler, L. Handling Missing Annotations for Semantic Segmentation with Deep ConvNets. In MICCAI workshop DLMIA, pages 20-28, Springer, Grenade, Spain, Lecture Notes in Computer Science book series (LNIP,volume 11045) , 2018. doi  www 
  1. Foscarin, F.; Fiala, D.; Jacquemard, F.; Rigaux, P. and Thion, V. Gioqoso, an online Quality Assessment Tool for Music Notation. In 4th International Conference on Technologies for Music Notation and Representation (TENOR'18), Concordia University, Montreal, Canada, Proceedings of the International Conference on Technologies for Music Notation and Representation -- TENOR'18 , 2018. www 
  1. Grossetti, Q.; Constantin, C.; Du Mouza, C. and Travers, N. An Homophily-based Approach for Fast Post Recommendation in Microblogging Systems. In 21st International Conference on Extending Database Technology (EDBT 2018), pages 229-240, Vienne, Austria, 2018. doi  www 

2017

Articles de conférence

  1. Rigaux, P. and Thion, V. Quality Awareness over Graph Pattern Queries. In Proceedings of the International Database Engineering & Applications Symposium (IDEAS), Bristol, United Kingdom, 2017. doi  www 
  1. Si-Said Cherfi, S.; Hamdi, F. c.; Rigaux, P.; Thion, V. and Travers, N. Formalizing quality rules on music notation. An ontology-based approach. In International Conference on Technologies for Music Notation and Representation - TENOR'17, Coruna, Spain, 2017. www 
  1. Cherfi, S. S-S.; Guillotel, C.; Hamdi, F. c.; Rigaux, P. and Travers, N. Ontology-Based Annotation of Music Scores. In Knowledge Capture Conference, pages 1-4, ACM Press, Austin, France, 2017. doi  www 
  1. Besedin, A.; Blanchart, P.; Crucianu, M. and Ferecatu, M. Evolutive deep models for online learning on data streams with no storage. In ECML/PKDD 2017 Workshop on Large-scale Learning from Data Streams in Evolving Environments, Skopje, Macedonia, 2017. www 

Communications

2023

Chapitres d'ouvrage

  1. Coquenet, D.; Chatelain, C. and Paquet, T. Faster DAN: Multi-target Queries with Document Positional Encoding for End-to-end Handwritten Document Recognition. In Document Analysis and Recognition - ICDAR 2023, pages 182-199, Springer Nature Switzerland, Lecture Notes in Computer Science 14190, 2023. doi  www 

2022

Chapitres d'ouvrage

  1. Serge, R. L'organisation spatiale des textes hiéroglyphiques. In Guide des écritures de l''Egypte ancienne, pages 130-137, 2022. www 
  1. Rosmorduc, S. Digital writing of hieroglyphic texts. In Handbook of Digital Egyptology: Texts, pages 37-53, Editorial Universidad de Alcal'a, 2022. www 

Divers

  1. Digard, M.; Jacquemard, F. and Rodriguez-de la Nava, L. MIDI To Score Automated Drum Transcription. , Poster. www 
  1. Yuehgoh, F.; Travers, N. and Djebali, S. A Technology Intelligence Recommendation System based on Multiplex Networks. , Poster. www 
  1. Yuehgoh, F.; Travers, N. and Djebali, S. A Technology Intelligence Recommendation System based on Multiplex Networks. , Poster. www 

2021

Chapitres d'ouvrage

  1. Le Cacheux, Y.; Le Borgne, H. and Crucianu, M. Zero-shot Learning with Deep Neural Networks for Object Recognition. In Multi-faceted Deep Learning: Models and Data, Springer, 2021. doi  www 

2019

Chapitres d'ouvrage

  1. Le Cacheux, Y.; Le Borgne, H. and Crucianu, M. From Classical to Generalized Zero-Shot Learning: A Simple Adaptation Process. In MultiMedia Modeling. 25th International Conference, MMM 2019, Thessaloniki, Greece, January 8--11, 2019, Proceedings, Part II, pages 465-477, Springer Verlag, Lecture Notes in Computer Science 11296, 2019. doi  www 

2018

Divers

  1. Besedin, A.; Blanchart, P.; Crucianu, M. and Ferecatu, M. Deep Online Storage-Free Learning on Unordered Image Streams. , Poster. doi  www 
  1. Besson, V.; Fiala, D.; Rigaux, P. and Thion, V. Gioqoso, an Online Quality Evaluation Tool for MEI Scores. , Poster. www 
  1. Foscarin, F.; Fournier-S'Niehotta, R.; Rigaux, P. and Jacquemard, F. Evaluating musical score difference: a two-level comparison. , Poster. www 

Rapports

  1. Fiala, D.; Rigaux, P.; Tacaille, A.; Thion, V. and Members, G. Data Quality Rules for Digital Score Libraries. Technical Report, IRISA, Université de Rennes, 2018.

2017

Chapitres d'ouvrage

  1. Yang, L.; Rodriguez, H.; Crucianu, M. and Ferecatu, M. Fully Convolutional Network with Superpixel Parsing for Fashion Web Image Segmentation. In MultiMedia Modeling - 23rd International Conference, MMM 2017, Reykjavik, Iceland, January 4-6, 2017, Proceedings, Part II, pages 139-151, Springer, Lecture Notes in Computer Science 10133, 2017. doi  www 

Softwares and patents

Ongoing projects

CI POLIFONIA
  • Full name: Coûts indirects de POLIFONIA: CI POLIFONIA - Funder: Commission européenne
  • Duration: January 2021 - April 2024
  • Description: Le projet Polifonia vise à créer un système de médiation pour l'ensemble des sources musicales en Europe. Il créera une base de connaissances décentralisée rassemblant le contexte historique et culturel, exprimée en différentes langues et couvrant tous les styles musicaux. L'objectif du projet est de promouvoir l'accès, la préservation, l'étude et l'exploitation de cet immense patrimoine.
POLIFONIA
  • Full name: POLIFONIA: POLIFONIA - Funder: Commission européenne
  • Duration: January 2021 - April 2024
  • Description: Polifonia met en œuvre un écosystème numérique pour le patrimoine musical européen : des objets musicaux ainsi que des connaissances pertinentes sur leur culture et le contexte historique, exprimés dans différentes langues et styles, et à travers les siècles. L'écosystème comprendra des méthodes, des outils, des lignes directrices, expériences et conceptions créatives, ouvertement partagées. L'objectif est de provoquer un changement de paradigme dans le patrimoine musical préservation, gestion, étude, interaction et exploitation. Dix pilotes, entre cloches historiques et orgue patrimoine, classement des la musique notée polyphonique, au rôle historique de la musique dans la vie des enfants, conduiront au développement de l'écosystème grâce à une validation de ses technologies. Le projet est conçu par un équipe interdisciplinaire de chercheurs et conservateurs passionnés : informaticiens, anthropologues et ethnomusicologues, historiens de la musique, linguistes, archivistes du patrimoine musical, catalogueurs et administrateurs, et professionnels de la création.
AHEAD SWORD
  • Full name: ANR AHEAD SWORD: AHEAD SWORD - Funder: ANR
  • Duration: July 2020 - December 2026
  • Description:
AHEAD IRCAD
  • Full name: ANR AHEAD couplé à la convention IRCAD: AHEAD IRCAD - Funder: ANR
  • Duration: July 2020 - December 2026
  • Description:
CollabScore
  • Full name: ANR CollabScore: CollabScore - Funder: ANR
  • Duration: October 2020 - March 2024
  • Description:
DIAMELEX
  • Full name: ANR DIAMELEX: DIAMELEX - Funder: ANR
  • Duration: October 2020 - May 2026
  • Description: Aide au diagnostic de mélanome par l'exemple
RECOMPENSE GOOGLE
  • Full name: RECOMPENSE GOOGLE N. AUDEBERT: RECOMPENSE GOOGLE - Funder: GOOGLE IRELAND LIMITED
  • Duration: April 2022 - April 2028
  • Description:
COLLABORATION COEXEL-ALDV
  • Full name: COLLABORATION COEXEL-ALDV: COLLABORATION COEXEL-ALDV - Funder: ASSOCIATION LEONARD DE VINCI
  • Duration: March 2022 - March 2025
  • Description:
COLLABORATION COCO PARKS
  • Full name: COLLABORATION COCO PARKS: COLLABORATION COCO PARKS - Funder: COCO PARKS
  • Duration: September 2022 - September 2024
  • Description: Ultr
ANR MAGE
  • Full name: ANR MAGE: ANR MAGE - Funder: ANR
  • Duration: January 2022 - April 2026
  • Description: Cartographier la terre via l'imagerie aérienne en apprenant sur des données de jeu
Dotation Vertigo 2024
  • Full name: Dotation Vertigo 2024: Dotation Vertigo 2024 - Funder: Laboratoire Cédric
  • Duration: January 2024 - December 2024
  • Description:
PEX Orion 2024
  • Full name: PEX Orion 2024: PEX Orion 2024 - Funder: Laboratoire Cédric
  • Duration: January 2024 - December 2024
  • Description:
PEX Generation 2024
  • Full name: PEX Generation 2024: PEX Generation 2024 - Funder: Laboratoire Cédric
  • Duration: January 2024 - December 2024
  • Description:
CIFRE Maxime Mérizette
  • Full name: CIFRE Maxime Mérizette: CIFRE Maxime Mérizette - Funder: Quarta
  • Duration: June 2022 - May 2025
  • Description: Deep leaarning cifre n°2022/0184
ANR AHEAD CEA BENALI
  • Full name: ANR AHEAD CEA BENALI: ANR AHEAD CEA BENALI - Funder: ANR
  • Duration: September 2020 - December 2026
  • Description:
CEA AHEAD BENALI
  • Full name: CEA AHEAD BENALI: CEA AHEAD BENALI - Funder: Commissariat a l'Energie Atomique et aux Energies Alternatives
  • Duration: September 2023 - September 2026
  • Description: Injection de connaissances pour apprendre des représentations multimédia explicables
ANR ASTRAL
  • Full name: ANR ASTRAL: ANR ASTRAL - Funder: ANR
  • Duration: October 2021 - December 2024
  • Description: Apprentissage Statistique pour l'imagerie Sar Multidimensionnelle

Past projects

    • Full name: Vertigo 2021
    • Duration: January 2020 - December 2021
    • Description:

    • Full name: Nouvelles méthodes informatiques pour les Humanités numériques
    • Duration: January 2021 - December 2021
    • Description: L’objectif de ce projet exploratoire est d’afficher ces travaux et compétences, actuellement dispersés, sous une étiquette “Humanités numériques”, et de mener un double travail de clarification interne et de communication externe pour identifier le potentiel de cette étiquette comme axe de recherche stable et pérenne. Comment caractériser les problématiques informatiques pertinentes pour participer à une recherche interdisciplinaire équilibrée en humanités numériques ? Le projet exploratoire se place dans une perspective de recherche informatique inspirée par des problématiques SHS. Il s’agit d’identifier ce qui, dans une démarche SHS, suscite une innovation méthodologique en informatique et mène à une recherche véritablement interdisciplinaire, encourageant une réflexion épistémologique croisée (par opposition à la simple mise au point d’outils). Quelles sont les méthodes de l’autre pour produire de la connaissance, comment mes propres méthodes peuvent-elles enrichir celles de l’autre et réciproquement.

    • Full name: Apprentissage par renforcement et diversité pour le jeu vidéo
    • Duration: January 2021 - December 2021
    • Description: L'apprentissage par renforcement (RL) a récemment abattu de nombreuses barrières en création d'intelligences artificielles (IA) pour le jeu vidéo. Il est désormais possible d'apprendre à des agents autonomes à jouer à des jeux de complexité variable, allant des classiques Atari (casse-briques, Space Invader) à des jeux de tir en environnement ouvert, en construisant des stratégies haut niveau y compris à partir de stimuli bas niveau (visuels, par exemple). Cependant, la recherche actuelle en RL se concentre sur l'optimalité, c'est-à-dire produire des agents maximisant leur score et jouant parfaitement. Cette approche n'est pas satisfaisante lorsque l'on cherche à utiliser ces agents virtuels comme adversaires d'un ou d'une joueuse. La curiosité est un des aspects les plus importants de la motivation du joueur. Pour être maintenue, il est nécessaire de le confronter à un défi qui se renouvelle par la narration, par l'environnement mais aussi par le comportement et les stratégies à adopter face à des adversaires variés. L'objectif de ce projet est de concevoir des algorithmes de RL produisant des agents aux stratégies diversifiés, même si celles-ci sont sous-optimales, afin de générer une expérience de jeu plus variée. Nous nous proposons d'une part de quantifier mathématiquement cette notion de diversité comportementale des agents virtuels et d'autre part d'intégrer cette diversité dans l'exploration de l'espace des comportements des algorithmes de RL.

    • Full name: Collaboration EDF V. LE GUEN
    • Duration: January 2019 - December 2023
    • Description:

    • Full name: IRCAD
    • Duration: April 2017 - October 2017
    • Description:

    • Full name: SWORD
    • Duration: May 2018 - December 2019
    • Description:

    • Full name: VISIBLE PATIENT IRCAD
    • Duration: November 2017 - July 2019
    • Description:

    • Full name: ERGONOVA CALEM
    • Duration: October 2018 - August 2019
    • Description:

    • Full name: CEA LIST LE CACHEUX
    • Duration: October 2017 - September 2020
    • Description:

    • Full name: Convention d'accueil Blaise Pascal no 17/04
    • Duration: March 2018 - February 2020
    • Description:

    • Full name: XXII Apprentisage profond
    • Duration: June 2019 - September 2022
    • Description:

    • Full name: Machine Learning to Explain Security Incidents
    • Duration: January 2021 - December 2021
    • Description: Collaboration des équipes ISID (Nadira Lammari, Nada Mimouni, Hammou Fadili), MSDMA (Nicolas Thome) and EE SD (Véronique Legrand) Il y a, de nos jours, une réelle prise de conscience que la sécurité n’est jamais acquise. Comme souligné par les professionnels de la cybersécurité, face à la complexité et la prolifération des attaques, une surveillance continue de la sécurité du Système d’Information (SI) est plus que jamais nécessaire. Cet objectif nécessite la mise en œuvre de plusieurs activités, y compris l’analyse des causes profondes des incidents de sécurité, connue sous l’acronyme anglais RCA (Root Cause Analysis). Dans le cadre de ce projet, nous souhaitons tirer profit de la capacité du « Machine Learning » (ML) à apprendre de masses de données et des capacités de raisonnement humain dans des contextes complexes afin de concevoir et mettre en œuvre une approche guidée qui aide, non seulement, à l’explication les incidents de sécurité mais qui apprend et transmet également les connaissances et les compétences métier. La transmission des connaissances en analyse de la sécurité fournira aux experts en sécurité des capacités défensives et offensives. La transmission des compétences en ML donnera aux experts en sécurité plus d’autonomie dans le choix l’orchestration et le calibrage des algorithmes.

    • Full name: SWORD AHEAD
    • Duration: January 2021 - December 2023
    • Description:

    • Full name: ANR AHEAD couplé à la convention IRCAD
    • Duration: October 2020 - September 2023
    • Description:

    • Full name: CEA AHEAD
    • Duration: October 2020 - September 2023
    • Description:

    • Full name: GE HEALTHCARE THUY LE
    • Duration: November 2017 - October 2020
    • Description:

    • Full name: VALEO Charles CORBIERE
    • Duration: January 2019 - February 2022
    • Description:

    • Full name: VISIBLE PATIENT Olivier PETIT
    • Duration: November 2018 - January 2022
    • Description:

    • Full name: ANR DEEPLOMATICS
    • Duration: October 2018 - September 2021
    • Description:

    • Full name: Cifre Valeo Calem
    • Duration: September 2020 - August 2023
    • Description:

    • Full name: Apprentissage par renforcement et diversité pour le jeu vidéo
    • Duration: January 2022 - December 2022
    • Description: L'objectif de ce projet est de concevoir des algorithmes d'apprentissage par renforcement produisant des agents aux stratégies diversifiés, même si celles-ci sont sous-optimales, afin de générer une expérience de jeu plus variée. Nous nous proposons d'une part de quantifier mathématiquement cette notion de diversité comportementale des agents virtuels et d'autre part d'intégrer cette diversité dans l'exploration de l'espace des comportements des algorithmes de RL dans des environnements de jeux.

    • Full name: Soutien équipe Vertigo 2022
    • Duration: January 2022 - December 2022
    • Description:

    • Full name: Dotation Vertigo 2023
    • Duration: January 2023 - December 2023
    • Description:

    • Full name: PEX ORION 2023
    • Duration: January 2023 - December 2023
    • Description:

    • Full name: CEA LIST Le Cacheux
    • Duration: October 2017 - September 2020
    • Description:

Top