Clément Rambour

Clément Rambour

Membre associé
Team: Données Complexes, Apprentissage et Représentations
Personal website: https://clementrambour.wp.imt.fr/
Office: 37.1.40

I am a associate professor in the Vertigo team of the CEDRIC. I am currently working on deep learning for time series of multi-modal images for changes detection, forecasting and inverse problem.

2024

Articles de revue

  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 

Articles de conférence

  1. Dalsasso, E.; Rambour, C.; Denis, L. and Tupin, F. Learning a versatile representation of SAR data for regression and segmentation by leveraging self-supervised despeckling with MERLIN. In European Conference on Synthetic Aperture Radar, Munich (Allemagne), Germany, 2024. www 
  1. Lafon, M.; Ramzi, E.; Rambour, C.; Audebert, N. and Thome, N. GalLoP: Learning Global and Local Prompts for Vision-Language Models. In The 18th European Conference on Computer Vision ECCV 2024, arXiv, Milan, Italy, 2024. doi  www 

2023

Articles de conférence

  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 
  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 

Non publié

  1. Coquenet, D.; Rambour, C.; Dalsasso, E. and Thome, N. Leveraging Vision-Language Foundation Models for Fine-Grained Downstream Tasks. , working paper or preprint. www 

2022

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. Boige, R.; Audebert, N.; Rambour, C. and Levieux, G. Now you see me: finding the right observation space to learn diverse behaviours by reinforcement in games. In Conférence sur l'Apprentissage automatique (CAp), Vannes, France, 2022. 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 

2021

Articles de conférence

  1. Rambour, C.; Denis, L. and Tupin, F. 3D Buildings Reconstruction with SAR Tomography Guided by Partial Footprints Information. In EUSAR 2021, VIRTUEL, Germany, 2021. www 
  1. Petit, O.; Thome, N.; Rambour, C.; Themyr, L.; Collins, T. and Soler, L. U-Net Transformer: Self and Cross Attention for Medical Image Segmentation. In MICCAI workshop MLMI, Strasbourg (virtuel), France, 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 

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. Rambour, C.; Budillon, A.; Johnsy, A.; Denis, L.; Tupin, F. and Schirinzi, G. From Interferometric to Tomographic Synthetic Aperture Radar. Scatterer unmixing in urban areas: A review of synthetic aperture radar tomography-processing techniques. In IEEE geoscience and remote sensing magazine, 8 (2), 2020. www 

Articles de conférence

  1. Charrier, L.; Godet, P.; Rambour, C.; Weissgerber, F.; Erdmann, S. and Koeniguer, E. C. Analysis of dense coregistration methods applied to optical and SAR time-series for ice flow estimations. In 2020 IEEE Radar Conference (RadarConf20), pages 1-6, IEEE, Florence, Italy, 2020. doi  www 
  1. Budillon, A.; Denis, L.; Rambour, C.; Schirinzi, G. and Tupin, F. Regularized SAR Tomography Approaches. In IGARSS (IEEE International Geoscience and Remote Sensing Symposium), IEEE, Hawa"i, United States, 2020. www 

2019

Articles de revue

  1. Rambour, C.; Denis, L.; Tupin, F. and Oriot, H. Introducing spatial regularization in SAR tomography reconstruction. In IEEE Transactions on Geoscience and Remote Sensing, 2019. doi  www 
  1. Rambour, C.; Denis, L.; Tupin, F.; Oriot, H.; Huang, Y. and Ferro-Famil, L. Urban Surface Reconstruction in SAR Tomography by Graph-Cuts. In Computer Vision and Image Understanding, 188: 102791, 2019. doi  www 

Articles de conférence

  1. Rambour, C.; Denis, L.; Tupin, F. and Oriot, H. Urban surface recovery through graph-cuts over SAR tomographic reconstruction. In 2019 Joint Urban Remote Sensing Event (JURSE), IEEE, Vannes, France, Urban Remote Sensing Joint Event , 2019. doi  www 

Thèses et habilitations

  1. Rambour, C. Structural tomographic approaches for urban area analysis using high resolution SAR tomography : TomoSAR. Ph.D. Thesis, Université Paris Saclay (COmUE), 2019.

2018

Articles de conférence

  1. Rambour, C.; Denis, L.; Tupin, F.; Nicolas, J-M. and Oriot, H. SAR TOMOGRAPHY OF URBAN AREAS: 3D REGULARIZED INVERSION IN THE SCENE GEOMETRY. In 2018 IEEE International Geoscience and Remote Sensing Symposium, Valence, Spain, 2018. www 

2017

Articles de conférence

  1. Rambour, C.; Denis, L.; Tupin, F.; Nicolas, J. M.; Oriot, H.; Ferro-Famil, L. and Deledalle, C-A. Similarity criterion for SAR tomography over dense urban area. In IEEE IGARSS, Fort Worth (TX), United States, 2017. doi  www 
Top