Sorbonne Université IUF

Publications

ISIR MLIA

Google Scholar Profile

International Journals

  1. Analyzing Asymmetric Fusion Between Hierarchical Modalities on Tabular & Echocardiographic Data
    for Clinical Diagnosis. [pdf]    . J. Stym, N. Painchaud, P.Y. Courand, N. Thome, O. Bernard. MELBA, to appear, 2026.
  2. Leveraging Scale Separation and Stochastic Closure for Data-Driven Prediction of Chaotic Dynamics. [pdf]. I. Zighed, N. Thome, P. Gallinari, T. Sayadi. Data-Centric Engineering (IF: 2.8), to appear, 2026.
  3. GPU-Accelerated ECSW Hyper-Reduction: Implementation and Performance Evaluation. [pdf].
    IN. Lepage, M. Carlino, C. Fiorini, S. Bennedine, D. Sipp, N. Thome, I. Mortazavi. Data-Centric Engineering (IF: 2.8), to appear, 2026.
  4. Optimization of Rank Losses for Image Retrieval. [pdf]. E. Ramzi, N. Audebert, C. Rambour, A. Araujo, X. Bitot, N. Thome.
    IEEE Transactions on Pattern Analysis and Machine Intelligence (IF: 20.8), vol. 47, no. 6, pp. 4317-4329, June 2025.
  5. Uncertainty-Aware and Parametrised dynamic Reduced-Order Model, application to unsteady flows. [pdf].
    I. Zighed, N. Thome, P. Gallinari, T. Sayadi. Physical Review Fluids (IF: 2.8), to appear, 2025.
  6. Hybrid AutoEncoder/Galerkin approach for nonlinear reduced order modelling. [pdf].
    N. Lepage, C. Fiorini, S. Bennedine, D. Sipp, N. Thome, I.Mortazavi. Computer and Fluids (CAF) (IF: 3), to appear, 2025.
  7. Combining Physics and Machine Learning: Hybrid Models for Predicting Interatomic Potentials. [pdf].
    K. El Haloui, N. Thome, N. Sisourat. Atoms (IF: 1.5), vol 13(11), 89, Nov 2025.
  8. Fusing Echocardiography Images and Medical Records for Continuous Patient Stratification. [pdf].
    N. Painchaud, J. Stym-Popper, P.Y. Courand, N. Thome, P.M. Jodoin, N. Duchateau, O. Bernard. IEEE TUFFC (IF: 3.7), to appear, 2025.
  9. TRUSTED : The Paired 3D Transabdominal Ultrasound and CT Human Data for Kidney Segmentation
    and Registration Research.[pdf]     W. Ndzimbong, C. Fourniol, L. Themyr, N. Thome, Y. Keeza, B. Sauer, P.-T. Piechaud,
    A. Mejean, J. Marescaux, D. George, D. Mutter, A. Hostettler, T. Collins.     In Scientific Data, Nature, 2025.
  10. Global Registration of Kidneys in 3D Ultrasound and CT images. [pdf].
    W. Ndzimbong, N. Thome, C. Fourniol, Y. Keeza, B. Sauer, J. Marescaux, D. George, A. Hostettler, T. Collins. IJCARS (IF: 3), 2025.
  11. Vision and Structured-Language Pretraining for Cross-Modal Food Retrieval. [pdf].
     M. Shukor, N. Thome, M. Cord. Computer Vision and Image Understanding (CVIU), 2024.
  12. ITEM: Improving Training and Evaluation of Message-Passing based GNNs for top-k recommendation. [pdf].
    Y. Karmim, E. Ramzi, R. Fournier, N. Thome. Transactions on Machine Learning Research (TLMLR), 2024.
  13. VidEdit: Zero-Shot and Spatially Aware Text-Driven Video Editing. [pdf]-[page].
    P. Couairon, C. Rambour, J.E. Haugeard, N. Thome. Transactions on Machine Learning Research (TMLR), 2024.
  14. MERLIN-Seg: self-supervised despeckling for label-efficient semantic segmentation. [pdf]
    E. Dalsasso, C. Rambour, N. Trouvé, N. Thome. Computer Vision and Image Understanding (CVIU, IF: 4.5), 2024.
  15. Semantic Augmentation by Mixing Contents for Semi-Supervised Learning. [pdf]
    R. Sun, C. Masson, G. Hénaff, N. Thome, M. Cord. Pattern Recognition (IF: 8.5), Vol 145, January 2024.
  16. Multivariate emulation of kilometer-scale numerical weather predictions with gans. [pdf]
    C. Brochet, L. Rayanud, N. Thome, M. Plu, C. Rambour. Artificial Intelligence for the Earth Systems (AIES), 2023, to appear.
  17. Deep Time Series Forecasting with Shape and Temporal Criteria. [pdf].
    V. Le Guen, N. Thome. IEEE Transactions on Pattern Analysis and Machine Intelligence (IF: 20.8), vol. 45, no. 1, pp. 342-355, Jan. 2023.
  18. Confidence Estimation via Auxiliary Models. [pdf]. C. Corbière, N. Thome, A. Saporta, T-H. Vu, M. Cord, P. Pérez.
    IEEE Transactions on Pattern Analysis and Machine Intelligence (IF: 20.8), vol. 44, no. 10, pp. 6043-6055, Oct. 2022.
  19. Augmenting Physical Models with Deep Networks for Complex Dynamics Forecasting. [pdf].
    Y. Yin, V. Le Guen, J. Dona, I. Ayed, E. de Bezenac, N. Thome, P. Gallinari. JSTAT (IF: 2.23), Vol. 12, December 2021.
  20. 3D Spatial Priors for Semi-Supervised Organ Segmentation with Deep ConvNets. [pdf].
    O. Petit, N. Thome, Luc Soler. International Journal of Computer Assisted Radiology and Surgery (IJCARS) (IF: 2.94), Springer 2021.
  21. Iterative Confidence Relabeling with Deep ConvNets for Organ Segmentation with Partial Labels. [pdf]
    O. Petit, N. Thome, L. Soler. Computerized Medical Imaging and Graphics (IF: 3.75), Volume 91, July 2021.
  22. End-to-End Learning of Latent Deformable Part-based Representations for Object Detection. [pdf]
    T. Mordan, N. Thome, G. Henaff, M. Cord. International Journal of Computer Vision (IJCV) (IF: 11.541), Pages 1-21, December 2019.
  23. Exploiting Negative Evidence for Deep Latent Structured Models. [pdf]
    T. Durand, N. Thome, M. Cord. IEEE Transactions on Pattern Analysis and Machine Intelligence (IF: 24.3), Pages 1-14, February 2019.
  24. Distributed Optimization for Deep Learning with Gossip Exchange. [pdf]
    M. Blot, D. Picard, N. Thome, M. Cord.     Neurocomputing (IF: 3.241), Volume 330, Pages 287-296, February 2019.
  25. SyMIL: MinMax Latent SVM for Weakly Labeled Data. [pdf]
    T. Durand, N. Thome, M. Cord. IEEE Transactions on Neural Networks and Learning Systems (IF: 7.89), Pages 1-14, December 2018.
  26. Classifying low-resolution images by integrating privileged information in deep CNNs. [pdf]
    M. Chevalier, N. Thome, G. Henaff, M. Cord.     Pattern Recognition Letters (PRL) (IF: 1.952), Volume 116, Pages 29-35, December 2018.
  27. Gaze Latent Support Vector Machine for Image Classification Improved by Weakly Supervised Region
    Selection. [pdf]     X. Wang, N. Thome, M. Cord. Pattern Recognition (PR) (IF: 3.96), Volume 72, Pages 59-71, December 2017.
  28. Learning a Distance Metric from Relative Comparisons between Quadruplets of Images. [pdf]
    M. Law, N. Thome, M. Cord. International Journal of Computer Vision (IJCV) (IF: 11.541), Volume 121, Issue 1, pp 65-94, January 2017.
  29. Perceptual principles for video classification with Slow Feature Analysis. [Project Page] [pdf]
    C. Thériault, N. Thome, M. Cord, P. Pérez. IEEE Journal of Selected Topics in Signal Processing (IF: 4.36), p. 428-437, vol 8, Ap 2014.
  30. Learning Deep Hierarchical Visual Feature Coding. [pdf]. H. Goh, N. Thome, M. Cord, J.H. Lim.
    IEEE Transactions on Neural Networks and Learning Systems (IF: 7.89), p. 2212-2225, vol 12, Dec 2014.
  31. SnooperText: A Text Detection System for Automatic Indexing of Urban Scenes. [Project Page] [pdf]
    R. Minetto, N. Thome, M. Cord, N. Leite, J. Stolfi. Computer Vision and Image Understanding (IF: 2.4), p. 92-104, vol 122, May 2014.
  32. JKernelMachines: A simple framework for Kernel Machines. [mloss] [pdf]. D. Picard, N. Thome and M. Cord.
    Journal of Machine Learning Research (JMLR), track for Machine Learning Open Source Software, p. 1417-1421, vol 14, May 2013.
  33. Extended Coding and Pooling in the HMAX Model. [Project Page] [pdf]
    C. Theriault, N. Thome and M. Cord. IEEE Transactions on Image Processing (IF: 5.071), vol 22, num 2, p. 764-777, February 2013.
  34. Pooling in Image Representation: the Visual Codeword Point of View. [Project Page] [pdf]
    S. Avila, N. Thome, M. Cord, E. Valle and A. Araujo. Computer Vision and Image Understanding (IF: 2.4),
    Special Issue on Visual Concept Detection    , , vol 117, num 5, p. 453-465, May 2013.
  35. T-HOG: an Effective Gradient-Based Descriptor for Single Line Text Regions. [Project Page] [pdf]
    R. Minetto, N. Thome, M. Cord, N. Leite, J. Stolfi. Pattern Recognition (PR) (IF: 3.96) , vol 46, num 3, p. 1078-1090, March 2013.
  36. A Cognitive and Video-based Approach for Multinational License Plate Recognition.
    N. Thome, A. Vacavant, L. Robinault, S. Miguet. Machine Vision and Applications (MVA) (IF: 1.306) ,
    vol 22, num 2, p. 389-407, March 2011.
  37. A Real-Time, MultiView Fall Detection System: a LHMM-Based Approach. [pdf]
    N. Thome, S. Miguet, Sébastien Ambellouis. IEEE Transactions on Circuits and Systems for Video Technology (IF: 3.558),
    Special Issue on Event Analysis in Videos, vol 18, Issue 11, p.1522-1532, November 2008.
  38. Learning Articulated Appearance Models for Tracking Humans: a Spectral Graph Matching Approach. [pdf]
    N. Thome, D. Mérad, S. Miguet. Signal Processing: Image Communication (IF: 2.073) , vol. 23, issue 10, p.769-787, December 2008.

International Conferences

  1. Boosting Visual Instruction Tuning with Self-Supervised Guidance. [pdf].
    S. Sirko-Galouchenko, M. Wysoczanska, A. Bursuc, N. Thome, S. Gidaris.     NeurIPS 2026.
  2. PRISM: Perception Reasoning Interleaved for Sequential Decision Making [pdf].
    S. Aissi, C. Grislain, C. Romac, L. Soulier, M. Chetouani, O. Sigaud, N. Thome.     ICML 2026.
  3. NAF: Zero-Shot Feature Upsampling via Neighborhood Attention Filtering [pdf].
    L. Chambon, P. Couairon, E. Zablocki, A. Boulch, N. Thome, M. Cord.     CVPR 2026.
  4. CLIPTTA: Robust Contrastive Vision-Language Test-Time Adaptation. [pdf].
    M. Lafon, G. Vargas Hakim, C. Rambour, C. Desrosiers, N. Thome.     NeurIPS 2025.
  5. JAFAR: Jack up Any Feature at Any Resolution. [pdf].
    P. Couairon, L. Chambon, L. Serrano, J.E. Haugeard, M. Cord, N. Thome.     NeurIPS 2025.
  6. ViLU: Learning Vision-Language Uncertainties for Failure Prediction. [pdf].
    M. Lafon, Y. Karmim, J. Silva-Rodriguez, P. Couairon, C. Rambour, R. Fournier, I. Ben Ayed, J. Dolz, N. Thome.     ICCV 2025.
  7. DIP: Unsupervised Dense In-Context Post-training of Visual Representations. [pdf].
    S. Sirko-Galouchenko, S. Gidaris, A. Vobecky, A. Bursuc, N. Thome.     ICCV 2025.
  8. RT-HCP: Dealing with Inference Delays and Sample Efficiency to Learn Directly on Robotic
    Platforms. [pdf]    . Z. El Asri, I. Laiche, C. Rambour, O. Sigaud, N. Thome. IROS 2025.
  9. Decoupled Asymmetric Fusion of Tabular and Echocardiographic Data for Cardiac Hypertension
    Diagnosis. [pdf]    . J. Stym-Popper, N. Painchaud, C. Rambour, P.Y. Courand, N. Thome, O. Bernard. MIDL 2025.
  10. Reinforcement Learning for Aligning LLM Agents: Quantifying and Mitigating Prompt Overfitting. [pdf]
    S. Aissi, C. Romac, T. Carta, S. Lamprier, P.Y. Oudeyer, O. Sigaud, L. Soulier, N. Thome. NAACL 2025 Findings.
  11. Supra-Laplacian Encoding for Transformer on Dynamic Graphs. [pdf]
    Y. Karmim, R. Fournier, M. Lafon, N. Thome. NeurIPS 2024.
  12. Zero-Shot Image Segmentation via Recursive Normalized Cut on Diffusion Features. [pdf]
    P. Couairon, M. Shukor, J.E. Haugeard, M. Cord, N. Thome. NeurIPS 2024.
  13. GalLoP: Learning Global and Local Prompts for Vision-Language Models. [pdf]
    M. Lafon, E. Ramzi, C. Rambour, N. Audebert, N. Thome. ECCV 2024.
  14. Physics-Informed Model and Hybrid Planning for Efficient Dyna-Style Reinforcement Learning. [pdf]
    Z. El Asri, O. Sigaud, N. Thome. RLC 2024.
  15. Hybrid Energy Based Model in the Feature Space for Out-of-Distribution Detection. [pdf]
    M. Lafon, E. Ramzi, C. Rambour, N. Thome. ICML 2023.
  16. Large-scale Learning of Turbulent Fluid Dynamics with Mesh Transformers. [pdf] - [demo-page]
    S. Janny, A. Bénéteau, M. Nadri, J. Digne, N. Thome, C. Wolf. ICLR 2023.
  17. Full Contextual Attention for Multi-resolution Transformers in Semantic Segmentation. [pdf]
    L. Themyr, C. Rambour, N. Thome, T. Collins, A. Hostettler. WACV 2023.
  18. Complementing Brightness Constancy with Deep Networks for Optical Flow Prediction. [pdf]
    V. Le Guen, C. Rambour, N. Thome. ECCV 2022. GitHub code
  19. Hierarchical Average Precision Training for Pertinent Image Retrieval. [pdf]
    E. Ramzi, N. Audebert, N. Thome, C. Rambour, X. Bitot. ECCV 2022. GitHub code
  20. Diverse probabilistic trajectory forecasting with admissibility constraints. [pdf]
    L. Calem, H. Ben Younes, N. Thome, P. Pérez. ICPR 2022.
  21. Swapping Semantic Contents for Mixing Images. [pdf]
    R. Sun, C. Masson, G. Hénaff, N. Thome, M. Cord. ICPR 2022.
  22. Robust and Decomposable Average Precision for Image Retrieval. [pdf]
    E. Ramzi, N. Thome, C. Rambour, N. Audebert, X. Bitot. NeurIPS 2021. GitHub code
  23. Augmenting Physical Models with Deep Networks for Complex Dynamics Forecasting. [pdf]
    Y. Yin, V. Le Guen, J. Dona, I. Ayed, E. de Bezenac, N. Thome, P. Gallinari. ICLR 2021 (oral). GitHub code
  24. Probabilistic Time Series Forecasting with Shape and Temporal Diversity. [pdf]
    V. Le Guen, N. Thome. NeurIPS 2020. GitHub code
  25. Disentangling Physical Dynamics from Unknown Factors for Unsupervised Video Prediction. [pdf]
    V. Le Guen, N. Thome. CVPR 2020. GitHub code
  26. Shape and Time Distortion Loss for Training Deep Time Series Forecasting Models. [pdf]
    V. Le Guen, N. Thome. NeurIPS 2019. GitHub code
  27. Addressing Failure Detection by Learning Model Confidence. [pdf]
    C. Corbière, N. Thome, A. Bar-Hen, M. Cord, P. Pérez. NeurIPS 2019. GitHub code
  28. DiscoNet: Shapes Learning on Disconnected Manifolds for 3D Editing. [pdf]
    E. Mehr, A. Jourdan, N. Thome, M. Cord, V. Guitteny. ICCV 2019.
  29. MUREL: Multimodal Relational Reasoning for Visual Question Answering. [pdf]
    H. Ben-younes, R. Cadene, M. Cord, N. Thome. CVPR 2019. GitHub code
  30. BLOCK: Bilinear Superdiagonal Fusion for Visual Question Answering and Visual Relationship
    Detection. [pdf].     H. Ben-younes, R. Cadene, N. Thome, M. Cord. AAAI 2019. GitHub code
  31. Revisiting Multi-Task Learning with ROCK: a Deep Residual Auxiliary Block for Visual Detection. [pdf]
    T. Mordan, N. Thome, G. Henaff, M. Cord. NeurIPS 2018.
  32. HybridNet: Classification and Reconstruction Cooperation for Semi-Supervised Learning. [pdf]
    T. Robert, N. Thome, M. Cord. ECCV 2018.
  33. Manifold Learning in Quotient Spaces. [pdf]
    E. Mehr, A. Lieutier, F. Sanchez, N. Thome, M. Cord, V. Guitteny. CVPR 2018.
  34. SHADE: Information-Based Regularization for Deep Learning. [pdf]
    M. Blot, T. Robert, N. Thome, M. Cord. ICIP 2018. ICIP'18 Best Paper Award
  35. Cross-modal Retrieval in the Cooking Context: Learning Semantic Text-Image Embeddings. [pdf]
    M. Carvalho, R. Cadene, D. Picard, L. Soulier, N. Thome, M. Cord. SIGIR 2018.
  36. MUTAN: Multimodal Tucker Fusion for Visual Question Answering. [pdf]
    H. Ben-younes, R. Cadene, M. Cord, N. Thome. ICCV 2017.
  37. Deformable Part-based Fully Convolutional Network for Object Detection. [pdf]
    T. Mordan, N. Thome, M. Cord, G. Henaff. BMCV 2017 (oral). BMVC'17 Best Science Paper Award
  38. WILDCAT: Weakly Supervised Learning of Deep ConvNets for Image Classification,
    Pointwise Localization and Segmentation. [pdf]    . T. Durand, T.Mordan, N. Thome, M. Cord. CVPR 2017.
  39. WELDON: Weakly Supervised Learning of Deep Convolutional Neural Networks. [pdf]
    T. Durand, N. Thome, M. Cord. CVPR 2016.
  40. Gaze Latent Support Vector Machine for Image Classification. [pdf]
    X. Wang, N. Thome, M. Cord. ICIP 2016.
  41. Max-Min convolutional neural networks for image classification. [pdf]
    M. Blot, N. Thome, M. Cord. ICIP 2016.
  42. Deep Neural Netwrks Under Stress. [pdf]
    M. Carvalho, M. Cord, S. Avila, N. Thome, E. Valle. ICIP 2016.
  43. MANTRA: Minimum Maximum Latent Structural SVM for Image Classification and Ranking. [pdf]
    T. Durand, N. Thome, M. Cord. ICCV 2015.
  44. LR-CNN For Fine-grained Classification with Varying Resolution. [pdf].
    M. Chevalier, N. Thome, M. Cord, J. Fournier, G. Henaff and E. Dusch. ICIP 2015.
  45. Exemplar Based Metric Learning For Robust Visual Localization. [pdf].
    C. Le Barz, N. Thome, M. Cord, M. Sanfourche and S. Herbin. ICIP 2015.
  46. Incremental Learning of Latent Structural SVM for Weakly Supervised Image Classification. [pdf].
    T. Durand, N. Thome, M. Cord. ICIP 2014, Paris, France, 27-30 Oct 2014.
  47. Semantic Pooling for Image Categorization using Multiple Kernel Learning. [pdf]
    T. Durand, D. Picard, N. Thome, M. Cord. ICIP 2014, Paris, France, 27-30 Oct 2014.
  48. Fantope Regularization in Metric Learning. [pdf]- [Project Page]
    M. Law, N. Thome, M. Cord. CVPR 2014, Columbus, Ohio, USA, 24-27 June 2014.
  49. Sequentially Generated Instance-Dependent Image Representations for Classification. [pdf]
    G. Dulac-Arnold, L. Denoyer, N. Thome, M. Cord, P. Gallinari. ICLR 2014, Banff, Canada, 14-16 April 2014.
  50. Top-Down Regularization of Deep Belief Networks. [pdf]
    H. Goh, N. Thome, M. Cord, J.H. Lim. NIPS 2013, p 1878-1886, Lake Tahoe, Nevada, USA, 5-8 December 2013.
  51. Quadruplet-wise Image Similarity Learning. [pdf] [Project Page]
    M. Law, N. Thome, M. Cord. ICCV 2013 , Sydney, Australia, 3-6 December 2013.
  52. Image Classification using Object Detectors. [pdf]
    T. Durand, N. Thome, M. Cord, S. Avila. ICIP 2013, p. 4340-4344, Melbourne, Australia, 15-18 Sep 2013.
  53. Dynamic Scene Classification: Learning Motion Descriptors with Slow Features Analysis. [pdf]
    C. Theriault, N. Thome, M. Cord. CVPR 2013, p 2603-2610, Portland, OR, USA, 23-28 June 2013.
  54. Unsupervised and Supervised Visual Codes with Restricted Boltzmann Machines. [pdf]
    H. Goh, N. Thome, M. Cord, J.H. Lim. ECCV 2012, p 298-311, Firenze, Italy, 7-13 Oct 2012.
  55. Structural and visual comparisons for Web page archiving. [pdf]
    M. Law, N. Thome, M. Cord, S. Gancarski. DocEng 2012.
  56. Contextual Detection of drawn Symbols in old Maps. [pdf]
    J. Guyomard, N. Thome, M. Cord, T. Artières. ICIP 2012, p 837-840, Orlando, USA, 2012.
  57. BossaNova at ImageCLEF 2012 Flickr Photo Annotation Task. [pdf]
    S. Avila, N. Thome, M. Cord, E. Valle, A. Araùjo. CLEF 2012.
  58. Learning geometric combinations of Gaussian kernels with alternating Quasi-Newton algorithm [pdf]
    D. Picard, N. Thome, M. Cord, A. Rakotomamonjy. ESANN 2012.
  59. Classification of Urban Scenes from Georeferenced Images in Urban Street-View Context
    C. Iovan, D. Picard, N. Thome, M. Cord. ICMLA 2012.
  60. HMAX-S: Deep scale representation for biologically inspired image categorization. [pdf]
    C. Theriault, N. Thome, M. Cord. ICIP 2011, p 1261-1264, Brussels, 11-14 Sep 2011.
  61. BOSSA: extended BoW formalism for image classification. [pdf]
    S. Avila, N. Thome, M. Cord, E. Valle, A. de Albuquerque. ICIP 2011, p 2909-2912, ISBN: 978-1-4673-0062-9, Brussels, 11-14 Sep 2011.
  62. SnooperTrack: Text Detection and Tracking for Outdoor Videos. [pdf]
    R. Minetto, N. Thome, M. Cord, N. Leite, J. Stolfi. ICIP 2011, p 505-508, ISBN: 978-1-4577-1304-0, Brussels, 11-14 Sep 2011.
  63. Learning Invariant Color Features with Sparse Topographic RBM. [pdf]
    H. Goh, L. Kusmierz, J.H. Lim, N. Thome, M. Cord. ICIP 2011., p 1241-1244, Brussels, 11-14 Sep 2011.
  64. Efficient Bag-of-Feature kernel representation for image similarity search. [pdf]
    F. Precioso, M. Cord, D. Gorisse, N. Thome. ICIP 2011.p 109-112, Brussels, 11-14 Sep 2011.
  65. Pedestrian head detection and tracking using graph skeleton for people counting in crowded
    environments. [pdf]     K.E. Aziz, D. Merad, N. Thome, B. Fertil. MVA 2011.
  66. People counting using skeleton graph and tracking.
    K.E. Aziz, D. Merad, N. Thome, B. Fertil. SIPA 2011, Crete, Greece, 2011.
  67. An efficient System for combining complementary kernels in complex visual categorization tasks. [pdf]
    D. Picard, N. Thome, M. Cord. ICIP 2010 , p 3877-3880, Hong-Kong, 26-29 Sep 2010.
  68. SnooperText: A Multiresolution System for Text Detection in Complex Visual Scenes. [pdf]
    R. Minetto, N. Thome, M. Cord, J. Fabrizio, B. Marcotegui. ICIP 2010, p 3861-3864, Hong-Kong, 26-29 Sep 2010.
  69. Fast People Counting using Head Detection from Skeleton Graph. [pdf]
    D. Merad, K.E. Aziz, N. Thome. AVSS 2010, pp.233-240, Boston, 29 august-1 september 2010.
  70. A Bottom/Up, View Point Invariant Human Detector. [pdf]
    N. Thome and Sébastien Ambellouis. ICPR 2008, p. 1-4, Tampa, Florida, December 8-11 2008.
  71. A Combined Statistical-Structural Strategy for Alphanumeric Recognition. [pdf]
    N. Thome and Antoine Vacavant. ISVC 2007, p. 529-538 Lake Tahoe, Nevada, California, November 26--28 2007.
  72. A HHMM-Based Approach for Robust Fall Detection. [pdf]
    N. Thome and Serge Miguet. ICARCV 2006, P. 1-8, Singapore, 4-9 december 2006.
  73. Human Body Part Labeling and Tracking Using Graph Matching Theory. [pdf]
    N. Thome, Djamel Mérad and Serge Miguet. AVSS 2006 , p. 38-43, Sydney, 21-24 november 2006.
  74. A Robust Appearance Model for Tracking Human Motions. [pdf]
    N. Thome and Serge Miguet. AVSS 2005, p. 528-533, Como, 15-16 september 2005. Best Paper Award.

International Workshops

  1. MODIP: Efficient Model-Based Optimization for Diffusion Policies. [pdf]
    Z. El Asri, P. Gratias, N. Thome, O. Sigaud. European Workshop on Reinforcement Learning (EWRL), 2026.
  2. TSPFN: A Temporal Tabular Foundation Model for Physiological Time Series Classification. [pdf]
    J. Stym, C. Rambour, F. Granese, N. Thome, O. Bernard. STACOM Workshop, MICCAI 2026.
  3. Temporal receptive field in dynamic graph learning: a comprehensive analysis. [pdf]
    Y. Karmim, L. Yang, R. Fournier, N. Thome, C. Chatelain, S. Adam. Workshop on Mining and Learning with Graphs, ECML PKDD 2024.
  4. VidEdit: Zero-Shot and Spatially Aware Text-Driven Video Editing. [pdf]
    P. Couairon, C. Rambour, N. Thome. Workshop on Diffusion Models, NeurIPS 2023.
  5. Residual Model-Based Reinforcement Learning for Physical Dynamics. [pdf]
    Z. El Asri, C. Rambour, V. Le Guen, N. Thome. 3rd Offline RL Workshop: Offline RL as a "Launchpad", NeurIPS 2022.
  6. Memory transformers for full context and high-resolution 3D Medical Segmentation. [pdf]
    L. Themyr, C. Rambour, N. Thome, T. Collins, A. Hostettler. Machine Learning in Medical Imaging (MLMI) workshop, MICCAI 2022.
  7. Adapting Multi-Input Multi-Output schemes to Vision Transformers. [pdf]
    R. Sun,C. Masson, N. Thome, M. Cord. Workshop on Efficient Deep Learning for Computer Vision (ECV), CVPR 2022.
  8. Towards efficient feature sharing in MIMO architectures. [pdf]
    R. Sun, A. Ramé, C. Masson, N. Thome, M. Cord. Workshop on Transformers and Attention for vision (T4V), CVPR 2022.
  9. U-Net Transformer: Self and Cross Attention for Medical Image Segmentation. [pdf]
    O. Petit, N. Thome, C. Rambour, L. Themyr, T. Collins, L. Soler. Machine Learning in Medical Imaging (MLMI) workshop, MICCAI 2021.
  10. Beyond First-Order Uncertainty Estimation with Evidential Models for Open-World Recognition. [pdf]
    C. Corbière, M. Lafon, N. Thome, M. Cord, P. Pérez. workshop on Uncertainty and Robustness in Deep Learning, ICML 2021.
  11. Semantic Augmentation with Self-Supervised Content Mixing for Semi-Supervised Learning. [pdf]
    R. Sun, C. Masson, G. Hénaff, N. Thome, M. Cord. Workshop on Self-Supervised Learning, Theory and Practice, NeurIPS 2020.
  12. A Deep Physical Model for Solar Irradiance Forecasting with Fisheye Images. [pdf]
    V. Le Guen, N. Thome. CVPR OMNI-CV workshop, 2020.
  13. Prévision de l'irradiance solaire par réseaux de neurones profonds à l'aide de caméras au sol. [pdf]
    V. Le Guen, N. Thome. GTETSI, XXVIIème Colloque francophonede traitement du signal et des images, Lille, 26-29 Aout 2019.
  14. Biasing Deep ConvNets for Semantic Segmentation of Medical Images with a Prior-driven Prediction Function. [pdf]. O. Petit, N. Thome, L. Soler. Extended abstract in MIDL, London, 8-10 July 2019.
  15. Multitask Classification and Segmentation for Cancer Diagnosis in Mammograph. [pdf]. T. Le, N. Thome, S. Bernard, V. Bismuth, F. Patoureaux. Extended abstract in MIDL, London, 8-10 July 2019.
  16. Handling Missing Annotations for Semantic Segmentation with Deep ConvNets. [pdf]
    O. Petit, N. Thome, A. Charnoz, A. Hostettler, L. Soler. 4th Workshop on Deep Learning in Medical Image Analysis, MICCAI 2018.
  17. Fully Convolutional Neural Network for accurate segmentation in CT Data. [pdf]
    B. Radharapu, N. Thome. Women in Machine Learning Workshop, NIPS 2017.
  18. M2CAI Challenge: Convolutional Neural Networks for Video Frames Classification. [pdf] - [poster]
    R. Cadene, T. Robert, N. Thome, M. Cord. . M2CAI Workshop, Workflow Challenge, MICCAI 2016.
  19. Low resolution convolutional neural network for automatic target recognition.
    M. Chevalier, N.home, M. Cord, G. Henaff, and E. Dusch. In 7th International Symposium on Optronics in Defence and Security, 2016.
  20. Recipe Recognition with Large Multimodal Food Dataset. [pdf]
    X. Wang, D. Kumar, N. Thome, M. Cord, F. Precioso. Workshop on Cooking and Eating Activities, ICME 2015.
  21. Absolute geo-localization thanks to Hidden Markov Model and exemplar-based metric learning. [pdf]
    C. Le Barz, N. Thome, M. Cord, Martial Sanfourche and S. Herbin. Workshop on Computer Vision in Vehicle Technology, CVPR 2015.
  22. Hybrid Pooling Fusion in the BoW Pipeline. [pdf]
    M. Law, N. Thome, and M. Cord. Workshop on Information fusion in computer vision for concept recognition, ECCV 2012.
  23. Structural and Visual Similarity Learning for Web Page Archiving. [pdf]
    M. Law, C. Sureda, N. Thome, S. Gancarski and M. Cord. 10th workshop on Content-Based Multimedia Indexing, CBMI 2012.
  24. Text Detection and Recognition in Urban Scenes. [pdf]
    R. Minetto, N. Thome, M. Cord, J. Stolfi, F. Precioso, J. Guyomard, N.J Leite. CVRS workshop - ICCV 2011.
  25. Combining complementary kernels in complex visual categorization. [poster][abstract]
    N. Thome, M. Cord and D. Picard. KDCV workshop - ICCV 2011, Barcelona, 6-13 Nov 2011.
  26. Biasing Restricted Boltzmann Machines to Manipulate Latent Selectivity and Sparsity. [pdf] [Supplementary]
    H. Goh, N. Thome, M. Cord. NIPS 2010 Workshop on Deep Learning and Unsupervised Feature Learning, p 1-8, Vancouver, Canada, 2010.

Book Chapters

  1. Beyond full supervision in deep learning [chapter]
    N. Thome. Multi-faceted Deep Learning: Models and Data, Springer, 2022.
  2. Cortical Networks of Visual Recognition
    C. Thériault, N. Thome, and M. Cord. Biologically-inspired Computer Vision: Fundamentals and Applications, 2015.
  3. Bag of Words Image Representation: Key Ideas and Further Insight
    M. Law, N. Thome, and M. Cord. Fusion in Computer Vision - Understanding Complex Visual Content, 2014.