2008-2022 Publications

• 2022
  • Ch. Corbière, N. Thome, A. Saporta, T.‑H. Vu, M. Cord, P. Pérez : “Confidence Estimation via Auxiliary Models”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44 (10), pp. 6043-6055, (Institute of Electrical and Electronics Engineers) (2022)
• 2021
  • Y. Yin, V. Le Guen, J. Donà, E. De Bézenac, I. Ayed, N. Thome, P. Gallinari : “Augmenting physical models with deep networks for complex dynamics forecasting”, Journal of Statistical Mechanics: Theory and Experiment, vol. 2021 (12), pp. 124012, (IOP Publishing) (2021)
  • Ch. Corbière, M. Lafon, N. Thome, M. Cord, P. Pérez : “Beyond First-Order Uncertainty Estimation with Evidential Models for Open-World Recognition”, ICML 2021 Workshop on Uncertainty and Robustness in Deep Learning, Virtual, Austria (2021)
  • Y. Yin, V. Le Guen, J. Donà, I. Ayed, E. De Bézenac, N. Thome, P. Gallinari : “Augmenting physical models with deep networks for complex dynamics forecasting”, Ninth International Conference on Learning Representations ICLR 2021, Vienna (virtual), Austria (2021)
• 2019
  • Ch. Corbière, N. Thome, A. Bar‑Hen, M. Cord, P. Pérez : “Addressing Failure Prediction by Learning Model Confidence”, Advances in Neural Information Processing Systems 32, Vancouver, Canada, pp. 2898-2909, (Curran Associates, Inc.) (2019)
  • R. Cadene, H. Ben‑younes, M. Cord, N. Thome : “MUREL: Multimodal Relational Reasoning for Visual Question Answering”, The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, United States (2019)
  • Th. Durand, N. Thome, M. Cord : “Exploiting Negative Evidence for Deep Latent Structured Models”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 41 (2), pp. 337-351, (Institute of Electrical and Electronics Engineers) (2019)
  • H. Ben‑younes, R. Cadene, N. Thome, M. Cord : “BLOCK: Bilinear Superdiagonal Fusion for Visual Question Answering and Visual Relationship Detection”, AAAI 2019 - 33^rd AAAI Conference on Artificial Intelligence, Honolulu, United States (2019)
  • M. Blot, D. Picard, N. Thome, M. Cord : “Distributed Optimization for Deep Learning with Gossip Exchange”, Neurocomputing, vol. 330, pp. 287-296, (Elsevier) (2019)
• 2018
  • T. Mordan, N. Thome, G. Henaff, M. Cord : “Revisiting Multi-Task Learning with ROCK: a Deep Residual Auxiliary Block for Visual Detection”, Advances in Neural Information Processing Systems 32 (NeurIPS 2018), Montréal, Canada (2018)
  • M. CHEVALIER, N. Thome, G. Henaff, M. Cord : “Classifying low-resolution images by integrating privileged information in deep CNNs”, Pattern Recognition Letters, vol. 116, pp. 29-35, (Elsevier) (2018)
  • Th. Durand, N. Thome, M. Cord : “SyMIL: MinMax Latent SVM for Weakly Labeled Data”, IEEE Transactions on Neural Networks and Learning Systems, vol. 29 (12), pp. 6099-6112, (IEEE) (2018)
  • M. Blot, Th. Robert, N. Thome, M. Cord : “SHADE: Information-Based Regularization for Deep Learning”, ICIP 2018 - 25^th IEEE International Conference on Image Processing, Athènes, Greece, pp. 813-817, (IEEE) (2018)
  • Th. Robert, N. Thome, M. Cord : “HybridNet: Classification and Reconstruction Cooperation for Semi-supervised Learning”, Computer Vision – ECCV 2018 15^th European Conference, Munich, Germany, September 8–14, 2018, Proceedings, vol. 11211, Lecture Notes in Computer Science, Munich, Germany, pp. 158-175, (Springer) (2018)
  • T. Mordan, N. Thome, G. Henaff, M. Cord : “End-to-End Learning of Latent Deformable Part-Based Representations for Object Detection”, International Journal of Computer Vision, (Springer Verlag) (2018)
  • E. Mehr, A. Lieutier, F. Bermudez, V. Guitteny, N. Thome, M. Cord : “Manifold Learning in Quotient Spaces”, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, United States, pp. 9165-9174, (IEEE) (2018)
  • M. Carvalho, R. Cadene, D. Picard, L. Soulier, N. Thome, M. Cord : “Cross-Modal Retrieval in the Cooking Context”, SIGIR proceedings, Ann Arbor, Michigan, United States, pp. 35-44, (ACM Press) (2018)
• 2017
  • X. Wang, N. Thome, M. Cord : “Gaze Latent Support Vector Machine for Image Classification Improved by Weakly Supervised Region Selection”, Pattern Recognition, vol. 72, pp. 59-71, (Elsevier) (2017)
  • H. Ben‑younes, R. Cadene, M. Cord, N. Thome : “MUTAN: Multimodal Tucker Fusion for Visual Question Answering”, 2017 IEEE International Conference on Computer Vision (ICCV), 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy, pp. 2631-2639, (IEEE) (2017)
  • T. Mordan, N. Thome, M. Cord, G. Henaff : “Deformable Part-based Fully Convolutional Network for Object Detection”, British Machine Vision Conference (BMVC), London, United Kingdom (2017)
  • Th. Durand, T. Mordan, N. Thome, M. Cord : “WILDCAT: Weakly Supervised Learning of Deep ConvNets for Image Classification, Pointwise Localization and Segmentation”, IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, United States, pp. 5957-5966 (2017)
• 2016
  • M. Carvalho, M. Cord, S. Avila, N. Thome, E. Valle : “Deep Neural Networks Under Stress”, IEEE International Conference on Image Processing (ICIP 2016), Phoenix, AZ, United States (2016)
  • X. Wang, N. Thome, M. Cord : “GAZE LATENT SUPPORT VECTOR MACHINE FOR IMAGE CLASSIFICATION”, IEEE International Conference on Image Processing (ICIP), Phoenix, AZ, United States (2016)
  • Th. Durand, N. Thome, M. Cord : “WELDON: Weakly Supervised Learning of Deep Convolutional Neural Networks”, 29^th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016), Las Vegas, NV, United States (2016)
  • M. CHEVALIER, N. Thome, M. Cord, J. Fournier, G. Henaff, E. Dusch : “LOW RESOLUTION CONVOLUTIONAL NEURAL NETWORK FOR AUTOMATIC TARGET RECOGNITION”, 7^th International Symposium on Optronics in Defence and Security, Paris, France (2016)
  • M. Blot, M. Cord, N. Thome : “Max-min convolutional neural networks for image classification”, Image Processing (ICIP), 2016 IEEE International Conference on, Phoenix, United States, pp. 3678-3682, (IEEE) (2016)
  • Marc T. Law, N. Thome, M. Cord : “Learning a Distance Metric from Relative Comparisons between Quadruplets of Images”, International Journal of Computer Vision, pp. 1-30, (Springer Verlag) (2016)
• 2015
  • N. Thome : “Représentations et apprentissage pour l’annotation sémantique de données visuelles”, habilitation, phd defence 07/01/2015 (2015)
  • Th. Durand, N. Thome, M. Cord : “MANTRA: Minimum Maximum Latent Structural SVM for Image Classification and Ranking”, IEEE International Conference on Computer Vision (ICCV15), Santiago, Chile (2015)
  • C. Le Barz, N. Thome, M. Cord, S. Herbin, M. Sanfourche : “EXEMPLAR BASED METRIC LEARNING FOR ROBUST VISUAL LOCALIZATION”, IEEE International Conference on Image Processing, ICIP 2015, Québec, Canada, pp. 388-w6mp-151 (2015)
  • M. CHEVALIER, N. Thome, M. Cord, J. Fournier, G. Henaff, E. Dusch : “LR-CNN FOR FINE-GRAINED CLASSIFICATION WITH VARYING RESOLUTION”, IEEE International Conference on Image Processing, Québec city, Canada (2015)
  • X. Wang, D. Kumar, N. Thome, M. Cord, F. Precioso : “RECIPE RECOGNITION WITH LARGE MULTIMODAL FOOD DATASET”, IEEE International Conference on Multimedia & Expo (ICME), workshop CEA, Turin, Italy (2015)
  • C. Le Barz, N. Thome, M. Cord, S. Herbin, M. Sanfourche : “Absolute geo-localization thanks to Hidden Markov Model and exemplar-based metric learning”, 6^th international Workshop on Computer Vision in Vehicle Technology, CHICAGO, United States (2015)
  • M. Law, N. Thome, S. Gançarski, M. Cord : “Apprentissage de métrique appliqué à la détection de changement de page Web et aux attributs relatifs”, CORIA 2015 - Conférence en Recherche d'Infomations et Applications - 12^th French Information Retrieval Conference, Paris, France (2015)
• 2014
  • H. Goh, N. Thome, M. Cord, J.‑H. Lim : “Learning Deep Hierarchical Visual Feature Coding”, IEEE Transactions on Neural Networks and Learning Systems, vol. 25 (12), pp. 2212-2225, (IEEE) (2014)
  • Th. Durand, N. Thome, M. Cord, D. Picard : “Incremental learning of latent structural SVM for weakly supervised image classification”, IEEE International Conference on Image Processing, Paris, France, pp. 4246-4250, (IEEE) (2014)
  • Th. Durand, D. Picard, N. Thome, M. Cord : “SEMANTIC POOLING FOR IMAGE CATEGORIZATION USING MULTIPLE KERNEL LEARNING”, IEEE International Conference on Image Processing, Paris, France, (Institute of Electrical and Electronics Engineers) (2014)
  • C. Le Barz, N. Thome, M. Cord, S. Herbin, M. Sanfourche : “Global Robot Ego-localization Combining Image Retrieval and HMM-based Filtering”, 6^th Workshop on Planning, Perception and Navigation for Intelligent Vehicles, Chicago, United States, pp. 6 p. (2014)
  • Ch. Theriault, N. Thome, M. Cord, P. Pérez : “Perceptual principles for video classification with Slow Feature Analysis”, IEEE Journal of Selected Topics in Signal Processing, vol. 8 (3), pp. 428-437, (IEEE) (2014)
  • R. Minetto, N. Thome, M. Cord, Neucimar J. Leite, J. Stolfi : “SnooperText: A Text Detection System for Automatic Indexing of Urban Scenes”, Computer Vision and Image Understanding, vol. 122, pp. 92-104, (Elsevier) (2014)
  • G. Dulac‑Arnold, L. Denoyer, N. Thome, M. Cord, P. Gallinari : “Sequentially Generated Instance-Dependent Image Representations for Classification”, International Conference on Learning Representations, ICLR 2014, Banff, Canada (2014)
  • M. Law, N. Thome, M. Cord : “Fantope Regularization in Metric Learning”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, Ohio, United States, pp. 1051-1058 (2014)
  • M. Law, N. Thome, M. Cord : “Bag-of-Words Image Representation: Key Ideas and Further Insight”, chapter in Fusion in Computer Vision - Understanding Complex Visual Content, Advances in Computer Vision and Pattern Recognition, pp. 29-52, (Springer) (2014)
• 2013
  • H. Goh, N. Thome, M. Cord, J.‑H. Lim : “Top-Down Regularization of Deep Belief Networks”, Advances in Neural Information Processing Systems 26, Lake Tahoe, United States, pp. 1878-1886 (2013)
  • Th. Durand, N. Thome, M. Cord, S. Avila : “Image classification using object detectors”, ICIP 2013 : IEEE International Conference on Image Processing, Melbourne, Australia, pp. 4340-4344 (2013)
  • S. Avila, N. Thome, M. Cord, E. Valle, A. De Albuquerque Araújo : “Extended Bag-of-Words Formalism for Image Classification”, Brazilian Symposium on Computer Graphics and Image Processing, Arequipa, Peru (2013)
  • Ch. Theriault, N. Thome, M. Cord : “Dynamic Scene Classification: Learning Motion Descriptors with Slow Features Analysis.”, IEEE Conference on Computer Vision and Pattern Recognition, Portland, OR, United States, pp. 2603-2610, (IEEE) (2013)
  • D. Picard, N. Thome, M. Cord : “JKernelMachines: A Simple Framework for Kernel Machines”, Journal of Machine Learning Research, vol. 14, pp. 1417-1421, (Journal of Machine Learning Research) (2013)
  • S. Avila, N. Thome, M. Cord, E. Valle, A. De Albuquerque Araújo : “Pooling in Image Representation: the Visual Codeword Point of View”, Computer Vision and Image Understanding, vol. 117 (5), pp. 453-465, (Elsevier) (2013)
  • R. Minetto, N. Thome, M. Cord, Neucimar J. Leite, J. Stolfi : “T-HOG: an Effective Gradient-Based Descriptor for Single Line Text Regions”, Pattern Recognition, vol. 46 (3), pp. 1078-1090, (Elsevier) (2013)
  • Ch. Theriault, N. Thome, M. Cord : “Extended Coding and Pooling in the HMAX Model”, IEEE Transactions on Image Processing, vol. 22 (2), pp. 764-777, (Institute of Electrical and Electronics Engineers) (2013)
  • M. Law, N. Thome, M. Cord : “Quadruplet-Wise Image Similarity Learning”, IEEE International Conference on Computer Vision (ICCV), Sydney, Australia, pp. 249-256 (2013)
• 2012
  • H. Goh, N. Thome, M. Cord, J.‑H. Lim : “Unsupervised and supervised visual codes with restricted Boltzmann machines”, 12^th European conference on Computer Vision, vol. 7576, Lecture Notes in Computer Science, Florence, Italy, pp. 298-311 (2012)
  • M. Law, N. Thome, M. Cord : “Hybrid Pooling Fusion in the BoW Pipeline”, ECCV 2012 Workshop on Information fusion in Computer Vision for Concept Recognition (ECCV-IFCVCR 2012), vol. 7585, Lecture Notes in Computer Science, Florence, Italy, pp. 355-364, (Springer) (2012)
  • J. Guyomard, N. Thome, M. Cord, Th. Artières : “Contextual Detection of Drawn Symbols in Old Maps”, International Conference on Image Processing (ICIP), Orlando, Florida, United States, pp. 837-840, (IEEE) (2012)
  • M. Law, N. Thome, S. Gançarski, M. Cord : “Structural and Visual Comparisons for Web Page Archiving”, 12^th edition of the ACM Symposium on Document Engineering, DocEng'12, Paris, France, pp. 117-120, (ACM) (2012)
  • M. Law, C. Sureda Gutierrez, N. Thome, S. Gançarski, M. Cord : “Structural and Visual Similarity Learning for Web Page Archiving”, 10^th workshop on Content-Based Multimedia Indexing (CBMI), Annecy, France, pp. 1-6, (IEEE) (2012)
  • D. Picard, N. Thome, M. Cord, A. Rakotomamonjy : “Learning geometric combinations of Gaussian kernels with alternating Quasi-Newton algorithm”, ESANN 2012, Bruges, Belgium, pp. 79-84 (2012)
  • M. Boufarguine, N. Thome, V. Guitteny, F. Precioso : “Suivi 3D Monoculaire pour un Système de Vidéosurveillance à l’aide d’un Modèle de Mouvement et un Modèle d’Apparence”, RFIA 2012 (Reconnaissance des Formes et Intelligence Artificielle), Lyon, France (2012)
  • C. Iovan, D. Picard, N. Thome, M. Cord : “Classification of Urban Scenes from Geo-referenced Images in Urban Street-View Context”, Machine Learning and Applications (ICMLA), 2012 11^th International Conference on, vol. 2, Boca Raton, Florida, United States, pp. 339-344 (2012)
• 2011
  • R. Minetto, N. Thome, M. Cord, J. Stolfi, F. Precioso, J. Guyomard, Neucimar J. Leite : “Text Detection and Recognition in Urban Scenes”, International Conference on Computer Vision (ICCV): Workshop on Computer Vision for Remote Sensing of the Environment, Barcelona, Spain, pp. 227-234, (IEEE) (2011)
  • S. Avila, N. Thome, M. Cord, E. Valle, A. De Albuquerque Araújo : “BOSSA: extended BoW formalism for image classification”, IEEE International Conference on Image Processing (ICIP), Brussels, Belgium, pp. 2909-2912, (IEEE) (2011)
  • R. Minetto, N. Thome, M. Cord, Neucimar J. Leite, J. Stolfi : “SNOOPERTRACK: TEXT DETECTION AND TRACKING FOR OUTDOOR VIDEOS”, IEEE International Conference on Image Processing (ICIP), Brussels, Belgium, pp. 505-508, (IEEE) (2011)
  • F. Precioso, M. Cord, D. Gorisse, N. Thome : “Efficient bag-of-feature kernel representation for image similarity search”, ICIP 2011 - IEEE International Conference on Image Processing, Bruxelles, Belgium, pp. 109-112, (IEEE) (2011)
  • N. Thome, A. Vacavant, L. Robinault, S. Miguet : “A cognitive and video-based approach for multinational License Plate Recognition”, Machine Vision and Applications, vol. 22 (2), pp. 389-407, (Springer Verlag) (2011)
  • Ch. Theriault, N. Thome, M. Cord : “HMAX-S: DEEP SCALE REPRESENTATION FOR BIOLOGICALLY INSPIRED IMAGE CATEGORIZATION”, IEEE International Conference on Image Processing, Brussels, Belgium, pp. 1261-1264, (IEEE) (2011)
  • H. Goh, K. Łukasz, J.‑H. Lim, N. Thome, M. Cord : “Learning Invariant Color Features with Sparse Topographic Restricted Boltzmann Machines”, ICIP 2011 - IEEE International Conference on Image Processing, Brussels, Belgium, pp. 1241-1244 (2011)
• 2010
  • D. Mérad, Kh. Aziz, N. Thome : “Fast People Counting using Head Detection from Skeleton Graph”, IEEE International Conference on Advanced Video and Signal based Surveillance (AVSS), Boston, MA, United States, pp. 233-240, (IEEE) (2010)
  • H. Goh, N. Thome, M. Cord : “Biasing Restricted Boltzmann Machines to Manipulate Latent Selectivity and Sparsity”, NIPS 2010 Workshop on Deep Learning and Unsupervised Feature Learning, Vancouver, Canada (2010)
  • D. Picard, N. Thome, M. Cord : “An efficient System for combining complementary kernels in complex visual categorization tasks”, ICIP 2010 - 17^th IEEE International Conference on Image Processing, Hong Kong, Hong Kong, pp. 3877-3880, (IEEE) (2010)
  • R. Minetto, N. Thome, M. Cord, J. Fabrizio, B. Marcotegui : “Snoopertext: A multiresolution system for text detection in complex visual scenes”, ICIP 2010 - 17^th IEEE International Conference on Image Processing, Hong-Kong, Hong Kong, pp. 3861-3864, (IEEE) (2010)
• 2008
  • N. Thome, S. Miguet, S. Ambellouis : “A Real-Time, Multi-View Fall Detection System: a LHMM-Based Approach”, IEEE Transactions on Circuits and Systems for Video Technology, vol. 18 (11), pp. 1522-1532, (Institute of Electrical and Electronics Engineers) (2008)
  • N. Thome, D. Mérad, S. Miguet : “Learning Articulated Appearance Models for Tracking Humans: a Spectral Graph Matching Approach”, Signal Processing: Image Communication, vol. 23 (10), pp. 769-787, (Elsevier) (2008)