Nicolas Thome
Membre associé
Site web : http://cedric.cnam.fr/~thomen/
Téléphone : +33 1 58 80 85 48
Bureau : 37.1.41
2024
Articles de revue
- Semantic augmentation by mixing contents for semi-supervised learning. In Pattern Recognition, 145: 109909, 2024. doi www
- MERLIN-Seg: self-supervised despeckling for label-efficient semantic segmentation. In Computer Vision and Image Understanding, 241, 2024. doi www
- Vision and Structured-Language Pretraining for Cross-Modal Food Retrieval. In Computer Vision and Image Understanding, 247, 2024. www
- Global Registration of Kidneys in 3D Ultrasound and CT images. In International Journal of Computer Assisted Radiology and Surgery, 2024. doi www
- ITEM: Improving Training and Evaluation of Message-Passing based GNNs for top-k recommendation. In Transactions on Machine Learning Research Journal, 2024. www
Articles de conférence
- 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
- Temporal receptive field in dynamic graph learning: A comprehensive analysis. In MLG Workshop at ECML-PKDD, Vilnius (Lituanie), France, 2024. www
- Supra-Laplacian Encoding for Transformer on Dynamic Graphs. In The Thirty-eighth Annual Conference on Neural Information Processing Systems, Vancouver (CA), Canada, 2024. www
- Global Registration of Kidneys in 3D Ultrasound and CT images. In IABM - Colloque Franc cais d'Intelligence Artificielle en Imagerie Biomédicale, Grenoble, France, mars 2024, Grenoble, France, 2024. www
2023
Articles de revue
- Multivariate Emulation of Kilometer-Scale Numerical Weather Predictions with Generative Adversarial Networks: A Proof of Concept. In Artificial Intelligence for the Earth Systems, 2 (4), 2023. doi www
Articles de conférence
- Hierarchical Average Precision Training for Pertinent Image Retrieval. In ORASIS 2023, Carqueiranne, France, 2023. www
- 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
- EAGLE: Large-Scale Learning of Turbulent Fluid Dynamics with Mesh Transformers. In Proceedings The Eleventh International Conference on Learning Representations (ICLR 2023), Kigali, Rwanda, 2023. www
- 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
- Histoire des réseaux de neurones et du deep learning en traitement des signaux et des images. , working paper or preprint. www
- Leveraging Vision-Language Foundation Models for Fine-Grained Downstream Tasks. , working paper or preprint. www
2022
Articles de revue
- Confidence Estimation via Auxiliary Models. In IEEE Transactions on Pattern Analysis and Machine Intelligence, 44 (10): 6043-6055, 2022. doi www
- 3D Spatial Priors for Semi-Supervised Organ Segmentation with Deep Convolutional Neural Networks. In International Journal of Computer Assisted Radiology and Surgery, 17 (1): 129-139, 2022. doi www
- 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
Articles de conférence
- 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
- 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
- Memory transformers for full context and high-resolution 3D Medical Segmentation. In Lecture Notes in Computer Science, vol 13583, Springer, Singapour, Singapore, 2022. doi www
- Swapping Semantic Contents for Mixing Images. In 2022 26th International Conference on Pattern Recognition (ICPR), pages 1280-1286, IEEE, Montreal, Canada, 2022. doi www
- Deeplomatics: A deep-learning based multimodal approach for aerial drone detection and localization. In QUIET DRONES 2022 SECOND INTERNATIONAL SYMPOSIUM ON NOISE FROM UASs/UAVs and eVTOLs SYMPOSIUM PROCEEDINGS, Paris, France, QUIET DRONES 2022 SECOND INTERNATIONAL SYMPOSIUM ON NOISE FROM UASs/UAVs and eVTOLs SYMPOSIUM PROCEEDINGS , 2022. www
- Hierarchical Average Precision Training for Pertinent Image Retrieval. In ECCV 2022, Tel-Aviv, Israel, 2022. www
- Complementing Brightness Constancy with Deep Networks for Optical Flow Prediction. In Lecture Notes in Computer Science, vol 13681, Springer, Tel Aviv, Israel, Lecture Notes in Computer Science, vol 13681 , 2022. doi www
2021
Articles de revue
- Augmenting physical models with deep networks for complex dynamics forecasting. In Journal of Statistical Mechanics: Theory and Experiment, 2021 (12): 124012, 2021. doi www
- Iterative Confidence Relabeling with Deep ConvNets for Organ Segmentation with Partial Labels. In Computerized Medical Imaging and Graphics: 101938, 2021. doi www
Articles de conférence
- Robust and Decomposable Average Precision for Image Retrieval. In Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS 2021), Sydney, Australia, 2021. www
- U-Net Transformer: Self and Cross Attention for Medical Image Segmentation. In MICCAI workshop MLMI, Strasbourg (virtuel), France, 2021. www
- 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
- Augmenting physical models with deep networks for complex dynamics forecasting. In Ninth International Conference on Learning Representations ICLR 2021, Vienna (virtual), Austria, 2021. www
2020
Articles de conférence
- Disentangling Physical Dynamics from Unknown Factors for Unsupervised Video Prediction. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, United States, 2020. doi www
- A Deep Physical Model for Solar Irradiance Forecasting with Fisheye Images. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Seattle, United States, 2020. doi www
- Probabilistic Time Series Forecasting with Structured Shape and Temporal Diversity. In NeurIPS 2020, Vancouver, Canada, 2020. www
2019
Articles de revue
- Distributed Optimization for Deep Learning with Gossip Exchange. In Neurocomputing, 330: 287-296, 2019. doi www
- Exploiting Negative Evidence for Deep Latent Structured Models. In IEEE Transactions on Pattern Analysis and Machine Intelligence, 41 (2): 337-351, 2019. doi www
Articles de conférence
- BLOCK: Bilinear Superdiagonal Fusion for Visual Question Answering and Visual Relationship Detection. In AAAI 2019 - 33rd AAAI Conference on Artificial Intelligence, Honolulu, United States, 2019. www
- Prévision de l'irradiance solaire par réseaux de neurones profonds `a l'aide de caméras au sol. In GRETSI 2019, Lille, France, 2019. www
- MUREL: Multimodal Relational Reasoning for Visual Question Answering. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, United States, 2019. www
- Shape and Time Distortion Loss for Training Deep Time Series Forecasting Models. In Advances in Neural Information Processing Systems 32 (NIPS 2019) proceedings, Vancouver, Canada, Advances in Neural Information Processing Systems 32 (NIPS 2019) proceedings 4191--4203, 2019. www
- Addressing Failure Prediction by Learning Model Confidence. In Advances in Neural Information Processing Systems 32, pages 2898-2909, Curran Associates, Inc., Vancouver, Canada, 2019. www
Divers
- Multitask Classification and Segmentation for Cancer Diagnosis in Mammography. , Annotation cost is a bottleneck for collecting massive data in mammography, especially for training deep neural networks. In this paper, we study the use of heterogeneous levels of annotation granularity to improve predictive performances. More precisely, we introduce a multi-task learning scheme for training convolutional neural network (ConvNets), which combines segmentation and classification, using image-level and pixel-level annotations. In this way, different objectives can be used to regularize training by sharing intermediate deep representations. Successful experiments are carried out on the Digital Database of Screening Mammography (DDSM) to validate the relevance of the proposed approach. www
2018
Articles de revue
- SyMIL: MinMax Latent SVM for Weakly Labeled Data. In IEEE Transactions on Neural Networks and Learning Systems, 29 (12): 6099-6112, 2018. doi www
- End-to-End Learning of Latent Deformable Part-Based Representations for Object Detection. In International Journal of Computer Vision, 2018. doi www
- Classifying low-resolution images by integrating privileged information in deep CNNs. In Pattern Recognition Letters, 116: 29-35, 2018. doi www
Articles de conférence
- HybridNet: Classification and Reconstruction Cooperation for Semi-supervised Learning. In Computer Vision -- ECCV 2018 15th European Conference, Munich, Germany, September 8--14, 2018, Proceedings, pages 158-175, Springer, Munich, Germany, Lecture Notes in Computer Science 11211, 2018. doi www
- SHADE: Information-Based Regularization for Deep Learning. In ICIP 2018 - 25th IEEE International Conference on Image Processing, pages 813-817, IEEE, Athènes, Greece, 2018. doi www
- Handling Missing Annotations for Semantic Segmentation with Deep ConvNets. In DLMIA 2018, ML-CDS 2018: Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, pages 20-28, Springer, Grenade, Spain, Lecture Notes in Computer Science book series (LNIP,volume 11045) , 2018. doi www
- Revisiting Multi-Task Learning with ROCK: a Deep Residual Auxiliary Block for Visual Detection. In Advances in Neural Information Processing Systems 32 (NeurIPS 2018), Montréal, Canada, 2018. www
- Manifold Learning in Quotient Spaces. In 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9165-9174, IEEE, Salt Lake City, United States, 2018. doi www
- Cross-Modal Retrieval in the Cooking Context. In SIGIR proceedings, pages 35-44, ACM Press, Ann Arbor, Michigan, United States, 2018. doi www
2017
Articles de revue
- Gaze Latent Support Vector Machine for Image Classification Improved by Weakly Supervised Region Selection. In Pattern Recognition, 72: 59-71, 2017. doi www
Articles de conférence
- Deformable Part-based Fully Convolutional Network for Object Detection. In British Machine Vision Conference (BMVC), London, United Kingdom, 2017. www
- WILDCAT: Weakly Supervised Learning of Deep ConvNets for Image Classification, Pointwise Localization and Segmentation. In IEEE Conference on Computer Vision and Pattern Recognition, pages 5957-5966, Honolulu, HI, United States, 2017. doi www
- MUTAN: Multimodal Tucker Fusion for Visual Question Answering. In 2017 IEEE International Conference on Computer Vision (ICCV), pages 2631-2639, IEEE, Venice, Italy, 2017 IEEE International Conference on Computer Vision (ICCV) , 2017. doi www
2016
Articles de revue
- Learning a Distance Metric from Relative Comparisons between Quadruplets of Images. In International Journal of Computer Vision: 1-30, 2016. doi www
Articles de conférence
- Deep Neural Networks Under Stress. In IEEE International Conference on Image Processing (ICIP 2016), Phoenix, AZ, United States, 2016. doi www
- Max-min convolutional neural networks for image classification. In Image Processing (ICIP), 2016 IEEE International Conference on, pages 3678-3682, IEEE, Phoenix, United States, 2016. doi www
- WELDON: Weakly Supervised Learning of Deep Convolutional Neural Networks. In 29th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016), Las Vegas, NV, United States, 2016. www
- GAZE LATENT SUPPORT VECTOR MACHINE FOR IMAGE CLASSIFICATION. In IEEE International Conference on Image Processing (ICIP), Phoenix, AZ, United States, 2016. doi www
- LOW RESOLUTION CONVOLUTIONAL NEURAL NETWORK FOR AUTOMATIC TARGET RECOGNITION. In 7th International Symposium on Optronics in Defence and Security, Paris, France, 2016. www
2015
Articles de conférence
- RECIPE RECOGNITION WITH LARGE MULTIMODAL FOOD DATASET. In IEEE International Conference on Multimedia & Expo (ICME), workshop CEA, Turin, Italy, 2015. doi www
- Absolute geo-localization thanks to Hidden Markov Model and exemplar-based metric learning. In 6th international Workshop on Computer Vision in Vehicle Technology, CHICAGO, United States, 2015. www
- Apprentissage de métrique appliqué `a la détection de changement de page Web et aux attributs relatifs. In CORIA 2015 - Conférence en Recherche d'Infomations et Applications - 12th French Information Retrieval Conference, Paris, France, 2015. www
- MANTRA: Minimum Maximum Latent Structural SVM for Image Classification and Ranking. In IEEE International Conference on Computer Vision (ICCV15), Santiago, Chile, 2015. www
- LR-CNN FOR FINE-GRAINED CLASSIFICATION WITH VARYING RESOLUTION. In IEEE International Conference on Image Processing, Québec city, Canada, 2015. www
Divers
2014
Articles de revue
- SnooperText: A Text Detection System for Automatic Indexing of Urban Scenes. In Computer Vision and Image Understanding, 122: 92-104, 2014. doi www
- Perceptual principles for video classification with Slow Feature Analysis. In IEEE Journal of Selected Topics in Signal Processing, 8 (3): 428-437, 2014. doi www
- Learning Deep Hierarchical Visual Feature Coding. In IEEE Transactions on Neural Networks and Learning Systems, 25 (12): 2212-2225, 2014. doi www
Chapitres d'ouvrage
- Bag-of-Words Image Representation: Key Ideas and Further Insight. In Fusion in Computer Vision - Understanding Complex Visual Content, pages 29-52, Springer, Advances in Computer Vision and Pattern Recognition , 2014. doi www
Articles de conférence
- Fantope Regularization in Metric Learning. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 1051-1058, Columbus, Ohio, United States, 2014. doi www
- Global Robot Ego-localization Combining Image Retrieval and HMM-based Filtering. In 6th Workshop on Planning, Perception and Navigation for Intelligent Vehicles, pages 6 p., Chicago, United States, 2014. www
- SEMANTIC POOLING FOR IMAGE CATEGORIZATION USING MULTIPLE KERNEL LEARNING. In IEEE International Conference on Image Processing, pages -, Institute of Electrical and Electronics Engineers, Paris, France, 2014. www
- Sequentially Generated Instance-Dependent Image Representations for Classification. In International Conference on Learning Representations, ICLR 2014, Banff, Canada, 2014. www
- Incremental learning of latent structural SVM for weakly supervised image classification. In IEEE International Conference on Image Processing, pages 4246-4250, IEEE, Paris, France, 2014. doi www
2013
Articles de revue
- Extended Coding and Pooling in the HMAX Model. In IEEE Transactions on Image Processing, 22 (2): 764-777, 2013. doi www
- JKernelMachines: A Simple Framework for Kernel Machines. In Journal of Machine Learning Research, 14: 1417-1421, 2013. www
- T-HOG: an Effective Gradient-Based Descriptor for Single Line Text Regions. In Pattern Recognition, 46 (3): 1078-1090, 2013. doi www
- Pooling in Image Representation: the Visual Codeword Point of View. In Computer Vision and Image Understanding, 117 (5): 453-465, 2013. doi www
Articles de conférence
- Extended Bag-of-Words Formalism for Image Classification. In Brazilian Symposium on Computer Graphics and Image Processing, Arequipa, Peru, 2013. www
- Image classification using object detectors. In IEEE International Conference on Image Processing, pages 4340-4344, Melbourne, Australia, 2013. doi www
- Quadruplet-Wise Image Similarity Learning. In IEEE International Conference on Computer Vision (ICCV), pages 249-256, Sydney, Australia, 2013. doi www
- Dynamic Scene Classification: Learning Motion Descriptors with Slow Features Analysis. In IEEE Conference on Computer Vision and Pattern Recognition, pages 2603-2610, IEEE, Portland, OR, United States, 2013. doi www
- Top-Down Regularization of Deep Belief Networks. In Advances in Neural Information Processing Systems 26, pages 1878-1886, Lake Tahoe, United States, 2013. www
2012
Articles de conférence
- Structural and Visual Comparisons for Web Page Archiving. In 12th edition of the ACM Symposium on Document Engineering, DocEng'12, pages 117-120, ACM, Paris, France, 2012. doi www
- Unsupervised and supervised visual codes with restricted Boltzmann machines. In Lecture Notes in Computer Science, pages 298-311, Florence, Italy, Lecture Notes in Computer Science 7576, 2012. doi www
- Structural and Visual Similarity Learning for Web Page Archiving. In 10th workshop on Content-Based Multimedia Indexing (CBMI), pages 1-6, IEEE, Annecy, France, 2012. doi www
- Hybrid Pooling Fusion in the BoW Pipeline. In ECCV 2012 Workshop on Information fusion in Computer Vision for Concept Recognition (ECCV-IFCVCR 2012), pages 355-364, Springer, Florence, Italy, Lecture Notes in Computer Science 7585, 2012. doi www
- Learning geometric combinations of Gaussian kernels with alternating Quasi-Newton algorithm. In ESANN 2012, pages 79-84, Bruges, Belgium, 2012. www
- Contextual Detection of Drawn Symbols in Old Maps. In International Conference on Image Processing (ICIP), pages 837-840, IEEE, Orlando, Florida, United States, 2012. doi www
- Classification of Urban Scenes from Geo-referenced Images in Urban Street-View Context. In Machine Learning and Applications (ICMLA), 2012 11th International Conference on, pages 339-344, Boca Raton, Florida, United States, 2012. www
- Suivi 3D Monoculaire pour un Système de Vidéosurveillance `a l'aide d'un Modèle de Mouvement et un Modèle d'Apparence. In RFIA 2012 (Reconnaissance des Formes et Intelligence Artificielle), Lyon, France, 2012. www
2011
Articles de revue
- A cognitive and video-based approach for multinational License Plate Recognition. In Machine Vision and Applications, 22 (2): 389-407, 2011. doi www
Articles de conférence
- SNOOPERTRACK: TEXT DETECTION AND TRACKING FOR OUTDOOR VIDEOS. In IEEE International Conference on Image Processing (ICIP), pages 505-508, IEEE, Brussels, Belgium, 2011. doi www
- Learning Invariant Color Features with Sparse Topographic Restricted Boltzmann Machines. In ICIP 2011 - IEEE International Conference on Image Processing, pages 1241-1244, Brussels, Belgium, 2011. doi www
- HMAX-S: DEEP SCALE REPRESENTATION FOR BIOLOGICALLY INSPIRED IMAGE CATEGORIZATION. In IEEE International Conference on Image Processing, pages 1261-1264, IEEE, Brussels, Belgium, 2011. doi www
- Text Detection and Recognition in Urban Scenes. In International Conference on Computer Vision (ICCV): Workshop on Computer Vision for Remote Sensing of the Environment, pages 227-234, IEEE, Barcelona, Spain, 2011. doi www
- Efficient bag-of-feature kernel representation for image similarity search. In ICIP 2011 - IEEE International Conference on Image Processing, pages 109-112, IEEE, Bruxelles, Belgium, 2011. doi www
- BOSSA: extended BoW formalism for image classification. In IEEE International Conference on Image Processing (ICIP), pages 2909-2912, IEEE, Brussels, Belgium, 2011. doi www
2010
Articles de conférence
- Biasing Restricted Boltzmann Machines to Manipulate Latent Selectivity and Sparsity. In NIPS 2010 Workshop on Deep Learning and Unsupervised Feature Learning, Vancouver, Canada, 2010. www
- Analyse de l'activité humaine dans les séquences vidéo. In Ecole de Préparation `a la Recherche Appliquée : Vidéosurveillance Industrielle et Sécuritaire, pages inconnue, Ile de Kerkennah, Tunisia, 2010. www
- Fast People Counting using Head Detection from Skeleton Graph. In IEEE International Conference on Advanced Video and Signal based Surveillance (AVSS), pages 233-240, IEEE, Boston, MA, United States, 2010. doi www
- Snoopertext: A multiresolution system for text detection in complex visual scenes. In ICIP 2010 - 17th IEEE International Conference on Image Processing, pages 3861-3864, IEEE, Hong-Kong, Hong Kong SAR China, 2010. doi www
- An efficient System for combining complementary kernels in complex visual categorization tasks. In ICIP 2010 - 17th IEEE International Conference on Image Processing, pages 3877-3880, IEEE, Hong Kong, Hong Kong SAR China, 2010. doi www
2008
Articles de revue
- A Real-Time, Multi-View Fall Detection System: a LHMM-Based Approach. In IEEE Transactions on Circuits and Systems for Video Technology, 18 (11): 1522-1532, 2008. doi www
- Learning Articulated Appearance Models for Tracking Humans: a Spectral Graph Matching Approach. In Signal Processing: Image Communication, 23 (10): 769-787, 2008. doi www
2007
Articles de conférence
- A Combined Statistical-Structural Strategy for Alphanumeric Recognition. In 3rd International Symposium on Visual Computing (ISCV 2007), pages 529-538, Springer, Lake Tahoe, United States, 2007. doi www
Non publié
2006
Articles de conférence
- A HHMM-Based Approach for Robust Fall Detection. In 9th International Conference on Control, Automation, Robotics & Vision, ICARCV'06, pages 1-8, IEEE, Singapore, Singapore, 2006. doi www
- Human Body Part Labeling and Tracking Using Graph Matching Theory. In International Conference on Advanced Video and Signal based Surveillance (IEEE AVSS), pages 38-38, IEEE Computer Society, Sydney, Australia, 2006. www
2005
Articles de conférence
- A Robust Appearance Model for Tracking Human Motions. In AVSS (IEEE International Conference on Advanced Video and Signal-Based Surveillance), pages 528-533, Como, Italy, 2005. www