Recherche - Archive ouverte HAL Accéder directement au contenu

Filtrer vos résultats

100 résultats
Image document

Deep Neural Networks Under Stress

Micael Carvalho , Matthieu Cord , Sandra Avila , Nicolas Thome , Eduardo Valle
IEEE International Conference on Image Processing (ICIP 2016), Sep 2016, Phoenix, AZ, United States. ⟨10.1109/ICIP.2016.7533200⟩
Communication dans un congrès hal-01340298v1
Image document

BLOCK: Bilinear Superdiagonal Fusion for Visual Question Answering and Visual Relationship Detection

Hedi Ben-Younes , Remi Cadene , Nicolas Thome , Matthieu Cord
AAAI 2019 - 33rd AAAI Conference on Artificial Intelligence, Jan 2019, Honolulu, United States
Communication dans un congrès hal-02073644v1

Extended Bag-of-Words Formalism for Image Classification

Sandra Avila , Nicolas Thome , Matthieu Cord , Eduardo Valle , Arnaldo de Albuquerque Araújo
Brazilian Symposium on Computer Graphics and Image Processing, Aug 2013, Arequipa, Peru
Communication dans un congrès hal-01216114v1
Image document

Biasing Restricted Boltzmann Machines to Manipulate Latent Selectivity and Sparsity

Hanlin Goh , Nicolas Thome , Matthieu Cord
NIPS 2010 Workshop on Deep Learning and Unsupervised Feature Learning, Dec 2010, Vancouver, Canada
Communication dans un congrès hal-00716050v1

A Real-Time, Multi-View Fall Detection System: a LHMM-Based Approach

Nicolas Thome , Serge Miguet , Sébastien Ambellouis
IEEE Transactions on Circuits and Systems for Video Technology, 2008, 18 (11), pp.1522-1532. ⟨10.1109/TCSVT.2008.2005606⟩
Article dans une revue hal-01172413v1
Image document

Semantic augmentation by mixing contents for semi-supervised learning

Rémy Sun , Clément Masson , Gilles Hénaff , Nicolas Thome , Matthieu Cord
Pattern Recognition, 2024, 145, pp.109909. ⟨10.1016/j.patcog.2023.109909⟩
Article dans une revue hal-04385089v1
Image document

MERLIN-Seg: self-supervised despeckling for label-efficient semantic segmentation

Emanuele Dalsasso , Clément Rambour , Nicolas Trouvé , Nicolas Thome
Computer Vision and Image Understanding, 2024, 241, ⟨10.1016/j.cviu.2024.103940⟩
Article dans une revue hal-04163624v2

A HHMM-Based Approach for Robust Fall Detection

Nicolas Thome , Serge Miguet
9th International Conference on Control, Automation, Robotics & Vision, ICARCV'06, Dec 2006, Singapore, Singapore. pp.1-8, ⟨10.1109/ICARCV.2006.345146⟩
Communication dans un congrès hal-01613501v1

Confidence Estimation via Auxiliary Models

Charles Corbière , Nicolas Thome , Antoine Saporta , Tuan-Hung Vu , Matthieu Cord , et al.
IEEE Transactions on Pattern Analysis and Machine Intelligence, In press, pp.1-1. ⟨10.1109/TPAMI.2021.3085983⟩
Article dans une revue hal-03252079v1
Image document

Multitask Classification and Segmentation for Cancer Diagnosis in Mammography

Thi-Lam-Thuy Le , Nicolas Thome , Sylvain Bernard , Vincent Bismuth , Fanny Patoureaux
2019
Autre publication scientifique hal-02986361v1
Image document

HybridNet: Classification and Reconstruction Cooperation for Semi-supervised Learning

Thomas Robert , Nicolas Thome , Matthieu Cord
ECCV 2018 - 15th European Conference on Computer Vision, Sep 2018, Munich, Germany. pp.158-175, ⟨10.1007/978-3-030-01234-2_10⟩
Communication dans un congrès hal-02073640v1
Image document

Gaze Latent Support Vector Machine for Image Classification Improved by Weakly Supervised Region Selection

Xin Wang , Nicolas Thome , Matthieu Cord
Pattern Recognition, 2017, 72, pp.59-71. ⟨10.1016/j.patcog.2017.07.001⟩
Article dans une revue hal-01557368v1

A cognitive and video-based approach for multinational License Plate Recognition

Nicolas Thome , Antoine Vacavant , Lionel Robinault , Serge Miguet
Machine Vision and Applications, 2011, 22 (2), pp.389-407. ⟨10.1007/s00138-010-0246-3⟩
Article dans une revue istex hal-01172444v1

Fast People Counting using Head Detection from Skeleton Graph

Djamel Merad , Kheir-Eddine Aziz , Nicolas Thome
IEEE International Conference on Advanced Video and Signal based Surveillance (AVSS), Sep 2010, Boston, MA, United States. pp.233-240, ⟨10.1109/AVSS.2010.77⟩
Communication dans un congrès hal-01292184v1
Image document

HMAX-S: DEEP SCALE REPRESENTATION FOR BIOLOGICALLY INSPIRED IMAGE CATEGORIZATION

Christian Theriault , Nicolas Thome , Matthieu Cord
IEEE International Conference on Image Processing, Sep 2011, Brussels, Belgium. pp.1261-1264, ⟨10.1109/ICIP.2011.6115663⟩
Communication dans un congrès hal-00625532v1
Image document

Image classification using object detectors

Thibaut Durand , Nicolas Thome , Matthieu Cord , Sandra Avila
IEEE International Conference on Image Processing, Sep 2013, Melbourne, Australia. pp.4340 - 4344, ⟨10.1109/ICIP.2013.6738894⟩
Communication dans un congrès hal-01078079v1
Image document

EXEMPLAR BASED METRIC LEARNING FOR ROBUST VISUAL LOCALIZATION

Cédric Le Barz , Nicolas Thome , Matthieu Cord , Stéphane Herbin , Martial Sanfourche
IEEE International Conference on Image Processing, ICIP 2015, Sep 2015, Québec, Canada. pp.388-w6mP-151, 2015
Poster de conférence hal-01198662v1
Image document

Max-min convolutional neural networks for image classification

Michael Blot , Matthieu Cord , Nicolas Thome
ICIP 2016 - IEEE International Conference on Image Processing, Sep 2016, Phoenix, United States. pp.3678-3682, ⟨10.1109/ICIP.2016.7533046⟩
Communication dans un congrès hal-01372216v1

T-HOG: an Effective Gradient-Based Descriptor for Single Line Text Regions

Rodrigo Minetto , Nicolas Thome , Matthieu Cord , Neucimar J. Leite , Jorge Stolfi
Pattern Recognition, 2013, 46 (3), pp.1078-1090. ⟨10.1016/j.patcog.2012.10.009⟩
Article dans une revue hal-01185468v1
Image document

Augmenting physical models with deep networks for complex dynamics forecasting

Yuan Yin , Vincent Le Guen , Jérémie Donà , Emmanuel de Bézenac , Ibrahim Ayed , et al.
Journal of Statistical Mechanics: Theory and Experiment, 2021, 2021 (12), pp.124012. ⟨10.1088/1742-5468/ac3ae5⟩
Article dans une revue hal-03508401v2
Image document

Fantope Regularization in Metric Learning

Marc T Law , Nicolas Thome , Matthieu Cord
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2014, Columbus, Ohio, United States. pp.1051 - 1058, ⟨10.1109/CVPR.2014.138⟩
Communication dans un congrès hal-01094074v1
Image document

Absolute geo-localization thanks to Hidden Markov Model and exemplar-based metric learning

Cédric Le Barz , Nicolas Thome , Matthieu Cord , Stephane Herbin , Martial Sanfourche
6th international Workshop on Computer Vision in Vehicle Technology, Jun 2015, CHICAGO, United States
Communication dans un congrès hal-01198673v1

Apprentissage de métrique appliqué à la détection de changement de page Web et aux attributs relatifs

Marc Teva Law , Nicolas Thome , Stéphane Gançarski , Matthieu Cord
CORIA 2015 - Conférence en Recherche d'Infomations et Applications - 12th French Information Retrieval Conference, Mar 2015, Paris, France
Communication dans un congrès hal-01500746v1

Structural and Visual Similarity Learning for Web Page Archiving

Marc Teva Law , Carlos Sureda Gutierrez , Nicolas Thome , Stéphane Gançarski , Matthieu Cord
10th workshop on Content-Based Multimedia Indexing (CBMI), Jun 2012, Annecy, France. pp.1-6, ⟨10.1109/CBMI.2012.6269849⟩
Communication dans un congrès hal-01271765v1
Image document

RECIPE RECOGNITION WITH LARGE MULTIMODAL FOOD DATASET

Xin Wang , Devinder Kumar , Nicolas Thome , Matthieu Cord , Frederic Precioso
IEEE International Conference on Multimedia & Expo (ICME), workshop CEA, Jun 2015, Turin, Italy. ⟨10.1109/ICMEW.2015.7169757⟩
Communication dans un congrès hal-01196959v1

Leveraging Vision-Language Foundation Models for Fine-Grained Downstream Tasks

Denis Coquenet , Clément Rambour , Emanuele Dalsasso , Nicolas Thome
2023
Pré-publication, Document de travail hal-04162923v1
Image document

Augmenting physical models with deep networks for complex dynamics forecasting

Yuan Yin , Vincent Le Guen , Jérémie Dona , Ibrahim Ayed , Emmanuel de Bézenac , et al.
Ninth International Conference on Learning Representations ICLR 2021, 2021, Vienna (virtual), Austria
Communication dans un congrès hal-03137025v1
Image document

Histoire des réseaux de neurones et du deep learning en traitement des signaux et des images

Nicolas Thome , Christian Wolf
2023
Pré-publication, Document de travail hal-04058482v1
Image document

Beyond First-Order Uncertainty Estimation with Evidential Models for Open-World Recognition

Charles Corbière , Marc Lafon , Nicolas Thome , Matthieu Cord , Patrick Pérez
ICML 2021 Workshop on Uncertainty and Robustness in Deep Learning, Sep 2021, Virtual, Austria
Communication dans un congrès hal-03347628v1
Image document

U-Net Transformer: Self and Cross Attention for Medical Image Segmentation

Olivier Petit , Nicolas Thome , Clement Rambour , Loic Themyr , Toby Collins , et al.
MICCAI workshop MLMI, Sep 2021, Strasbourg (virtuel), France
Communication dans un congrès hal-03337089v1