Bertrand Coüasnon
YOU?
Author Swipe
View article: Relaxed Syntax Modeling in Transformers for Future-Proof License Plate Recognition
Relaxed Syntax Modeling in Transformers for Future-Proof License Plate Recognition Open
View article: Proceedings of the 6th International Workshop on Reading Music Systems
Proceedings of the 6th International Workshop on Reading Music Systems Open
The International Workshop on Reading Music Systems (WoRMS) is a workshop that tries to connect researchers who develop systems for reading music, such as in the field of Optical Music Recognition, with other researchers and practitioners …
View article: Training transformer architectures on few annotated data: an application to historical handwritten text recognition
Training transformer architectures on few annotated data: an application to historical handwritten text recognition Open
View article: Full-page music symbols recognition: state-of-the-art deep models comparison for handwritten and printed music scores
Full-page music symbols recognition: state-of-the-art deep models comparison for handwritten and printed music scores Open
View article: StyleGAN-based heatmap generator for face alignment with limited training data
StyleGAN-based heatmap generator for face alignment with limited training data Open
While the performance of face alignment models has been improving over the years, they still need large, annotated datasets during their training to perform well. In this paper, we propose a new architecture to perform face alignment with …
View article: Knowledge Integration Inside Multitask Network for Analysis of Unseen ID Types
Knowledge Integration Inside Multitask Network for Analysis of Unseen ID Types Open
View article: Architecture Transformer Légère pour la Reconnaissance de Textes Anciens
Architecture Transformer Légère pour la Reconnaissance de Textes Anciens Open
View article: Exploring StyleGAN Latent Space for Face Alignment with Limited Training Data
Exploring StyleGAN Latent Space for Face Alignment with Limited Training Data Open
View article: A Light Transformer-Based Architecture for Handwritten Text Recognition
A Light Transformer-Based Architecture for Handwritten Text Recognition Open
International audience
View article: A comparative study of information extraction strategies using an attention-based neural network
A comparative study of information extraction strategies using an attention-based neural network Open
International audience
View article: Document Analysis Systems
Document Analysis Systems Open
View article: SCAF: Skip-Connections in Auto-encoder for Face Alignment with Few Annotated Data
SCAF: Skip-Connections in Auto-encoder for Face Alignment with Few Annotated Data Open
View article: Data extraction and matching The EurHisFirm experience
Data extraction and matching The EurHisFirm experience Open
International audience
View article: Transformers for Historical Handwritten Text Recognition
Transformers for Historical Handwritten Text Recognition Open
The document describes ongoing works and is published as part of 16th International Conference on Document Analysis and Recognition (ICDAR 2021) Doctoral Consortium. The full document is available here : https://icdar2021.org/wp-content/up…
View article: EURHISFIRM M7.2: Final version of the data extraction system
EURHISFIRM M7.2: Final version of the data extraction system Open
Final version of the data extraction system.
View article: Exploitation de Big Data Historiques pour les Humanités Numériques : application aux données financières HBDEX
Exploitation de Big Data Historiques pour les Humanités Numériques : application aux données financières HBDEX Open
International audience
View article: EurHisFirm M7.1: First version of the data extraction system
EurHisFirm M7.1: First version of the data extraction system Open
Work Package 7 develops an intelligent and collaborative system for the extraction of structured information from images of historical documents related to companies’ financial and economic activities. The system focuses on printed serial …
View article: Signature detection as a way to recognise historical parish register structure
Signature detection as a way to recognise historical parish register structure Open
International audience
View article: Combination of deep learning and syntactical approaches for the interpretation of interactions between text-lines and tabular structures in handwritten documents
Combination of deep learning and syntactical approaches for the interpretation of interactions between text-lines and tabular structures in handwritten documents Open
International audience
View article: CNN-Based Accidental Detection in Dense Printed Piano Scores
CNN-Based Accidental Detection in Dense Printed Piano Scores Open
International audience
View article: Big-data historique : modélisation de stratégies d'analyse de collections de document
Big-data historique : modélisation de stratégies d'analyse de collections de document Open
International audience
View article: Music Symbol Detection with Faster R-CNN Using Synthetic Annotations
Music Symbol Detection with Faster R-CNN Using Synthetic Annotations Open
International audience
View article: A combined strategy of analysis for the localization of heterogeneous form fields in ancient pre-printed records
A combined strategy of analysis for the localization of heterogeneous form fields in ancient pre-printed records Open
View article: Handwritten Music Object Detection: Open Issues and Baseline Results
Handwritten Music Object Detection: Open Issues and Baseline Results Open
International audience
View article: DMOS, It's your turn !
DMOS, It's your turn ! Open
International audience
View article: HBA 1.0
HBA 1.0 Open
International audience
View article: Bootstrapping Samples of Accidentals in Dense Piano Scores for CNN-Based Detection
Bootstrapping Samples of Accidentals in Dense Piano Scores for CNN-Based Detection Open
International audience
View article: DMOS : A vous de jouer !
DMOS : A vous de jouer ! Open
Depuis plus de 20 ans, l'equipe Intuidoc a developpe un systeme complet de reconnaissance de documents : la methode DMOS (Description et MOdification de la Segmentation). Cette methode est basee sur trois niveaux :
(1) des indices visuel…
View article: Eyes Wide Open: an interactive learning method for the design of rule-based systems
Eyes Wide Open: an interactive learning method for the design of rule-based systems Open
View article: Inférence semi-automatique et interactive de règles sans vérité terrain.
Inférence semi-automatique et interactive de règles sans vérité terrain. Open
RÉSUMÉ. La conception de systèmes de reconnaissance de documents à partir de documents non annotés est particulièrement difficile. En général, les méthodes statistiques ne peuvent apprendre sans une vérité terrain annotée, contrairement au…