Search

Your search keyword '"Soullard, Yann"' showing total 36 results
Start Over Author "Soullard, Yann"

Refine your results

more »

more »

more »

more »
36 results on '"Soullard, Yann"'

2. Domain Adaptation for Handwriting Trajectory Reconstruction from IMU Sensors

Author

Imbert, Florent, Tavenard, Romain, Soullard, Yann, Anquetil, Eric, Goos, Gerhard, Series Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Mouchère, Harold, editor, and Zhu, Anna, editor

Published
2024
Full Text
View/download PDF

3. Full-Page Music Symbols Recognition: State-of-the-Art Deep Model Comparison for Handwritten and Printed Music Scores

Author

Yesilkanat, Ali, Soullard, Yann, Coüasnon, Bertrand, Girard, Nathalie, Goos, Gerhard, Series Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Sfikas, Giorgos, editor, and Retsinas, George, editor

Published
2024
Full Text
View/download PDF

4. Have convolutions already made recurrence obsolete for unconstrained handwritten text recognition ?

Author

Coquenet, Denis, Soullard, Yann, Chatelain, Clément, and Paquet, Thierry

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Unconstrained handwritten text recognition remains an important challenge for deep neural networks. These last years, recurrent networks and more specifically Long Short-Term Memory networks have achieved state-of-the-art performance in this field. Nevertheless, they are made of a large number of trainable parameters and training recurrent neural networks does not support parallelism. This has a direct influence on the training time of such architectures, with also a direct consequence on the time required to explore various architectures. Recently, recurrence-free architectures such as Fully Convolutional Networks with gated mechanisms have been proposed as one possible alternative achieving competitive results. In this paper, we explore convolutional architectures and compare them to a CNN+BLSTM baseline. We propose an experimental study regarding different architectures on an offline handwriting recognition task using the RIMES dataset, and a modified version of it that consists of augmenting the images with notebook backgrounds that are printed grids.

Published
2020
Full Text
View/download PDF

5. Knowledge Integration Inside Multitask Network for Analysis of Unseen ID Types

Author

Neitthoffer, Timothée, Lemaitre, Aurélie, Coüasnon, Bertrand, Soullard, Yann, Awal, Ahmad Montaser, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Coustaty, Mickael, editor, and Fornés, Alicia, editor

Published
2023
Full Text
View/download PDF

7. Time Series Alignment with Global Invariances

Author

Vayer, Titouan, Tavenard, Romain, Chapel, Laetitia, Courty, Nicolas, Flamary, Rémi, and Soullard, Yann

Subjects
Statistics - Machine Learning, Computer Science - Machine Learning
Abstract

Multivariate time series are ubiquitous objects in signal processing. Measuring a distance or similarity between two such objects is of prime interest in a variety of applications, including machine learning, but can be very difficult as soon as the temporal dynamics and the representation of the time series, {\em i.e.} the nature of the observed quantities, differ from one another. In this work, we propose a novel distance accounting both feature space and temporal variabilities by learning a latent global transformation of the feature space together with a temporal alignment, cast as a joint optimization problem. The versatility of our framework allows for several variants depending on the invariance class at stake. Among other contributions, we define a differentiable loss for time series and present two algorithms for the computation of time series barycenters under this new geometry. We illustrate the interest of our approach on both simulated and real world data and show the robustness of our approach compared to state-of-the-art methods., Comment: Published in Transactions on Machine Learning (Oct 2022)

Published
2020

8. CTCModel: a Keras Model for Connectionist Temporal Classification

Author

Soullard, Yann, Ruffino, Cyprien, and Paquet, Thierry

Subjects
Computer Science - Machine Learning, Statistics - Machine Learning
Abstract

We report an extension of a Keras Model, called CTCModel, to perform the Connectionist Temporal Classification (CTC) in a transparent way. Combined with Recurrent Neural Networks, the Connectionist Temporal Classification is the reference method for dealing with unsegmented input sequences, i.e. with data that are a couple of observation and label sequences where each label is related to a subset of observation frames. CTCModel makes use of the CTC implementation in the Tensorflow backend for training and predicting sequences of labels using Keras. It consists of three branches made of Keras models: one for training, computing the CTC loss function; one for predicting, providing sequences of labels; and one for evaluating that returns standard metrics for analyzing sequences of predictions.

Published
2019

10. A Light Transformer-Based Architecture for Handwritten Text Recognition

Author

Barrere, Killian, Soullard, Yann, Lemaitre, Aurélie, Coüasnon, Bertrand, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Uchida, Seiichi, editor, Barney, Elisa, editor, and Eglin, Véronique, editor

Published
2022
Full Text
View/download PDF

11. A Unified Multilingual Handwriting Recognition System using multigrams sub-lexical units

Author

Swaileh, Wassim, Soullard, Yann, and Paquet, Thierry

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

We address the design of a unified multilingual system for handwriting recognition. Most of multi- lingual systems rests on specialized models that are trained on a single language and one of them is selected at test time. While some recognition systems are based on a unified optical model, dealing with a unified language model remains a major issue, as traditional language models are generally trained on corpora composed of large word lexicons per language. Here, we bring a solution by con- sidering language models based on sub-lexical units, called multigrams. Dealing with multigrams strongly reduces the lexicon size and thus decreases the language model complexity. This makes pos- sible the design of an end-to-end unified multilingual recognition system where both a single optical model and a single language model are trained on all the languages. We discuss the impact of the language unification on each model and show that our system reaches state-of-the-art methods perfor- mance with a strong reduction of the complexity., Comment: preprint

Published
2018
Full Text
View/download PDF

14. Co-training with Credal Models

Author

Soullard, Yann, Destercke, Sébastien, Thouvenin, Indira, Hutchison, David, Series editor, Kanade, Takeo, Series editor, Kittler, Josef, Series editor, Kleinberg, Jon M., Series editor, Mattern, Friedemann, Series editor, Mitchell, John C., Series editor, Naor, Moni, Series editor, Pandu Rangan, C., Series editor, Steffen, Bernhard, Series editor, Terzopoulos, Demetri, Series editor, Tygar, Doug, Series editor, Weikum, Gerhard, Series editor, Schwenker, Friedhelm, editor, Abbas, Hazem M., editor, El Gayar, Neamat, editor, and Trentin, Edmondo, editor

Published
2016
Full Text
View/download PDF

15. Domain adaptation for pen trajectory reconstruction from kinematic sensors

Author

Imbert, Florent, Soullard, Yann, Tavenard, Romain, Anquetil, Eric, Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), Université de Rennes (UR), Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA), Intuitive user-interaction for document (INTUIDOC), SIGNAL, IMAGE ET LANGAGE (IRISA-D6), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes 2 (UR2), Littoral, Environnement, Télédétection, Géomatique UMR 6554 (LETG), Université de Brest (UBO)-Université de Rennes 2 (UR2)-Centre National de la Recherche Scientifique (CNRS)-Institut de Géographie et d'Aménagement Régional de l'Université de Nantes (Nantes Univ - IGARUN), Nantes Université - pôle Humanités, Nantes Université (Nantes Univ)-Nantes Université (Nantes Univ)-Nantes Université - pôle Humanités, Nantes Université (Nantes Univ)-Nantes Université (Nantes Univ), and Observation de l’environnement par imagerie complexe (OBELIX)

Subjects
[INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], [INFO]Computer Science [cs], Inertial Measurement Units, Digital Pen, [INFO.INFO-NE]Computer Science [cs]/Neural and Evolutionary Computing [cs.NE], Online Handwriting, Domain Adaptation, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]
Abstract

International audience; Handwriting with connected pen becomes one of the major human-computer easy interaction methods. In comparison with traditional touch screen handwriting systems, the pen-based interaction method has the advantage of producing the online handwriting signal without surface constraints. Indeed, people who write on a paper obtain the corresponding pen trajectory coordinates that represent the online handwriting signal. Furthermore, the feeling of writing on paper is important particularly for the children during the learning of writing. In this work which is part of ANR Franco-German KIHT project with Stabilo, we introduce a domain adaptation-based approach that reconstructs the paper handwriting traces of the digital stylus Digipen of STABILO which is equipped with a wireless trajectory tracking system based on kinematic sensors. We use unsupervised domain adaptation method, to pass from the tablet domain where the ground truth (the online trace of the writing on the tablet) is known, to the paper domain where only the input sensors data are known.

Published
2023

16. Entraînement d'architectures type Transformer sur peu de données : application à la reconnaissance de texte manuscrit ancien

Author

Barrere, Killian, Soullard, Yann, Lemaitre, Aurélie, Coüasnon, Bertrand, Université de Rennes (UR), Intuitive user-interaction for document (INTUIDOC), SIGNAL, IMAGE ET LANGAGE (IRISA-D6), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), Camille Kurtz, Florence Cloppet, and Nicole Vincent

Subjects
[INFO.INFO-TT]Computer Science [cs]/Document and Text Processing, [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR], [INFO.INFO-NE]Computer Science [cs]/Neural and Evolutionary Computing [cs.NE]
Abstract

National audience

Published
2023

18. Handwritting Recognition using Multi-Hypothesis based Semi-Supervised Learning for adaptation to specific documents

Author

Chapin, Alexandre, Soullard, Yann, Lemaitre, Aurélie, Coüasnon, Bertrand, Intuitive user-interaction for document (INTUIDOC), SIGNAL, IMAGE ET LANGAGE (IRISA-D6), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), Littoral, Environnement, Télédétection, Géomatique (LETG - Rennes ), Université de Brest (UBO)-Université de Rennes 2 (UR2)-Nantes Université (Nantes Univ)-Littoral, Environnement, Télédétection, Géomatique UMR 6554 (LETG), Université de Brest (UBO)-Université de Rennes 2 (UR2)-Centre National de la Recherche Scientifique (CNRS)-Institut de Géographie et d'Aménagement Régional de l'Université de Nantes (Nantes Univ - IGARUN), Nantes Université - pôle Humanités, Nantes Université (Nantes Univ)-Nantes Université (Nantes Univ)-Nantes Université - pôle Humanités, Nantes Université (Nantes Univ)-Nantes Université (Nantes Univ)-Centre National de la Recherche Scientifique (CNRS)-Institut de Géographie et d'Aménagement Régional de l'Université de Nantes (Nantes Univ - IGARUN), Nantes Université (Nantes Univ), and Soullard, Yann

Subjects
[INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI], [INFO.INFO-TT]Computer Science [cs]/Document and Text Processing, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], [INFO.INFO-NE] Computer Science [cs]/Neural and Evolutionary Computing [cs.NE], [INFO.INFO-TT] Computer Science [cs]/Document and Text Processing, [INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG], [INFO.INFO-NE]Computer Science [cs]/Neural and Evolutionary Computing [cs.NE], [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]
Abstract

International audience

Published
2022

19. Iterative Refinement of HMM and HCRF for Sequence Classification

Author

Soullard, Yann, Artieres, Thierry, Hutchison, David, Series editor, Kanade, Takeo, Series editor, Kittler, Josef, Series editor, Kleinberg, Jon M., Series editor, Mattern, Friedemann, Series editor, Mitchell, John C., Series editor, Naor, Moni, Series editor, Nierstrasz, Oscar, Series editor, Pandu Rangan, C., Series editor, Steffen, Bernhard, Series editor, Sudan, Madhu, Series editor, Terzopoulos, Demetri, Series editor, Tygar, Doug, Series editor, Vardi, Moshe Y., Series editor, Weikum, Gerhard, Series editor, Goebel, Randy, editor, Siekmann, Jörg, editor, Wahlster, Wolfgang, editor, Schwenker, Friedhelm, editor, and Trentin, Edmondo, editor

Published
2012
Full Text
View/download PDF

20. Toward Deep neural network for pen trajectory reconstruction from kinematic sensors

Author

Imbert, Florent, Anquetil, Eric, Tavenard, Romain, Soullard, Yann, Swaileh, Wassim, Intuitive user-interaction for document (INTUIDOC), SIGNAL, IMAGE ET LANGAGE (IRISA-D6), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), Littoral, Environnement, Télédétection, Géomatique (LETG - Rennes ), Université de Brest (UBO)-Université de Rennes 2 (UR2)-Nantes Université (Nantes Univ)-Littoral, Environnement, Télédétection, Géomatique UMR 6554 (LETG), Université de Brest (UBO)-Université de Rennes 2 (UR2)-Centre National de la Recherche Scientifique (CNRS)-Institut de Géographie et d'Aménagement Régional de l'Université de Nantes (Nantes Univ - IGARUN), Nantes Université - pôle Humanités, Nantes Université (Nantes Univ)-Nantes Université (Nantes Univ)-Nantes Université - pôle Humanités, Nantes Université (Nantes Univ)-Nantes Université (Nantes Univ)-Centre National de la Recherche Scientifique (CNRS)-Institut de Géographie et d'Aménagement Régional de l'Université de Nantes (Nantes Univ - IGARUN), and Nantes Université (Nantes Univ)

Subjects
[INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], [INFO.INFO-NE]Computer Science [cs]/Neural and Evolutionary Computing [cs.NE], [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]
Abstract

International audience

Published
2022

21. Architecture Transformer Légère pour la Reconnaissance de Textes Anciens

Author

Barrere, Killian, Coüasnon, Bertrand, Lemaitre, Aurélie, Soullard, Yann, Université de Rennes (UR), Intuitive user-interaction for document (INTUIDOC), SIGNAL, IMAGE ET LANGAGE (IRISA-D6), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), and Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)

Subjects
[INFO.INFO-TT]Computer Science [cs]/Document and Text Processing, [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR], [INFO.INFO-NE]Computer Science [cs]/Neural and Evolutionary Computing [cs.NE]
Abstract

International audience

Published
2022

24. Architecture Légère de Transformer pour la Reconnaissance d' Écriture Manuscrite

Author

Barrere, Killian, Soullard, Yann, Lemaitre, Aurélie, Coüasnon, Bertrand, Université de Rennes (UR), Intuitive user-interaction for document (INTUIDOC), SIGNAL, IMAGE ET LANGAGE (IRISA-D6), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), and Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)

Subjects
[INFO.INFO-TT]Computer Science [cs]/Document and Text Processing, [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR], [INFO.INFO-NE]Computer Science [cs]/Neural and Evolutionary Computing [cs.NE]
Abstract

International audience

Published
2021

25. Transformers for Historical Handwritten Text Recognition

Author

Barrere, Killian, Soullard, Yann, Lemaitre, Aurélie, Coüasnon, Bertrand, Université de Rennes (UNIV-RENNES), Intuitive user-interaction for document (INTUIDOC), MEDIA ET INTERACTIONS (IRISA-D6), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-CentraleSupélec-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), Nibal Nayef and Jean-Christophe Burie, Université de Rennes (UR), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), and Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes)

Subjects
ComputingMethodologies_PATTERNRECOGNITION, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], [INFO.INFO-IR]Computer Science [cs]/Information Retrieval [cs.IR], ComputingMethodologies_DOCUMENTANDTEXTPROCESSING, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]
Abstract

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/uploads/ICDAR_DC_FinalBooklet_Sept2021.pdf; International audience; Handwritten documents are recently getting more and more publicly available, but searching efficiently information through them is difficult. Handwritten Text Recognition systems automatically transcribe documents and offer excellent solutions to make the content of handwritten documents available. Neural networks are currently the state-of-the-art approaches for this task. Recently, Transformer architectures have gained in popularity in many fields. We present the works we have done so far toward an efficient architecture using transformer layers for the field of Handwritten Text Recognition. Architectures using Transformer for Handwritten Text Recognition are presented. Our architectures aim to replace recurrent layers with transformers, while combining optical recognition and language modeling in end-to-end model. We manage to obtain state-of-the-art results on the IAM dataset with one of our architecture.

Published
2021

30. CalliSmart: an Adaptive Informed Environment for Intelligent Calligraphy Training

Author

Frenoy, Rémy, Thouvenin, Indira, Soullard, Yann, Gapenne, Olivier, Heuristique et Diagnostic des Systèmes Complexes [Compiègne] (Heudiasyc), Université de Technologie de Compiègne (UTC)-Centre National de la Recherche Scientifique (CNRS), Biomécanique et Bioingénierie (BMBI), Région Picardie, and Frenoy, Rémy

Subjects
[INFO.EIAH] Computer Science [cs]/Technology for Human Learning, Adaptive Systems, Gesture Recognition, [INFO.EIAH]Computer Science [cs]/Technology for Human Learning, [INFO.INFO-MO] Computer Science [cs]/Modeling and Simulation, [INFO.INFO-HC]Computer Science [cs]/Human-Computer Interaction [cs.HC], [INFO.INFO-HC] Computer Science [cs]/Human-Computer Interaction [cs.HC], Interactive systems, [INFO.INFO-MO]Computer Science [cs]/Modeling and Simulation, Training Systems
Abstract

International audience; Gesture learning is a complex and multistep process where trainees are supposed to improve several psychomotor and cognitive skills. According to numerous studies, trainees need to be provided with various types of feedback to improve these skills. These studies also highlight that benefits of a given type of feedback depend on trainees situation. Therefore, feedback must be chosen according to an analysis of trainees activity. Sensorimotor approaches have investigated the impact of feedback on specific learning situations, but the analysis of gestural activity, which would allow the automatic selection of an appropriate type of feedback, is still a recurring issue. In this paper, we propose a new model for gestural training systems based on smart interaction. This model relies on a recognition module based on Naive Bayes classifiers, representing trainees activity by a vector describing their errors, and representing training environments by vectors describing their set of implemented types of feedback. We present a platform for calligraphy training we designed and developed based on our model. Through a user study, we emphasize the benefits of our approach on trainees development.

Published
2016

36. Hybrid HMM and HCRF model for sequence classification

Author

Soullard, Yann, Artières, Thierry, Machine Learning and Information Retrieval (MALIRE), Laboratoire d'Informatique de Paris 6 (LIP6), Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS)-Université Pierre et Marie Curie - Paris 6 (UPMC)-Centre National de la Recherche Scientifique (CNRS), and Publications, Lip6

Subjects
ComputingMethodologies_PATTERNRECOGNITION, [INFO]Computer Science [cs], [INFO] Computer Science [cs]
Abstract

International audience; We propose a hybrid model combining a generative model and a discriminative model for signal labelling and classification tasks, aiming at taking the best from each world. The idea is to focus the learning of the discriminative model on most likely state sequences as output by the generative model. This allows taking advantage of the usual increased accuracy of generative models on small training datasets and of discriminative models on large training datasets. We instantiate this framework with Hidden Markov Models and Hidden Conditional Random Fields. We validate our model on financial time series and on handwriting data.

Published
2011

Catalog

Books, media, physical & digital resources
See catalog results