CV HAL - Denis Coquenet

N-gram Injection into Transformers for Dynamic Language Model Adaptation in Handwritten Text Recognition

Florent Meyer , Laurent Guichard , Yann Soullard , Denis Coquenet , Guillaume Gravier et al.

ICDAR 2026 - International Conference on Document Analysis and Recognition, Aug 2026, Vienna, Austria. pp.572-589, ⟨10.1007/978-3-032-36033-5_34⟩

Communication dans un congrès hal-05537580v1

Foundation vs. Specialized Models: Evaluating Catastrophic Forgetting in Continual Time Series Forecasting

Nouha Karaouli , Denis Coquenet , Elisa Fromont , Martial Mermillod , Marina Reyboz

DS'2026 - 29th International Conference on Discovery Science, Oct 2026, Mainz, Germany

Communication dans un congrès hal-05725331v1

Relaxed syntax modeling in Transformers for future-proof license plate recognition

Florent Meyer , Laurent Guichard , Denis Coquenet , Guillaume Gravier , Yann Soullard et al.

ICDAR 2025 - International Conference on Document Analysis and Recognition, Sep 2025, Wuhan, China. pp.154-171, ⟨10.1007/978-3-032-04627-7_9⟩

Communication dans un congrès hal-05147482v1

How Foundational are Foundation Models for Time Series Forecasting?

Nouha Karaouli , Denis Coquenet , Elisa Fromont , Martial Mermillod , Marina Reyboz

BERT2 S 2025 - NeurIPS Workshop on Recent Advances in Time Series Foundation Models, Dec 2025, San Diego, CA, United States. pp.1-8

Communication dans un congrès hal-05300066v1

Faster DAN: Multi-target Queries with Document Positional Encoding for End-to-end Handwritten Document Recognition

Denis Coquenet , Clément Chatelain , Thierry Paquet

International Conference on Document Analysis and Recognition, 2023, San josé, CA,, United States. pp.182-199, ⟨10.1007/978-3-031-41685-9_12⟩

Communication dans un congrès hal-03957156v1

SPAN: A Simple Predict & Align Network for Handwritten Paragraph Recognition

Denis Coquenet , Clément Chatelain , Thierry Paquet

ICDAR, 2021, Lausanne, France. pp.70-84, ⟨10.1007/978-3-030-86334-0_5⟩

Communication dans un congrès hal-05273562v1

Handwritten text recognition: from isolated text lines to whole documents

Denis Coquenet , Clément Chatelain , Thierry Paquet

ORASIS 2021, Centre National de la Recherche Scientifique [CNRS], Sep 2021, Saint Ferréol, France

Communication dans un congrès hal-03339648v1

Recurrence-free unconstrained handwritten text recognition using gated fully convolutional network

Denis Coquenet , Clément Chatelain , Thierry Paquet

2020 17th International Conference on Frontiers in Handwriting Recognition (ICFHR), Sep 2020, Dortmund, Germany. pp.19-24, ⟨10.1109/ICFHR2020.2020.00015⟩

Communication dans un congrès hal-03073795v1

Have Convolutions Already Made Recurrence Obsolete for Unconstrained Handwritten Text Recognition?

Denis Coquenet , Yann Soullard , Clement Chatelain , Thierry Paquet

2019 International Conference on Document Analysis and Recognition Workshops (ICDARW), Sep 2019, Sydney, Australia. pp.65-70, ⟨10.1109/ICDARW.2019.40083⟩

Communication dans un congrès hal-02420313v1

Meta-DAN: towards an efficient prediction strategy for page-level handwritten text recognition

Denis Coquenet

Pattern Recognition, 2026, 177, pp.113373. ⟨10.1016/j.patcog.2026.113373⟩

Article dans une revue hal-05405085v1

DAN : a Segmentation-free Document Attention Network for Handwritten Document Recognition

Denis Coquenet , Clément Chatelain , Thierry Paquet

IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, ⟨10.1109/tpami.2023.3235826⟩

Article dans une revue hal-03621784v1

End-to-End Handwritten Paragraph Text Recognition Using a Vertical Attention Network

Denis Coquenet , Clément Chatelain , Thierry Paquet

IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45 (1), pp.508-524. ⟨10.1109/TPAMI.2022.3144899⟩

Article dans une revue hal-05273612v1

Text-MAE: Learning Language through Self-Supervised Visual Reconstruction for Handwritten Text Line Recognition

Noé Zhang , Denis Coquenet , Yann Soullard , Bertrand Coüasnon

2026

Pré-publication, Document de travail hal-05732156v1

Are Time Series Foundation Models Susceptible to Catastrophic Forgetting?

Nouha Karaouli , Denis Coquenet , Elisa Fromont , Martial Mermillod , Marina Reyboz

2025

Pré-publication, Document de travail hal-05306471v1

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

Τοwards Εnd-tο-end Handwritten Document Recognition

Denis Coquenet

Computer Vision and Pattern Recognition [cs.CV]. Normandie Université, 2022. English. ⟨NNT : 2022NORMR028⟩

Thèse tel-04199374v1

Towards End-to-end Handwritten Document Recognition

Denis Coquenet

Computer Vision and Pattern Recognition [cs.CV]. Université de Rouen Normandie, 2022. English. ⟨NNT : ⟩

Thèse tel-03789236v1

Denis Coquenet

Publications

Publications

N-gram Injection into Transformers for Dynamic Language Model Adaptation in Handwritten Text Recognition

Foundation vs. Specialized Models: Evaluating Catastrophic Forgetting in Continual Time Series Forecasting

Relaxed syntax modeling in Transformers for future-proof license plate recognition

How Foundational are Foundation Models for Time Series Forecasting?

Faster DAN: Multi-target Queries with Document Positional Encoding for End-to-end Handwritten Document Recognition

SPAN: A Simple Predict & Align Network for Handwritten Paragraph Recognition

Handwritten text recognition: from isolated text lines to whole documents

Recurrence-free unconstrained handwritten text recognition using gated fully convolutional network

Have Convolutions Already Made Recurrence Obsolete for Unconstrained Handwritten Text Recognition?

Meta-DAN: towards an efficient prediction strategy for page-level handwritten text recognition

DAN : a Segmentation-free Document Attention Network for Handwritten Document Recognition

End-to-End Handwritten Paragraph Text Recognition Using a Vertical Attention Network

Text-MAE: Learning Language through Self-Supervised Visual Reconstruction for Handwritten Text Line Recognition

Are Time Series Foundation Models Susceptible to Catastrophic Forgetting?

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

Τοwards Εnd-tο-end Handwritten Document Recognition

Towards End-to-end Handwritten Document Recognition

Denis Coquenet

Publications

Publications

N-gram Injection into Transformers for Dynamic Language Model Adaptation in Handwritten Text Recognition

Foundation vs. Specialized Models: Evaluating Catastrophic Forgetting in Continual Time Series Forecasting

Relaxed syntax modeling in Transformers for future-proof license plate recognition

How Foundational are Foundation Models for Time Series Forecasting?

Faster DAN: Multi-target Queries with Document Positional Encoding for End-to-end Handwritten Document Recognition

SPAN: A Simple Predict &amp; Align Network for Handwritten Paragraph Recognition

Handwritten text recognition: from isolated text lines to whole documents

Recurrence-free unconstrained handwritten text recognition using gated fully convolutional network

Have Convolutions Already Made Recurrence Obsolete for Unconstrained Handwritten Text Recognition?

Meta-DAN: towards an efficient prediction strategy for page-level handwritten text recognition

DAN : a Segmentation-free Document Attention Network for Handwritten Document Recognition

End-to-End Handwritten Paragraph Text Recognition Using a Vertical Attention Network

Text-MAE: Learning Language through Self-Supervised Visual Reconstruction for Handwritten Text Line Recognition

Are Time Series Foundation Models Susceptible to Catastrophic Forgetting?

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

Τοwards Εnd-tο-end Handwritten Document Recognition

Towards End-to-end Handwritten Document Recognition

SPAN: A Simple Predict & Align Network for Handwritten Paragraph Recognition