Denis Coquenet

Denis Coquenet

Post-doctorant
Équipe : Données Complexes, Apprentissage et Représentations
Site web : https://factodeeplearning.github.io/
Bureau : 37.0E.31

2026

Articles de revue

  1. Coquenet, D. Meta-DAN: towards an efficient prediction strategy for page-level handwritten text recognition. In Pattern Recognition, 177: 113373, 2026. doi  www 

Articles de conférence

  1. Meyer, F.; Guichard, L.; Soullard, Y.; Coquenet, D.; Gravier, G. and Co"uasnon, B. N-gram Injection into Transformers for Dynamic Language Model Adaptation in Handwritten Text Recognition. In International Conference on Document Analysis and Recognition (ICDAR) 2026, pages 572-589, Vienna, Austria, 2026. doi  www 
  1. Karaouli, N.; Coquenet, D.; Fromont, E.; Mermillod, M. and Reyboz, M. Foundation vs. Specialized Models: Evaluating Catastrophic Forgetting in Continual Time Series Forecasting. In Proceedings of the 29th International Conference on Discovery Science, Mainz, Germany, 2026. www 

Non publié

  1. Zhang, N.; Coquenet, D.; Soullard, Y. and Co"uasnon, B. Text-MAE: Learning Language through Self-Supervised Visual Reconstruction for Handwritten Text Line Recognition. , working paper or preprint. doi  www 

2025

Articles de conférence

  1. Meyer, F.; Guichard, L.; Coquenet, D.; Gravier, G.; Soullard, Y. and Co"uasnon, B. Relaxed syntax modeling in Transformers for future-proof license plate recognition. In International Conference on Document Analysis and Recognition (ICDAR) 2025, pages 154-171, Wuhan, China, 2025. doi  www 
  1. Karaouli, N.; Coquenet, D.; Fromont, E.; Mermillod, M. and Reyboz, M. How Foundational are Foundation Models for Time Series Forecasting?. In BERT2 S 2025 - NeurIPS Workshop on Recent Advances in Time Series Foundation Models, pages 1-8, San Diego, CA, United States, 2025. www 

Non publié

  1. Karaouli, N.; Coquenet, D.; Fromont, E.; Mermillod, M. and Reyboz, M. Are Time Series Foundation Models Susceptible to Catastrophic Forgetting?. , working paper or preprint. www 

2023

Articles de revue

  1. Coquenet, D.; Chatelain, C. and Paquet, T. End-to-End Handwritten Paragraph Text Recognition Using a Vertical Attention Network. In IEEE Transactions on Pattern Analysis and Machine Intelligence, 45 (1): 508-524, 2023. doi  www 
  1. Coquenet, D.; Chatelain, C. and Paquet, T. DAN : a Segmentation-free Document Attention Network for Handwritten Document Recognition. In IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023. doi  www 

Articles de conférence

  1. Coquenet, D.; Chatelain, C. and Paquet, T. Faster DAN: Multi-target Queries with Document Positional Encoding for End-to-end Handwritten Document Recognition. In International Conference on Document Analysis and Recognition, pages 182-199, Springer Nature Switzerland, San josé, CA,, United States, Lecture Notes in Computer Science 14190, 2023. doi  www 

Non publié

  1. Coquenet, D.; Rambour, C.; Dalsasso, E. and Thome, N. Leveraging Vision-Language Foundation Models for Fine-Grained Downstream Tasks. , working paper or preprint. www 

2022

Thèses et habilitations

  1. Coquenet, D. $T$$o$wards $E$nd-t$o$-end Handwritten Document Recognition. Ph.D. Thesis, Normandie Université, 2022. doi 
  1. Coquenet, D. Towards End-to-end Handwritten Document Recognition. Ph.D. Thesis, Université de Rouen Normandie, 2022.

2021

Articles de conférence

  1. Coquenet, D.; Chatelain, C. and Paquet, T. SPAN: A Simple Predict & Align Network for Handwritten Paragraph Recognition. In ICDAR, pages 70-84, Springer International Publishing, Lausanne, France, Lecture Notes in Computer Science 12823, 2021. doi  www 
  1. Coquenet, D.; Chatelain, C. and Paquet, T. Handwritten text recognition: from isolated text lines to whole documents. In ORASIS 2021, Saint Ferréol, France, 2021. www 

2020

Articles de conférence

  1. Coquenet, D.; Chatelain, C. and Paquet, T. Recurrence-free unconstrained handwritten text recognition using gated fully convolutional network. In 2020 17th International Conference on Frontiers in Handwriting Recognition (ICFHR), pages 19-24, IEEE, Dortmund, Germany, 2020. doi  www 

2019

Articles de conférence

  1. Coquenet, D.; Soullard, Y.; Chatelain, C. and Paquet, T. Have Convolutions Already Made Recurrence Obsolete for Unconstrained Handwritten Text Recognition?. In 2019 International Conference on Document Analysis and Recognition Workshops (ICDARW), pages 65-70, IEEE, Sydney, Australia, 2019. doi  www 
Haut