Denis Coquenet
Post-doctorant
Personal website: https://factodeeplearning.github.io/
Office: 37.0E.31
2023
Articles de revue
- DAN : a Segmentation-free Document Attention Network for Handwritten Document Recognition. In IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023. doi www
Chapitres d'ouvrage
- Faster DAN: Multi-target Queries with Document Positional Encoding for End-to-end Handwritten Document Recognition. In Document Analysis and Recognition - ICDAR 2023, pages 182-199, Springer Nature Switzerland, Lecture Notes in Computer Science 14190, 2023. doi www
Non publié
- Leveraging Vision-Language Foundation Models for Fine-Grained Downstream Tasks. , working paper or preprint. www
2022
Articles de revue
- End-to-end Handwritten Paragraph Text Recognition Using a Vertical Attention Network. In IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022. doi www
Thèses et habilitations
- Towards End-to-end Handwritten Document Recognition. Ph.D. Thesis, Université de Rouen Normandie, 2022.
2021
Chapitres d'ouvrage
- SPAN: A Simple Predict & Align Network for Handwritten Paragraph Recognition. In International Conference on Document Analysis and Recognition, pages 70-84, 2021. doi www
Articles de conférence
- Handwritten text recognition: from isolated text lines to whole documents. In ORASIS 2021, Saint Ferréol, France, 2021. www
2020
Articles de conférence
- 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
- 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