Distributed machine learning for wireless communication networks: Techniques, architectures, and applications

S Hu, X Chen, W Ni, E Hossain… - … Surveys & Tutorials, 2021 - ieeexplore.ieee.org
Distributed machine learning (DML) techniques, such as federated learning, partitioned
learning, and distributed reinforcement learning, have been increasingly applied to wireless …

[HTML][HTML] Transformer-based approach for joint handwriting and named entity recognition in historical document

AC Rouhou, M Dhiaf, Y Kessentini, SB Salem - Pattern Recognition Letters, 2022 - Elsevier
The extraction of relevant information carried out by named entities in handwriting
documents is still a challenging task. Unlike traditional information extraction approaches …

[HTML][HTML] Few shots are all you need: a progressive learning approach for low resource handwritten text recognition

MA Souibgui, A Fornés, Y Kessentini… - Pattern Recognition …, 2022 - Elsevier
Handwritten text recognition in low resource scenarios, such as manuscripts with rare
alphabets, is a challenging problem. In this paper, we propose a few-shot learning-based …

Domain and writer adaptation of offline Arabic handwriting recognition using deep neural networks

SK Jemni, S Ammar, Y Kessentini - Neural Computing and Applications, 2022 - Springer
Abstract Arabic Handwritten Text Recognition (AHTR) based on deep learning approaches
remains a challenging problem due to the inevitable domain shift like the variability among …

One-shot compositional data generation for low resource handwritten text recognition

MA Souibgui, AF Biten, S Dey… - Proceedings of the …, 2022 - openaccess.thecvf.com
Abstract Low resource Handwritten Text Recognition (HTR) is a hard problem due to the
scarce annotated data and the very limited linguistic information (dictionaries and language …

A few shot multi-representation approach for n-gram spotting in historical manuscripts

G De Gregorio, S Biswas, MA Souibgui… - … Conference on Frontiers …, 2022 - Springer
Despite recent advances in automatic text recognition, the performance remains moderate
when it comes to historical manuscripts. This is mainly because of the scarcity of available …

The learnable typewriter: a generative approach to text analysis

I Siglidis, N Gonthier, J Gaubil, T Monnier… - … Conference on Document …, 2024 - Springer
We present a generative document-specific approach to character analysis and recognition
in text lines. Our main idea is to build on unsupervised multi-object segmentation methods …

A User Perspective on HTR Methods for the Automatic Transcription of Rare Scripts: The Case of Codex Runicus

MA Souibgui, A Bensalah, J Chen, A Fornés… - ACM Journal on …, 2023 - dl.acm.org
Recent breakthroughs in Artificial Intelligence, Deep Learning, and Document Image
Analysis and Recognition have significantly eased the creation of digital libraries and the …

Classification of incunable glyphs and out-of-distribution detection with joint energy-based models

F Kordon, N Weichselbaumer, R Herz… - International Journal on …, 2023 - Springer
Optical character recognition (OCR) has proved a powerful tool for the digital analysis of
printed historical documents. However, its ability to localize and identify individual glyphs is …

Few-Shot Learning for Word Recognition in Handwritten Seventeenth-Century Spanish American Notary Records

N Alrasheed, S Sarker, V Grieco, P Rao - Proceedings of the 5th ACM …, 2023 - dl.acm.org
Historical records are invaluable sources of information that provide insights into multiple
aspects of past events and societies. The analysis of historical records using deep learning …