6 papers
Towards Hierarchical Structure Understanding of Newspaper Images
William Mocaër, Solène Tarride, Thomas Constum +7
Understanding newspaper images remains a challenging task due to their complex, nested hierarchical structures and dense, heterogeneous layouts. In this paper, we explore two compl…
Scaling State-Space Models from Lines to Paragraphs: An Ablation of Mamba-based OCR
Merveilles Agbeti-Messan, Pierrick Tranouez, Stéphane Nicolas +2
End-to-end OCR increasingly relies on autoregressive sequence models, where the quadratic cost of Transformer attention limits efficient transcription of long, paragraph-level text…
A Benchmark of State-Space Models vs. Transformers and BiLSTM-based Models for Historical Newspaper OCR
Merveilles Agbeti-Messan, Pierrick Tranouez, Stéphane Nicolas +2
End-to-end OCR for historical newspapers remains challenging, as models must handle long text sequences, degraded print quality, and complex layouts. While Transformer-based recogn…
Few-shot Writer Adaptation via Multimodal In-Context Learning
Tom Simon, Stephane Nicolas, Pierrick Tranouez +2
While state-of-the-art Handwritten Text Recognition (HTR) models perform well on standard benchmarks, they frequently struggle with writers exhibiting highly specific styles that a…
Pattern Spotting in Historical Documents Using Convolutional Models
Ignacio Úbeda, Jose M. Saavedra, Stéphane Nicolas +2
Pattern spotting consists of searching in a collection of historical document images for occurrences of a graphical object using an image query. Contrary to object detection, no pr…
Logical segmentation for article extraction in digitized old newspapers
Thomas Palfray, David Hébert, Stéphane Nicolas +2
Newspapers are documents made of news item and informative articles. They are not meant to be red iteratively: the reader can pick his items in any order he fancies. Ignoring this…