Zobrazeno 1 - 10
of 1 008
pro vyhledávání: '"Kessentini A"'
Document analysis and understanding models often require extensive annotated data to be trained. However, various document-related tasks extend beyond mere text transcription, requiring both textual content and precise bounding-box annotations to ide
Externí odkaz:
http://arxiv.org/abs/2311.11856
The Transformer has quickly become the dominant architecture for various pattern recognition tasks due to its capacity for long-range representation. However, transformers are data-hungry models and need large datasets for training. In Handwritten Te
Externí odkaz:
http://arxiv.org/abs/2303.13931
CSSL-MHTR: Continual Self-Supervised Learning for Scalable Multi-script Handwritten Text Recognition
Autor:
Dhiaf, Marwa, Souibgui, Mohamed Ali, Wang, Kai, Liu, Yuyang, Kessentini, Yousri, Fornés, Alicia, Rouhou, Ahmed Cheikh
Self-supervised learning has recently emerged as a strong alternative in document analysis. These approaches are now capable of learning high-quality image representations and overcoming the limitations of supervised methods, which require a large am
Externí odkaz:
http://arxiv.org/abs/2303.09347
Autor:
Jemni, Sana Khamekhem, Ammar, Sourour, Souibgui, Mohamed Ali, Kessentini, Yousri, Cheddad, Abbas
Keyword spotting (KWS) in historical documents is an important tool for the initial exploration of digitized collections. Nowadays, the most efficient KWS methods are relying on machine learning techniques that require a large amount of annotated tra
Externí odkaz:
http://arxiv.org/abs/2303.03127
Autor:
Boudhiaf, Ridha, Kessentini, Sameh, Abdelgaied, Mohamed, El Hadi Attia, Mohammed, Harby, K., Driss, Zied
Publikováno v:
In Desalination and Water Treatment January 2025 321
Autor:
Souibgui, Mohamed Ali, Biswas, Sanket, Mafla, Andres, Biten, Ali Furkan, Fornés, Alicia, Kessentini, Yousri, Lladós, Josep, Gomez, Lluis, Karatzas, Dimosthenis
In this paper, we propose a Text-Degradation Invariant Auto Encoder (Text-DIAE), a self-supervised model designed to tackle two tasks, text recognition (handwritten or scene-text) and document image enhancement. We start by employing a transformer-ba
Externí odkaz:
http://arxiv.org/abs/2203.04814
Autor:
Ivers, James, Nord, Robert L., Ozkaya, Ipek, Seifried, Chris, Timperley, Christopher S., Kessentini, Marouane
Software refactoring plays an important role in software engineering. Developers often turn to refactoring when they want to restructure software to improve its quality without changing its external behavior. Studies show that small-scale (floss) ref
Externí odkaz:
http://arxiv.org/abs/2202.00173
Autor:
Souibgui, Mohamed Ali, Biswas, Sanket, Jemni, Sana Khamekhem, Kessentini, Yousri, Fornés, Alicia, Lladós, Josep, Pal, Umapada
Document images can be affected by many degradation scenarios, which cause recognition and processing difficulties. In this age of digitization, it is important to denoise them for proper usage. To address this challenge, we present a new encoder-dec
Externí odkaz:
http://arxiv.org/abs/2201.10252
Publikováno v:
Pattern Recognition Letters, 2022
The extraction of relevant information carried out by named entities in handwriting documents is still a challenging task. Unlike traditional information extraction approaches that usually face text transcription and named entity recognition as separ
Externí odkaz:
http://arxiv.org/abs/2112.04189
Handwritten text recognition in low resource scenarios, such as manuscripts with rare alphabets, is a challenging problem. The main difficulty comes from the very few annotated data and the limited linguistic information (e.g. dictionaries and langua
Externí odkaz:
http://arxiv.org/abs/2107.10064