166 citations · 272 across the 19 of their papers we have counts for
19 papers
Learning Quantifiable Visual Explanations Without Ground-Truth
Amritpal Singh, Andrey Barsky, Mohamed Ali Souibgui +2
Explainable AI (XAI) techniques are increasingly important for the validation and responsible use of modern deep learning models, but are difficult to evaluate due to the lack of g…
LayerBoost: Layer-Aware Attention Reduction for Efficient LLMs
Mohamed Ali Souibgui, Jan Fostier, Rodrigo Abadía-Heredia +3
Transformers are mostly relying on softmax attention, which introduces quadratic complexity with respect to sequence length and remains a major bottleneck for efficient inference.…
ORCA: Orchestrated Reasoning with Collaborative Agents for Document Visual Question Answering
Aymen Lassoued, Mohamed Ali Souibgui, Yousri Kessentini
Document Visual Question Answering (DocVQA) remains challenging for existing Vision-Language Models (VLMs), especially under complex reasoning and multi-step workflows. Current app…
DocVXQA: Context-Aware Visual Explanations for Document Question Answering
Mohamed Ali Souibgui, Changkyu Choi, Andrey Barsky +3
We propose DocVXQA, a novel framework for visually self-explainable document question answering. The framework is designed not only to produce accurate answers to questions but als…
NeurIPS 2023 Competition: Privacy Preserving Federated Learning Document VQA
Marlon Tobaben, Mohamed Ali Souibgui, Rubèn Tito +24
The Privacy Preserving Federated Learning Document VQA (PFL-DocVQA) competition challenged the community to develop provably private and communication-efficient solutions in a fede…
One missing piece in Vision and Language: A Survey on Comics Understanding
Emanuele Vivoli, Mohamed Ali Souibgui, Andrey Barsky +3
Vision-language models have recently evolved into versatile systems capable of high performance across a range of tasks, such as document understanding, visual question answering,…
GRIF-DM: Generation of Rich Impression Fonts using Diffusion Models
Lei Kang, Fei Yang, Kai Wang +5
Fonts are integral to creative endeavors, design processes, and artistic productions. The appropriate selection of a font can significantly enhance artwork and endow advertisements…
Machine Unlearning for Document Classification
Lei Kang, Mohamed Ali Souibgui, Fei Yang +3
Document understanding models have recently demonstrated remarkable performance by leveraging extensive collections of user documents. However, since documents often contain large…
Privacy-Aware Document Visual Question Answering
Rubèn Tito, Khanh Nguyen, Marlon Tobaben +11
Document Visual Question Answering (DocVQA) has quickly grown into a central task of document understanding. But despite the fact that documents contain sensitive or copyrighted in…
ST-KeyS: Self-Supervised Transformer for Keyword Spotting in Historical Handwritten Documents
Sana Khamekhem Jemni, Sourour Ammar, Mohamed Ali Souibgui +2
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 ma…
CSSL-MHTR: Continual Self-Supervised Learning for Scalable Multi-script Handwritten Text Recognition
Marwa Dhiaf, Mohamed Ali Souibgui, Kai Wang +4
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 over…
A Few Shot Multi-Representation Approach for N-gram Spotting in Historical Manuscripts
Giuseppe De Gregorio, Sanket Biswas, Mohamed Ali Souibgui +4
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…
Text-DIAE: A Self-Supervised Degradation Invariant Autoencoders for Text Recognition and Document Enhancement
Mohamed Ali Souibgui, Sanket Biswas, Andres Mafla +6
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)…
DocEnTr: An End-to-End Document Image Enhancement Transformer
Mohamed Ali Souibgui, Sanket Biswas, Sana Khamekhem Jemni +4
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…
Few Shots Are All You Need: A Progressive Few Shot Learning Approach for Low Resource Handwritten Text Recognition
Mohamed Ali Souibgui, Alicia Fornés, Yousri Kessentini +1
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 dat…
Enhance to Read Better: A Multi-Task Adversarial Network for Handwritten Document Image Enhancement
Sana Khamekhem Jemni, Mohamed Ali Souibgui, Yousri Kessentini +1
Handwritten document images can be highly affected by degradation for different reasons: Paper ageing, daily-life scenarios (wrinkles, dust, etc.), bad scanning process and so on.…
One-shot Compositional Data Generation for Low Resource Handwritten Text Recognition
Mohamed Ali Souibgui, Ali Furkan Biten, Sounak Dey +5
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 models). F…
DE-GAN: A Conditional Generative Adversarial Network for Document Enhancement
Mohamed Ali Souibgui, Yousri Kessentini
Documents often exhibit various forms of degradation, which make it hard to be read and substantially deteriorate the performance of an OCR system. In this paper, we propose an eff…
A Few-shot Learning Approach for Historical Ciphered Manuscript Recognition
Mohamed Ali Souibgui, Alicia Fornés, Yousri Kessentini +1
Encoded (or ciphered) manuscripts are a special type of historical documents that contain encrypted text. The automatic recognition of this kind of documents is challenging because…