3 citations · 5 across the 29 of their papers we have counts for
24 papers · 1 filter
Rethinking Expert Training for Model Merging with Prompt Learning
Christos Georgakilas, Aniello Panariello, Samir El Karrat Moreno +3
Model merging aims to combine multiple domain-specialized experts trained from a shared foundation model into a single multi-task model. Existing approaches largely focus on improv…
SMI: Efficient Self-Supervised Learning via Mutual-Information-Inspired Dependency Optimization
Pritam Mishra, Coloma Ballester, Dimosthenis Karatzas
Self-supervised learning (SSL) has achieved remarkable representation learning performance, but many existing methods rely on large batch sizes, memory banks, momentum encoders, or…
TRIMMER: A New Paradigm for Video Summarization through Self-Supervised Reinforcement Learning
Pritam Mishra, Coloma Ballester, Dimosthenis Karatzas
The rapid growth of video content across domains such as surveillance, education, and social media has made efficient content understanding increasingly critical. Video summarizati…
Reading in the Dark: Low-light Scene Text Recognition
Xuanshuo Fu, Lei Kang, Ernest Valveny +2
Accurate text recognition in low-light environments is essential for intelligent systems in applications ranging from autonomous vehicles to smart surveillance. However, challenges…
AVIR: Adaptive Visual In-Document Retrieval for Efficient Multi-Page Document Question Answering
Zongmin Li, Yachuan Li, Lei Kang +2
Multi-page Document Visual Question Answering (MP-DocVQA) remains challenging because long documents not only strain computational resources but also reduce the effectiveness of th…
Counterfeit Answers: Adversarial Forgery against OCR-Free Document Visual Question Answering
Marco Pintore, Maura Pintor, Dimosthenis Karatzas +1
Document Visual Question Answering (DocVQA) enables end-to-end reasoning grounded on information present in a document input. While recent models have shown impressive capabilities…
Spatially Grounded Explanations in Vision Language Models for Document Visual Question Answering
Maximiliano Hormazábal Lagos, Héctor Cerezo-Costas, Dimosthenis Karatzas
We introduce EaGERS, a fully training-free and model-agnostic pipeline that (1) generates natural language rationales via a vision language model, (2) grounds these rationales to s…
CoSMo: A Multimodal Transformer for Page Stream Segmentation in Comic Books
Marc Serra Ortega, Emanuele Vivoli, Artemis Llabrés +1
This paper introduces CoSMo, a novel multimodal Transformer for Page Stream Segmentation (PSS) in comic books, a critical task for automated content understanding, as it is a neces…
TRIM: A Self-Supervised Video Summarization Framework Maximizing Temporal Relative Information and Representativeness
Pritam Mishra, Coloma Ballester, Dimosthenis Karatzas
The increasing ubiquity of video content and the corresponding demand for efficient access to meaningful information have elevated video summarization and video highlights as a vit…
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…
NoTeS-Bank: Benchmarking Neural Transcription and Search for Scientific Notes Understanding
Aniket Pal, Sanket Biswas, Alloy Das +6
Understanding and reasoning over academic handwritten notes remains a challenge in document AI, particularly for mathematical equations, diagrams, and scientific notations. Existin…
Preserving Privacy Without Compromising Accuracy: Machine Unlearning for Handwritten Text Recognition
Lei Kang, Xuanshuo Fu, Lluis Gomez +3
Handwritten Text Recognition (HTR) is crucial for document digitization, but handwritten data can contain user-identifiable features, like unique writing styles, posing privacy ris…
ComicsPAP: understanding comic strips by picking the correct panel
Emanuele Vivoli, Artemis Llabrés, Mohamed Ali Souibgui +3
Large multimodal models (LMMs) have made impressive strides in image captioning, VQA, and video comprehension, yet they still struggle with the intricate temporal and spatial cues…
ComiCap: A VLMs pipeline for dense captioning of Comic Panels
Emanuele Vivoli, Niccolò Biondi, Marco Bertini +1
The comic domain is rapidly advancing with the development of single- and multi-page analysis and synthesis models. Recent benchmarks and datasets have been introduced to support a…
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…
Image-text matching for large-scale book collections
Artemis Llabrés, Arka Ujjal Dey, Dimosthenis Karatzas +1
We address the problem of detecting and mapping all books in a collection of images to entries in a given book catalogue. Instead of performing independent retrieval for each book…
Comics Datasets Framework: Mix of Comics datasets for detection benchmarking
Emanuele Vivoli, Irene Campaioli, Mariateresa Nardoni +3
Comics, as a medium, uniquely combine text and images in styles often distinct from real-world visuals. For the past three decades, computational research on comics has evolved fro…
CoMix: A Comprehensive Benchmark for Multi-Task Comic Understanding
Emanuele Vivoli, Marco Bertini, Dimosthenis Karatzas
The comic domain is rapidly advancing with the development of single-page analysis and synthesis models. However, evaluation metrics and datasets lag behind, often limited to small…
Federated Document Visual Question Answering: A Pilot Study
Khanh Nguyen, Dimosthenis Karatzas
An important handicap of document analysis research is that documents tend to be copyrighted or contain private information, which prohibits their open publication and the creation…
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…
Multi-Page Document Visual Question Answering using Self-Attention Scoring Mechanism
Lei Kang, Rubèn Tito, Ernest Valveny +1
Documents are 2-dimensional carriers of written communication, and as such their interpretation requires a multi-modal approach where textual and visual information are efficiently…
Multimodal Transformer for Comics Text-Cloze
Emanuele Vivoli, Joan Lafuente Baeza, Ernest Valveny Llobet +1
This work explores a closure task in comics, a medium where visual and textual elements are intricately intertwined. Specifically, Text-cloze refers to the task of selecting the co…
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…