activity
20182025
most citedAsking questions on handwritten document collections

12 citations · 23 across the 17 of their papers we have counts for

collaborators
Showing cs.CVShow all

28 papers · 1 filter

cs.CV2025★ 3 cited

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…

cs.CV2024

Transductive Learning for Near-Duplicate Image Detection in Scanned Photo Collections

Francesc Net, Marc Folia, Pep Casals +1

This paper presents a comparative study of near-duplicate image detection techniques in a real-world use case scenario, where a document management company is commissioned to manua…

cs.CV2024

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…

cs.CV2024

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…

cs.CV2022★ 2 cited

Show, Interpret and Tell: Entity-aware Contextualised Image Captioning in Wikipedia

Khanh Nguyen, Ali Furkan Biten, Andres Mafla +2

Humans exploit prior knowledge to describe images, and are able to adapt their explanation to specific contextual information, even to the extent of inventing plausible explanation…

cs.CV2022★ 1 cited

MUST-VQA: MUltilingual Scene-text VQA

Emanuele Vivoli, Ali Furkan Biten, Andres Mafla +2

In this paper, we present a framework for Multilingual Scene Text Visual Question Answering that deals with new languages in a zero-shot fashion. Specifically, we consider the task…