Search Results for author: Josep Lladós

Found 18 papers, 7 papers with code

Doc2Graph: a Task Agnostic Document Understanding Framework based on Graph Neural Networks

no code implementations23 Aug 2022 Andrea Gemelli, Sanket Biswas, Enrico Civitelli, Josep Lladós, Simone Marinai

Geometric Deep Learning has recently attracted significant interest in a wide range of machine learning fields, including document analysis.

Key information extraction Table Detection

A Generic Image Retrieval Method for Date Estimation of Historical Document Collections

no code implementations8 Apr 2022 Adrià Molina, Lluis Gomez, Oriol Ramos Terrades, Josep Lladós

Date estimation of historical document images is a challenging problem, with several contributions in the literature that lack of the ability to generalize from one dataset to others.

Image Retrieval Retrieval

Text-DIAE: A Self-Supervised Degradation Invariant Autoencoders for Text Recognition and Document Enhancement

no code implementations9 Mar 2022 Mohamed Ali Souibgui, Sanket Biswas, Andres Mafla, Ali Furkan Biten, Alicia Fornés, Yousri Kessentini, Josep Lladós, Lluis Gomez, Dimosthenis Karatzas

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.

Image Enhancement Scene Text Recognition

Graph-based Deep Generative Modelling for Document Layout Generation

no code implementations9 Jul 2021 Sanket Biswas, Pau Riba, Josep Lladós, Umapada Pal

One of the major prerequisites for any deep learning approach is the availability of large-scale training data.

DocSynth: A Layout Guided Approach for Controllable Document Image Synthesis

1 code implementation6 Jul 2021 Sanket Biswas, Pau Riba, Josep Lladós, Umapada Pal

The results highlight that our model can successfully generate realistic and diverse document images with multiple objects.

Document Layout Analysis Image Generation

Learning to Rank Words: Optimizing Ranking Metrics for Word Spotting

1 code implementation9 Jun 2021 Pau Riba, Adrià Molina, Lluis Gomez, Oriol Ramos-Terrades, Josep Lladós

In this paper, we explore and evaluate the use of ranking-based objective functions for learning simultaneously a word string and a word image encoder.

Learning-To-Rank Retrieval

One-shot Compositional Data Generation for Low Resource Handwritten Text Recognition

no code implementations11 May 2021 Mohamed Ali Souibgui, Ali Furkan Biten, Sounak Dey, Alicia Fornés, Yousri Kessentini, Lluis Gomez, Dimosthenis Karatzas, Josep Lladós

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).

Handwritten Text Recognition

Learning Graph Edit Distance by Graph Neural Networks

no code implementations17 Aug 2020 Pau Riba, Andreas Fischer, Josep Lladós, Alicia Fornés

The emergence of geometric deep learning as a novel framework to deal with graph-based representations has faded away traditional approaches in favor of completely new methodologies.

Graph Similarity Keyword Spotting +2

A Neural Model for Text Localization, Transcription and Named Entity Recognition in Full Pages

2 code implementations20 Dec 2019 Manuel Carbonell, Alicia Fornés, Mauricio Villegas, Josep Lladós

In this work we propose an end-to-end model that combines a one stage object detection network with branches for the recognition of text and named entities respectively in a way that shared features can be learned simultaneously from the training error of each of the tasks.

named-entity-recognition Named Entity Recognition +2

Hierarchical stochastic graphlet embedding for graph-based pattern recognition

1 code implementation8 Jul 2018 Anjan Dutta, Pau Riba, Josep Lladós, Alicia Fornés

Graph embedding, which maps graphs to a vectorial space, has been proposed as a way to tackle these difficulties enabling the use of standard machine learning techniques.

BIG-bench Machine Learning Graph Embedding

Learning Cross-Modal Deep Embeddings for Multi-Object Image Retrieval using Text and Sketch

no code implementations28 Apr 2018 Sounak Dey, Anjan Dutta, Suman K. Ghosh, Ernest Valveny, Josep Lladós, Umapada Pal

In this work we introduce a cross modal image retrieval system that allows both text and sketch as input modalities for the query.

Image Retrieval Retrieval

Joint Recognition of Handwritten Text and Named Entities with a Neural End-to-end Model

no code implementations16 Mar 2018 Manuel Carbonell, Mauricio Villegas, Alicia Fornés, Josep Lladós

When extracting information from handwritten documents, text transcription and named entity recognition are usually faced as separate subsequent tasks.

Language Modelling named-entity-recognition +2

e-Counterfeit: a mobile-server platform for document counterfeit detection

no code implementations21 Aug 2017 Albert Berenguel, Oriol Ramos Terrades, Josep Lladós, Cristina Cañero

This paper presents a novel application to detect counterfeit identity documents forged by a scan-printing operation.

Texture Classification

Product Graph-based Higher Order Contextual Similarities for Inexact Subgraph Matching

no code implementations1 Feb 2017 Anjan Dutta, Josep Lladós, Horst Bunke, Umapada Pal

Many algorithms formulate graph matching as an optimization of an objective function of pairwise quantification of nodes and edges of two graphs to be matched.

Graph Matching

Cannot find the paper you are looking for? You can Submit a new open access paper.