Search Results for author: Pau Riba

Found 13 papers, 6 papers with code

Content and Style Aware Generation of Text-line Images for Handwriting Recognition

no code implementations12 Apr 2022 Lei Kang, Pau Riba, Marçal Rusiñol, Alicia Fornés, Mauricio Villegas

Once properly trained, our method can also be adapted to new target data by only accessing unlabeled text-line images to mimic handwritten styles and produce images with any textual content.

Handwriting Recognition Handwritten Text Recognition

Localizing Infinity-shaped fishes: Sketch-guided object localization in the wild

no code implementations24 Sep 2021 Pau Riba, Sounak Dey, Ali Furkan Biten, Josep Llados

This work investigates the problem of sketch-guided object localization (SGOL), where human sketches are used as queries to conduct the object localization in natural images.

Instance Segmentation Object +4

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

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

Pay Attention to What You Read: Non-recurrent Handwritten Text-Line Recognition

no code implementations26 May 2020 Lei Kang, Pau Riba, Marçal Rusiñol, Alicia Fornés, Mauricio Villegas

Sequential architectures are a perfect fit to model text lines, not only because of the inherent temporal aspect of text, but also to learn probability distributions over sequences of characters and words.

Few-Shot Learning Handwriting Recognition +1

GANwriting: Content-Conditioned Generation of Styled Handwritten Word Images

3 code implementations ECCV 2020 Lei Kang, Pau Riba, Yaxing Wang, Marçal Rusiñol, Alicia Fornés, Mauricio Villegas

We propose a novel method that is able to produce credible handwritten word images by conditioning the generative process with both calligraphic style features and textual content.

Handwritten Word Generation

Candidate Fusion: Integrating Language Modelling into a Sequence-to-Sequence Handwritten Word Recognition Architecture

no code implementations21 Dec 2019 Lei Kang, Pau Riba, Mauricio Villegas, Alicia Fornés, Marçal Rusiñol

The main challenge faced when training a language model is to deal with the language model corpus which is usually different to the one used for training the handwritten word recognition system.

Language Modelling

Unsupervised Adaptation for Synthetic-to-Real Handwritten Word Recognition

no code implementations18 Sep 2019 Lei Kang, Marçal Rusiñol, Alicia Fornés, Pau Riba, Mauricio Villegas

Handwritten Text Recognition (HTR) is still a challenging problem because it must deal with two important difficulties: the variability among writing styles, and the scarcity of labelled data.

Data Augmentation Handwritten Text Recognition +1

Doodle to Search: Practical Zero-Shot Sketch-based Image Retrieval

1 code implementation CVPR 2019 Sounak Dey, Pau Riba, Anjan Dutta, Josep Llados, Yi-Zhe Song

Highly abstract amateur human sketches are purposefully sourced to maximize the domain gap, instead of ones included in existing datasets that can often be semi-photorealistic.

Retrieval Sketch-Based Image Retrieval

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 Clustering +1

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