Pau Riba

Pau Riba

Postdoctoral Researcher at Computer Vision Center

CVC UAB

Bio

I received my B.Sc. degrees (with honours) in Mathematics and Computer Science from the Universitat Autònoma de Barcelona in 2015 and my M.Sc. degree (with honours) in Computer Vision from the Universitat Autònoma de Barcelona (UAB), Barcelona in 2016 where I was awarded with the "Best Master Thesis" award. In 2013 I joined the Computer Vision Center as an Intern Student. Later, I pursued my Ph.D. degree titled "Distilling Structure from Imagery: Graph-based Models for the Interpretation of Document Images" under the supervision of Dr. Josep Lladós and Dr. Alicia Fornés starting in 2016 and finishing in September 2020. I also acted as Assistant Editor at the Electronic Letters on Computer Vision and Image Analysis Journal (ELCVIA) of the Computer Vision Center. Currently, I am a Postdoctoral researcher at the Computer Vision Center and the dataset curator of the IAPR-TC10. My main research interests include Structural Pattern Recognition, Sketch-based applications, Graphics Recognition and Word Spotting

My personal interest includes reading and cinema.

Publications

List of publications

Journals

Learning Graph Edit Distance by Graph Neural Networks

Authors: Pau Riba, Andreas Fischer, Josep Lladós, Alicia Fornés

Pattern Recognition (PR), 2021Accepted

Doi:

Find out more   Code

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

Authors: Lei Kang, Pau Riba, Marçal Rusiñol, Alicia Fornés, Mauricio Villegas

Submitted, 2020

Doi:

Find out more

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

Authors: Lei Kang, Pau Riba, Mauricio Villegas, Alicia Fornés, Marçal Rusiñol

Pattern Recognition (PR), Vol.112, 2021

Doi: 10.1016/j.patcog.2020.107790

Find out more

Hierarchical Stochastic Graphlet Embedding for Graph-based Pattern Recognition

Authors: Anjan Dutta*, Pau Riba*, Josep Lladós, Alicia Fornés

Neural Computing and Applications (NCAA), pp.1-18, 2019

Doi: 10.1007/s00521-019-04642-7

Find out more

From Optical Music Recognition to Handwritten Music Recognition: a Baseline

Authors: Arnau Baró, Pau Riba, Jorge Calvo-Zaragoza, Alicia Fornés

Pattern Recognition Letters (PRL), Vol.124, pp.1-8, 2019

Doi: 10.1016/j.patrec.2019.02.029

Find out more

Hierarchical graphs for coarse-to-fine error tolerant matching

Authors: Pau Riba, Josep Lladós, Alicia Fornés

Pattern Recognition Letters (PRL), In Press

Doi: 10.1016/j.patrec.2019.02.001

Find out more

Large-scale Graph Indexing using Binary Embeddings of Node Contexts for Information Spotting in Document Image Databases

Authors: Pau Riba, Josep Lladós, Alicia Fornés, Anjan Dutta

Pattern Recognition Letters (PRL), Vol.87, pp.203-211, 2016

Doi: 10.1016/j.patrec.2016.06.015

Find out more

Conferences and Workshops

Named Entity Recognition and Relation Extraction with Graph Neural Networks in Semi Structured Documents

Authors: Manuel Carbonell, Pau Riba, Mauricio Villegas, Alicia Fornés, Josep Lladós

International Conference on Pattern Recognition (ICPR), 2020; Oral

Find out more   Code

Distilling Content from Style for Handwritten Word Recognition

Authors: Lei Kang, Pau Riba, Marçal Rusiñol, Alicia Fornés, Mauricio Villegas

International Conference on Frontiers in Handwriting Recognition (ICFHR), 2020; Oral

ICFHR2020 Best Paper Award

Find out more   Code

GANwriting: Content-Conditioned Generation of Styled Handwritten Word Images

Authors: Lei Kang, Pau Riba, Yaxing Wang, Marçal Rusiñol, Alicia Fornés, Mauricio Villegas

European Conference on Computer Vision (ECCV), 2020; Poster (Acceptance Rate: 26%)

Find out more   Code

Unsupervised Adaptation for Synthetic-to-Real Handwritten Word Recognition

Authors: Lei Kang, Marçal Rusiñol, Alicia Fornés, Pau Riba and Mauricio Villegas

Winter Conference on Applications of Computer Vision (WACV), 2020; Poster

Find out more   Code

Table Detection in Invoice Documents by Graph Neural Networks

Authors: Pau Riba, Anjan Dutta, Lutz Goldmann, Alicia Fornés, Oriol Ramos and Josep Lladós

15th International Conference on Document Analysis and Recognition (ICDAR), 2019; Oral

Find out more   Slides

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

Authors: Sounak Dey*, Pau Riba*, Anjan Dutta, Josep Lladós and Yi-zhe Song

Conference on Computer Vision and Pattern Recognition (CVPR), 2019; Oral (Acceptance Rate: 25.2%)

Find out more   Code   Project

Convolve, Attend and Spell: An Attention-based Sequence-to-Sequence model for Handwritten Word Recognition

Authors: Lei Kang, J.Ignacio Toledo, Pau Riba, Mauricio Villegas, Alicia Fornés and Marçal Rusiñol

40th German Conference on Pattern Recognition (GCPR), 2018; Poster

Find out more   Code

Learning Graph Distances with Message Passing Neural Networks

Authors: Pau Riba, Andreas Fischer, Josep Llados and Alicia Fornés

24th International Conference on Pattern Recognition (ICPR), pp.2239-2244, 2018; Oral

ICPR2018 Best Scientific Paper Award

Find out more   Code   Slides

Word-Hunter: A Gamesourcing Experience to Validate the Transcription of Historical Manuscripts

Authors: Jialuo Chen, Pau Riba, Alicia Fornés Joan Mas, Josep Llados and Joana Maria Pujadas-Mora

16th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp.528-533, 2018

Find out more

Improving Information Retrieval in Multiwriter Scenario by Exploiting the Similarity Graph of Document Terms

Authors: Pau Riba, Anjan Dutta, Sounak Dey, Josep Llados and Alicia Fornés

14th International Conference on Document Analysis and Recognition (ICDAR), pp.475-480, 2017; Oral

Find out more   Slides

Pyramidal Stochastic Graphlet Embedding for Document Pattern Classification

Authors: Anjan Dutta, Pau Riba, Josep Lladós and Alicia Fornés

14th International Conference on Document Analysis and Recognition (ICDAR), pp.33-38, 2017; Oral

Find out more   Code   Slides

Error-tolerant coarse-to-fine matching model for hierarchical graphs

Authors: Pau Riba, Josep Lladós, Alicia Fornés

11th International Workshop on Graph-Based Representations in Pattern Recognition (GbR), pp.107-117, 2017

Find out more   Slides

Towards the recognition of compound music notes in handwritten music scores

Authors: Arnau Baró, Pau Riba, Alicia Fornés

15th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp.465-470, 2016

Find out more

Handwritten Word Spotting by Inexact Matching of Grapheme Graphs

Authors: Pau Riba, Josep Lladós, Alicia Fornés

13th International Conference on Document Analysis and Recognition (ICDAR), pp.781-785, 2015; Oral

Find out more

Towards the alignment of handwritten music scores

Authors: Pau Riba, Alicia Fornés, Josep Lladós

"Graphic Recognition. Current Trends and Challenges", Lecture Notes in Computer Science, Vol.9657, pp.103-116, 2017

Find out more

Monitoring Neuromotricity On-line: a Cloud Computing Approach

Authors: Olivier Lefebvre, Pau Riba, Jules Gagnon-Marchand, Charles Fournier, Alicia Fornes, Josep Llados, Réjean Plamondon

17th Biennial Conference of the International Graphonomics Society (IGS), pp.63-66, 2015

Find out more

Large-scale graph indexing using binary embeddings of node contexts

Authors: Pau Riba, Josep Lladós, Alicia Fornés, Anjan Dutta

"Graph-Based Representations in Pattern Recognition", Lecture Notes in Computer Science, Vol.9069, pp.208-217, 2015

Find out more

On the Influence of Key Point Encoding for Handwritten Word Spotting

Authors: David Fernández-Mota, Pau Riba, Alicia Fornés, Josep Lladós

14th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp.476-481, 2014

Find out more

e-Crowds: a mobile platform for browsing and searching in historical demography-related manuscripts

Authors: Pau Riba, Jon Almazán, Alicia Fornés, David Fernández-Mota, Ernest Valveny, Josep Lladós

14th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp.228-233, 2014

Find out more

Theses

Ph.D. Thesis:

Distilling Structure from Imagery: Graph-based Models for the Interpretation of Document Images

Advisors: Josep Lladós and Alicia Fornés

Find out more   Video

Master Thesis:

An error-tolerant graph matching model for hierarchical graphs with topological node embedding in large scale visual retrieval

Advisors: Josep Lladós and Alicia Fornés

Find out more

Bachelor Thesis:

Graph-Based Word Spotting by Inexact Matching Techniques

Advisors: Josep Lladós and Alicia Fornés

Find out more

Projects

Consolidated Research Group DAG-CVC (SGR)

Principal Investigator: Josep Lladós (CVC)

Funding: AGAUR

From: 2018 to -

NETWORKS: Tecnology and citizen innovation for building historical social networks to understand the demographic past

Principal Investigator: Alicia Fornés (CVC) and Joana Maria Pujades (CED)

Funding: RECERCAIXA

From: 15-02-2017 to 14-02-2019

Find out more

CONtextualising the COntents in the Recognition of Document Images from Archives (CONCORDIA)

Principal Investigator: Josep Lladós (CVC) and Alicia Fornés (CVC)

Funding: FEDER, MINECO

From: 01-01-2016 to 31-12-2018

Find out more

Digitus II: Automatic Indexation Service for Handwritten Archives

Principal Investigator: Pau Riba (CVC) and Marçal Rossinyol (CVC)

Funding: FEDER, AGAUR

From: 21-07-2017 to 21-01-2018

Find out more

Contextual Recognition of Ancient Documents (Co-Read)

Principal Investigator: Josep Lladós (CVC)

Funding: MINECO

From: 01-01-2013 to 31-12-2015

Find out more

Consolidated Research Group DAG-CVC (SGR)

Principal Investigator: Josep Lladós (CVC)

Funding: AGAUR

From: 07-05-2014 to 30-04-2017