List of accepted Full-Papers

DAS 2022, the 15th IAPR International Workshop on Document Analysis System, received 88 full-paper submissions. After careful and intensive review, for which we thank the reviewers, 31 papers are accepted for oral presentation and 21 for poster presentation.

(The list is sorted by ORAL/POSTER and EasyChair submission number.)

#	Authors	Title	Presentation type
2	Rafael Lins, Rodrigo B. Bernardino, Ricardo Barboza and Raimundo Oliveira	The Winner Takes It All: choosing the “best” binarization algorithm for photographed documents	Oral
6	Shuang Liu, Renshen Wang, Michalis Raptis and Yasuhisa Fujii	Unified Line and Paragraph Detection by Graph Convolutional Networks	Oral
9	Christoph Wick, Jochen Zöllner and Tobias Grüning	Rescoring Sequence-to-Sequence Models for Text Line Recognition with CTC-Prefixes	Oral
12	Michael Koepf, Florian Kleber and Robert Sablatnig	Writer Identification and Writer Retrieval using Vision Transformer for Forensic Documents	Oral
14	Hussein Mohammed, Agnieszka Helman-Wazny, Claudia Colini, Wiebke Beyer and Sebastian Bosch	Pattern Analysis Software Tools (PAST) for Ancient Written Artefacts	Oral
16	Martin Maarand, Yngvil Beyer, Andre Kåsen, Knut Fosseide and Christopher Kermorvant	A Comprehensive Comparison of Open-Source Libraries for Handwritten Text Recognition in Norwegian	Oral
19	Christian Reul, Stefan Tomasek, Florian Langhanki and Uwe Springmann	Open Source Handwritten Text Recognition on Medieval Manuscripts using Mixed Models and Document-Specific Finetuning	Oral
20	Hadia Showkat Kawoosa, Mandhatya Singh, Manoj Manikrao Joshi and Puneet Goyal	NCERT5K-IITRPR: A Benchmark Dataset for Non-Textual Component Detection in School Books	Oral
23	Claire Bizon Monroc, Blanche Miret, Marie-Laurence Bonhomme and Christopher Kermorvant	A Comprehensive Study of Open-source Libraries for Named Entity Recognition on Handwritten Historical Documents	Oral
26	Oliver Tüselmann and Gernot Fink	Named Entity Linking on Handwritten Document Images	Oral
27	José Andrés, Alejandro H. Toselli and Enrique Vidal	Approximate Search for Keywords in Handwritten Text Images	Oral
28	Killian Barrere, Yann Soullard, Aurélie Lemaitre and Bertrand Coüasnon	A Light Transformer-Based Architecture for Handwritten Text Recognition	Oral
33	Ladislav Lenc, Jiří Martínek, Martin Prantl, Josef Baloun and Pavel Král	Historical Map Toponym Extraction for Efficient Information Retrieval	Oral
36	Giorgos Sfikas, George Retsinas, Angelos P. Giotis, Basilis Gatos and Christophoros Nikou	Keyword Spotting with Quaternionic ResNet: Application to Spotting in Greek Manuscripts	Oral
37	Martin Kišš, Jan Kohút, Karel Beneš and Michal Hradiš	Importance of Textlines in Historical Document Classification	Oral
46	Simon Schiff, Sylvia Melzer, Eva Wilden and Ralf Möller	TEI-based Interactive Critical Editions	Oral
48	Josep Brugués i Pujolràs, Lluis Gomez and Dimosthenis Karatzas	A Multilingual Approach to Scene Text Visual Question Answering	Oral
54	Thomas Constum, Nicolas Kempf, Thierry Paquet, Pierrick Tranouez and Clément Chatelain	Recognition and information extraction in historical handwritten tables: toward understanding early 20th century Paris census	Oral
56	José Andrés, Jose Ramón Prieto, Emilio Granell, Verónica Romero, Joan Andreu Sánchez and Enrique Vidal	Information Extraction from Handwritten Tables in Historical Documents	Oral
58	Ramon Pires, Fabio Souza, Guilherme Rosa, Roberto Lotufo and Rodrigo Nogueira	Sequence-to-Sequence Models for Extracting Information from Registration and Legal Documents	Oral
60	Nathalie Abadie, Edwin Carlinet, Joseph Chazalon and Bertrand Duménieu	A Benchmark of NER Approaches in Historical Documents	Oral
63	G Nagendar and Ramachandrula Sitaram	Contrastive Graph Learning with Graph Convolutional Networks	Oral
64	Xiaotong Ji, Yan Zheng, Daiki Suehiro and Seiichi Uchida	Revealing Reliable Signatures by Learning Top-Rank Pairs	Oral
66	Masaya Ueda, Akisato Kimura and Seiichi Uchida	Font Shape-to-Impression Translation	Oral
71	Prabhat Kumar Bharti, Tirthankar Ghosal, Mayank Agrawal and Asif Ekbal	How Confident Was Your Reviewer? Estimating Reviewer Confidence From Peer Review Texts	Oral
72	Yusuke Nagata, Jinki Otao, Daichi Haraguchi and Seiichi Uchida	TrueType Transformer: Character and Font Style Recognition in Outline Format	Oral
74	George Retsinas, Giorgos Sfikas, Basilis Gatos and Christophoros Nikou	Best Practices for a Handwritten Text Recognition system	Oral
76	George Retsinas, Giorgos Sfikas, Basilis Gatos and Christophoros Nikou	On-The-Fly Deformations for Keyword Spotting	Oral
87	Joan Andreu Sanchez, Enrique Vidal and Vicente Bosch	Effective Crowdsourcing in the EDT Project with Probabilistic Indexes	Oral
90	Thibault Douzon, Christophe Garcia, Stefan Duffner and Jérémy Espinas	Improving Information Extraction on Business Documents with Specific Pre Training Tasks	Oral
92	Raphaela Heil, Ekta Vats and Anders Hast	Paired Image to Image Translation for Strikethrough Removal From Handwritten Words	Oral
5	Gonzalo Santamaría, Cesar Dominguez, Jónathan Heras, Eloy Mata and Vico Pascual	Combining image processing techniques, OCR, and OMR for the digitization of musical books	Poster
15	Wassim Swaileh, Michel Jordan and Dimitrios Kotzinos	3D Modelling Approach for Ancient Floor Plans’ Quick Browsing	Poster
17	Mohamed El Baha, Olivier Augereau, Sofiya Kobylyanskaya, Ioana Vasilescu and Laurence Devillers	Eye Got It : a System for Automatic Calculation of the Eye-Voice Span.	Poster
18	David Villanova-Aparisi, Carlos-D. Martínez-Hinarejos, Verónica Romero and Moisés Pastor-Gadea	Evaluation of Named Entity Recognition in handwritten documents	Poster
21	Ahmad Droby, Daria Vasyutinsky Shapira, Irina Rabaev, Berat Kurar and Jihad El-Sana	Hard and Soft Labeling for Hebrew Paleography: A Case Study	Poster
22	Solène Tarride, Aurélie Lemaitre, Bertrand Coüasnon and Sophie Tardivel	A comparative study of information extraction strategies using an attention-based neural network	Poster
34	Ibrahim Souleiman Mahamoud, Michaël Coustaty, Aurélie Joseph, Vincent Poulain d’Andecy and Jean-Marc Ogier	Qalayout :Question answering Layout based on multimodal Attention for visual question answering on corporate Document	Poster
41	Konstantina Nikolaidou, Richa Upadhyay, Mathias Seuret and Marcus Liwicki	Investigating the Effect of using Synthetic and Semi-synthetic Images for Historical Document Classification	Poster
45	Adrià Molina Rodríguez, Josep Lladós Canet, Oriol Ramos Terrades and Lluis Gomez Bigorda	A Generic Date Estimation System for Historical Document Images based on Ordinal Classification	Poster
51	Alexander Mattick, Martin Mayr, Andreas Maier and Vincent Christlein	Is multi-task learning always better?	Poster
55	Mathieu Francois, Véronique Eglin and Maxime Biou	Text detection and post-OCR correction in Engineering Documents	Poster
59	Dmitrijs Kass and Ekta Vats	AttentionHTR: Handwritten Text Recognition Based on Attention Encoder-Decoder Networks	Poster
62	Sergi Garcia, George Tom, Sangeeth Battu, Minesh Mathew, Marçal Rusiñol, C.V. Jawahar and Dimosthenis Karatzas	Read while you Drive – Multilingual Text Tracking on the Road	Poster
67	Athar Sefid and C. Lee Giles	SciBERTSUM: Extractive Summarization for Scientific Documents	Poster
73	Hai Thi Tuyet Nguyen, Adam Jatowt, Mickael Coustaty and Antoine Doucet	ReadOCR: A Novel Dataset and Readability Assessment of OCRed Texts	Poster
75	Panagiotis Kaddas and Basilis Gatos	Using Multi-level Segmentation Features for Document Image Classification	Poster
78	Muhammad Atif Butt, Adnan Ul-Hasan and Faisal Shafait	TraffSign: Multilingual Traffic Signboard Text Detection and Recognition for Urdu and English	Poster
79	Martin Mayr, Alex Felker, Andreas Maier and Vincent Christlein	Combining Visual and Linguistic Models for a Robust Recipient Line Recognition in Historical Documents	Poster
80	Borak Madi, Reem Alaasam, Ahmad Droby and Jihad El-Sana	HST-GAN: Historical Style Transfer GAN for Generating Historical Text Images	Poster
89	Sofiane Medjram and Véronique Eglin	Challenging children handwriting recognition study exploiting synthetic, mixed and real data	Poster
98	Richin Sukesh, Mathias Seuret, Anguelos Nikolaou, Martin Mayr and Vincent Christlein	A Fair Evaluation of Deep Learning-based Binarization Methods	Poster