toggle visibility Search & Display Options

Select All    Deselect All
 |   | 
Details
  Records Links
Author George Tom; Minesh Mathew; Sergi Garcia Bordils; Dimosthenis Karatzas; CV Jawahar edit  url
openurl 
  Title ICDAR 2023 Competition on RoadText Video Text Detection, Tracking and Recognition Type Conference Article
  Year 2023 Publication 17th International Conference on Document Analysis and Recognition Abbreviated Journal  
  Volume (down) 14188 Issue Pages 577–586  
  Keywords  
  Abstract In this report, we present the final results of the ICDAR 2023 Competition on RoadText Video Text Detection, Tracking and Recognition. The RoadText challenge is based on the RoadText-1K dataset and aims to assess and enhance current methods for scene text detection, recognition, and tracking in videos. The RoadText-1K dataset contains 1000 dash cam videos with annotations for text bounding boxes and transcriptions in every frame. The competition features an end-to-end task, requiring systems to accurately detect, track, and recognize text in dash cam videos. The paper presents a comprehensive review of the submitted methods along with a detailed analysis of the results obtained by the methods. The analysis provides valuable insights into the current capabilities and limitations of video text detection, tracking, and recognition systems for dashcam videos.  
  Address San Jose; CA; USA; August 2023  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title LNCS  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference ICDAR  
  Notes DAG Approved no  
  Call Number Admin @ si @ TMG2023 Serial 3905  
Permanent link to this record
 

 
Author Ayan Banerjee; Sanket Biswas; Josep Llados; Umapada Pal edit  url
openurl 
  Title SwinDocSegmenter: An End-to-End Unified Domain Adaptive Transformer for Document Instance Segmentation Type Conference Article
  Year 2023 Publication 17th International Conference on Document Analysis and Recognition Abbreviated Journal  
  Volume (down) 14187 Issue Pages 307–325  
  Keywords  
  Abstract Instance-level segmentation of documents consists in assigning a class-aware and instance-aware label to each pixel of the image. It is a key step in document parsing for their understanding. In this paper, we present a unified transformer encoder-decoder architecture for en-to-end instance segmentation of complex layouts in document images. The method adapts a contrastive training with a mixed query selection for anchor initialization in the decoder. Later on, it performs a dot product between the obtained query embeddings and the pixel embedding map (coming from the encoder) for semantic reasoning. Extensive experimentation on competitive benchmarks like PubLayNet, PRIMA, Historical Japanese (HJ), and TableBank demonstrate that our model with SwinL backbone achieves better segmentation performance than the existing state-of-the-art approaches with the average precision of 93.72, 54.39, 84.65 and 98.04 respectively under one billion parameters. The code is made publicly available at: github.com/ayanban011/SwinDocSegmenter .  
  Address San Jose; CA; USA; August 2023  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title LNCS  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference ICDAR  
  Notes DAG Approved no  
  Call Number Admin @ si @ BBL2023 Serial 3893  
Permanent link to this record
 

 
Author Subhajit Maity; Sanket Biswas; Siladittya Manna; Ayan Banerjee; Josep Llados; Saumik Bhattacharya; Umapada Pal edit   pdf
url  doi
openurl 
  Title SelfDocSeg: A Self-Supervised vision-based Approach towards Document Segmentation Type Conference Article
  Year 2023 Publication 17th International Conference on Doccument Analysis and Recognition Abbreviated Journal  
  Volume (down) 14187 Issue Pages 342–360  
  Keywords  
  Abstract Document layout analysis is a known problem to the documents research community and has been vastly explored yielding a multitude of solutions ranging from text mining, and recognition to graph-based representation, visual feature extraction, etc. However, most of the existing works have ignored the crucial fact regarding the scarcity of labeled data. With growing internet connectivity to personal life, an enormous amount of documents had been available in the public domain and thus making data annotation a tedious task. We address this challenge using self-supervision and unlike, the few existing self-supervised document segmentation approaches which use text mining and textual labels, we use a complete vision-based approach in pre-training without any ground-truth label or its derivative. Instead, we generate pseudo-layouts from the document images to pre-train an image encoder to learn the document object representation and localization in a self-supervised framework before fine-tuning it with an object detection model. We show that our pipeline sets a new benchmark in this context and performs at par with the existing methods and the supervised counterparts, if not outperforms. The code is made publicly available at: this https URL  
  Address Document Layout Analysis; Document  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference ICDAR  
  Notes DAG Approved no  
  Call Number Admin @ si @ MBM2023 Serial 3990  
Permanent link to this record
 

 
Author Stepan Simsa; Michal Uricar; Milan Sulc; Yash Patel; Ahmed Hamdi; Matej Kocian; Matyas Skalicky; Jiri Matas; Antoine Doucet; Mickael Coustaty; Dimosthenis Karatzas edit  url
doi  openurl
  Title Overview of DocILE 2023: Document Information Localization and Extraction Type Conference Article
  Year 2023 Publication International Conference of the Cross-Language Evaluation Forum for European Languages Abbreviated Journal  
  Volume (down) 14163 Issue Pages 276–293  
  Keywords Information Extraction; Computer Vision; Natural Language Processing; Optical Character Recognition; Document Understanding  
  Abstract This paper provides an overview of the DocILE 2023 Competition, its tasks, participant submissions, the competition results and possible future research directions. This first edition of the competition focused on two Information Extraction tasks, Key Information Localization and Extraction (KILE) and Line Item Recognition (LIR). Both of these tasks require detection of pre-defined categories of information in business documents. The second task additionally requires correctly grouping the information into tuples, capturing the structure laid out in the document. The competition used the recently published DocILE dataset and benchmark that stays open to new submissions. The diversity of the participant solutions indicates the potential of the dataset as the submissions included pure Computer Vision, pure Natural Language Processing, as well as multi-modal solutions and utilized all of the parts of the dataset, including the annotated, synthetic and unlabeled subsets.  
  Address Thessaloniki; Greece; September 2023  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title LNCS  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference CLEF  
  Notes DAG Approved no  
  Call Number Admin @ si @ SUS2023a Serial 3924  
Permanent link to this record
 

 
Author Emanuele Vivoli; Ali Furkan Biten; Andres Mafla; Dimosthenis Karatzas; Lluis Gomez edit   pdf
url  doi
openurl 
  Title MUST-VQA: MUltilingual Scene-text VQA Type Conference Article
  Year 2022 Publication Proceedings European Conference on Computer Vision Workshops Abbreviated Journal  
  Volume (down) 13804 Issue Pages 345–358  
  Keywords Visual question answering; Scene text; Translation robustness; Multilingual models; Zero-shot transfer; Power of language models  
  Abstract 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 of Scene Text Visual Question Answering (STVQA) in which the question can be asked in different languages and it is not necessarily aligned to the scene text language. Thus, we first introduce a natural step towards a more generalized version of STVQA: MUST-VQA. Accounting for this, we discuss two evaluation scenarios in the constrained setting, namely IID and zero-shot and we demonstrate that the models can perform on a par on a zero-shot setting. We further provide extensive experimentation and show the effectiveness of adapting multilingual language models into STVQA tasks.  
  Address Tel-Aviv; Israel; October 2022  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title LNCS  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference ECCVW  
  Notes DAG; 302.105; 600.155; 611.002 Approved no  
  Call Number Admin @ si @ VBM2022 Serial 3770  
Permanent link to this record
 

 
Author Sergi Garcia Bordils; Andres Mafla; Ali Furkan Biten; Oren Nuriel; Aviad Aberdam; Shai Mazor; Ron Litman; Dimosthenis Karatzas edit   pdf
url  doi
openurl 
  Title Out-of-Vocabulary Challenge Report Type Conference Article
  Year 2022 Publication Proceedings European Conference on Computer Vision Workshops Abbreviated Journal  
  Volume (down) 13804 Issue Pages 359–375  
  Keywords  
  Abstract This paper presents final results of the Out-Of-Vocabulary 2022 (OOV) challenge. The OOV contest introduces an important aspect that is not commonly studied by Optical Character Recognition (OCR) models, namely, the recognition of unseen scene text instances at training time. The competition compiles a collection of public scene text datasets comprising of 326,385 images with 4,864,405 scene text instances, thus covering a wide range of data distributions. A new and independent validation and test set is formed with scene text instances that are out of vocabulary at training time. The competition was structured in two tasks, end-to-end and cropped scene text recognition respectively. A thorough analysis of results from baselines and different participants is presented. Interestingly, current state-of-the-art models show a significant performance gap under the newly studied setting. We conclude that the OOV dataset proposed in this challenge will be an essential area to be explored in order to develop scene text models that achieve more robust and generalized predictions.  
  Address Tel-Aviv; Israel; October 2022  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title LNCS  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference ECCVW  
  Notes DAG; 600.155; 302.105; 611.002 Approved no  
  Call Number Admin @ si @ GMB2022 Serial 3771  
Permanent link to this record
 

 
Author Andrea Gemelli; Sanket Biswas; Enrico Civitelli; Josep Llados; Simone Marinai edit   pdf
url  doi
isbn  openurl
  Title Doc2Graph: A Task Agnostic Document Understanding Framework Based on Graph Neural Networks Type Conference Article
  Year 2022 Publication 17th European Conference on Computer Vision Workshops Abbreviated Journal  
  Volume (down) 13804 Issue Pages 329–344  
  Keywords  
  Abstract Geometric Deep Learning has recently attracted significant interest in a wide range of machine learning fields, including document analysis. The application of Graph Neural Networks (GNNs) has become crucial in various document-related tasks since they can unravel important structural patterns, fundamental in key information extraction processes. Previous works in the literature propose task-driven models and do not take into account the full power of graphs. We propose Doc2Graph, a task-agnostic document understanding framework based on a GNN model, to solve different tasks given different types of documents. We evaluated our approach on two challenging datasets for key information extraction in form understanding, invoice layout analysis and table detection.  
  Address  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title LNCS  
  Series Volume Series Issue Edition  
  ISSN ISBN 978-3-031-25068-2 Medium  
  Area Expedition Conference ECCV-TiE  
  Notes DAG; 600.162; 600.140; 110.312 Approved no  
  Call Number Admin @ si @ GBC2022 Serial 3795  
Permanent link to this record
 

 
Author Giuseppe De Gregorio; Sanket Biswas; Mohamed Ali Souibgui; Asma Bensalah; Josep Llados; Alicia Fornes; Angelo Marcelli edit   pdf
doi  openurl
  Title A Few Shot Multi-representation Approach for N-Gram Spotting in Historical Manuscripts Type Conference Article
  Year 2022 Publication Frontiers in Handwriting Recognition. International Conference on Frontiers in Handwriting Recognition (ICFHR2022) Abbreviated Journal  
  Volume (down) 13639 Issue Pages 3-12  
  Keywords N-gram spotting; Few-shot learning; Multimodal understanding; Historical handwritten collections  
  Abstract Despite recent advances in automatic text recognition, the performance remains moderate when it comes to historical manuscripts. This is mainly because of the scarcity of available labelled data to train the data-hungry Handwritten Text Recognition (HTR) models. The Keyword Spotting System (KWS) provides a valid alternative to HTR due to the reduction in error rate, but it is usually limited to a closed reference vocabulary. In this paper, we propose a few-shot learning paradigm for spotting sequences of a few characters (N-gram) that requires a small amount of labelled training data. We exhibit that recognition of important n-grams could reduce the system’s dependency on vocabulary. In this case, an out-of-vocabulary (OOV) word in an input handwritten line image could be a sequence of n-grams that belong to the lexicon. An extensive experimental evaluation of our proposed multi-representation approach was carried out on a subset of Bentham’s historical manuscript collections to obtain some really promising results in this direction.  
  Address December 04 – 07, 2022; Hyderabad, India  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title LNCS  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference ICFHR  
  Notes DAG; 600.121; 600.162; 602.230; 600.140 Approved no  
  Call Number Admin @ si @ GBS2022 Serial 3733  
Permanent link to this record
 

 
Author Arnau Baro; Pau Riba; Alicia Fornes edit  doi
openurl 
  Title Musigraph: Optical Music Recognition Through Object Detection and Graph Neural Network Type Conference Article
  Year 2022 Publication Frontiers in Handwriting Recognition. International Conference on Frontiers in Handwriting Recognition (ICFHR2022) Abbreviated Journal  
  Volume (down) 13639 Issue Pages 171-184  
  Keywords Object detection; Optical music recognition; Graph neural network  
  Abstract During the last decades, the performance of optical music recognition has been increasingly improving. However, and despite the 2-dimensional nature of music notation (e.g. notes have rhythm and pitch), most works treat musical scores as a sequence of symbols in one dimension, which make their recognition still a challenge. Thus, in this work we explore the use of graph neural networks for musical score recognition. First, because graphs are suited for n-dimensional representations, and second, because the combination of graphs with deep learning has shown a great performance in similar applications. Our methodology consists of: First, we will detect each isolated/atomic symbols (those that can not be decomposed in more graphical primitives) and the primitives that form a musical symbol. Then, we will build the graph taking as root node the notehead and as leaves those primitives or symbols that modify the note’s rhythm (stem, beam, flag) or pitch (flat, sharp, natural). Finally, the graph is translated into a human-readable character sequence for a final transcription and evaluation. Our method has been tested on more than five thousand measures, showing promising results.  
  Address December 04 – 07, 2022; Hyderabad, India  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title LNCS  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference ICFHR  
  Notes DAG; 600.162; 600.140; 602.230 Approved no  
  Call Number Admin @ si @ BRF2022b Serial 3740  
Permanent link to this record
 

 
Author Utkarsh Porwal; Alicia Fornes; Faisal Shafait (eds) edit  doi
isbn  openurl
  Title Frontiers in Handwriting Recognition. International Conference on Frontiers in Handwriting Recognition. 18th International Conference, ICFHR 2022 Type Book Whole
  Year 2022 Publication Frontiers in Handwriting Recognition. Abbreviated Journal  
  Volume (down) 13639 Issue Pages  
  Keywords  
  Abstract  
  Address ICFHR 2022, Hyderabad, India, December 4–7, 2022  
  Corporate Author Thesis  
  Publisher Springer Place of Publication Editor Utkarsh Porwal; Alicia Fornes; Faisal Shafait  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title LNCS  
  Series Volume Series Issue Edition  
  ISSN ISBN 978-3-031-21648-0 Medium  
  Area Expedition Conference ICFHR  
  Notes DAG Approved no  
  Call Number Admin @ si @ PFS2022 Serial 3809  
Permanent link to this record
Select All    Deselect All
 |   | 
Details

Save Citations:
Export Records: