toggle visibility Search & Display Options

Select All    Deselect All
 |   | 
Details
  Records Links
Author Soumya Jahagirdar; Minesh Mathew; Dimosthenis Karatzas; CV Jawahar edit   pdf
url  openurl
  Title Watching the News: Towards VideoQA Models that can Read Type Conference Article
  Year (down) 2023 Publication Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract Video Question Answering methods focus on commonsense reasoning and visual cognition of objects or persons and their interactions over time. Current VideoQA approaches ignore the textual information present in the video. Instead, we argue that textual information is complementary to the action and provides essential contextualisation cues to the reasoning process. To this end, we propose a novel VideoQA task that requires reading and understanding the text in the video. To explore this direction, we focus on news videos and require QA systems to comprehend and answer questions about the topics presented by combining visual and textual cues in the video. We introduce the ``NewsVideoQA'' dataset that comprises more than 8,600 QA pairs on 3,000+ news videos obtained from diverse news channels from around the world. We demonstrate the limitations of current Scene Text VQA and VideoQA methods and propose ways to incorporate scene text information into VideoQA methods.  
  Address Waikoloa; Hawai; USA; January 2023  
  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 WACV  
  Notes DAG Approved no  
  Call Number Admin @ si @ JMK2023 Serial 3899  
Permanent link to this record
 

 
Author Stepan Simsa; Milan Sulc; Michal Uricar; Yash Patel; Ahmed Hamdi; Matej Kocian; Matyas Skalicky; Jiri Matas; Antoine Doucet; Mickael Coustaty; Dimosthenis Karatzas edit   pdf
url  openurl
  Title DocILE Benchmark for Document Information Localization and Extraction Type Conference Article
  Year (down) 2023 Publication 17th International Conference on Document Analysis and Recognition Abbreviated Journal  
  Volume 14188 Issue Pages 147–166  
  Keywords Document AI; Information Extraction; Line Item Recognition; Business Documents; Intelligent Document Processing  
  Abstract This paper introduces the DocILE benchmark with the largest dataset of business documents for the tasks of Key Information Localization and Extraction and Line Item Recognition. It contains 6.7k annotated business documents, 100k synthetically generated documents, and nearly 1M unlabeled documents for unsupervised pre-training. The dataset has been built with knowledge of domain- and task-specific aspects, resulting in the following key features: (i) annotations in 55 classes, which surpasses the granularity of previously published key information extraction datasets by a large margin; (ii) Line Item Recognition represents a highly practical information extraction task, where key information has to be assigned to items in a table; (iii) documents come from numerous layouts and the test set includes zero- and few-shot cases as well as layouts commonly seen in the training set. The benchmark comes with several baselines, including RoBERTa, LayoutLMv3 and DETR-based Table Transformer; applied to both tasks of the DocILE benchmark, with results shared in this paper, offering a quick starting point for future work. The dataset, baselines and supplementary material are available at https://github.com/rossumai/docile.  
  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 @ SSU2023 Serial 3903  
Permanent link to this record
 

 
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 (down) 2023 Publication 17th International Conference on Document Analysis and Recognition Abbreviated Journal  
  Volume 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 George Tom; Minesh Mathew; Sergi Garcia Bordils; Dimosthenis Karatzas; CV Jawahar edit  url
openurl 
  Title Reading Between the Lanes: Text VideoQA on the Road Type Conference Article
  Year (down) 2023 Publication 17th International Conference on Document Analysis and Recognition Abbreviated Journal  
  Volume 14192 Issue Pages 137–154  
  Keywords VideoQA; scene text; driving videos  
  Abstract Text and signs around roads provide crucial information for drivers, vital for safe navigation and situational awareness. Scene text recognition in motion is a challenging problem, while textual cues typically appear for a short time span, and early detection at a distance is necessary. Systems that exploit such information to assist the driver should not only extract and incorporate visual and textual cues from the video stream but also reason over time. To address this issue, we introduce RoadTextVQA, a new dataset for the task of video question answering (VideoQA) in the context of driver assistance. RoadTextVQA consists of 3, 222 driving videos collected from multiple countries, annotated with 10, 500 questions, all based on text or road signs present in the driving videos. We assess the performance of state-of-the-art video question answering models on our RoadTextVQA dataset, highlighting the significant potential for improvement in this domain and the usefulness of the dataset in advancing research on in-vehicle support systems and text-aware multimodal question answering. The dataset is available at http://cvit.iiit.ac.in/research/projects/cvit-projects/roadtextvqa.  
  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 3906  
Permanent link to this record
 

 
Author Sergi Garcia Bordils; Dimosthenis Karatzas; Marçal Rusiñol edit  url
openurl 
  Title Accelerating Transformer-Based Scene Text Detection and Recognition via Token Pruning Type Conference Article
  Year (down) 2023 Publication 17th International Conference on Document Analysis and Recognition Abbreviated Journal  
  Volume 14192 Issue Pages 106-121  
  Keywords Scene Text Detection; Scene Text Recognition; Transformer Acceleration  
  Abstract Scene text detection and recognition is a crucial task in computer vision with numerous real-world applications. Transformer-based approaches are behind all current state-of-the-art models and have achieved excellent performance. However, the computational requirements of the transformer architecture makes training these methods slow and resource heavy. In this paper, we introduce a new token pruning strategy that significantly decreases training and inference times without sacrificing performance, striking a balance between accuracy and speed. We have applied this pruning technique to our own end-to-end transformer-based scene text understanding architecture. Our method uses a separate detection branch to guide the pruning of uninformative image features, which significantly reduces the number of tokens at the input of the transformer. Experimental results show how our network is able to obtain competitive results on multiple public benchmarks while running at significantly higher speeds.  
  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 @ GKR2023a Serial 3907  
Permanent link to this record
 

 
Author Adarsh Tiwari; Sanket Biswas; Josep Llados edit  url
openurl 
  Title Can Pre-trained Language Models Help in Understanding Handwritten Symbols? Type Conference Article
  Year (down) 2023 Publication 17th International Conference on Document Analysis and Recognition Abbreviated Journal  
  Volume 14193 Issue Pages 199–211  
  Keywords  
  Abstract The emergence of transformer models like BERT, GPT-2, GPT-3, RoBERTa, T5 for natural language understanding tasks has opened the floodgates towards solving a wide array of machine learning tasks in other modalities like images, audio, music, sketches and so on. These language models are domain-agnostic and as a result could be applied to 1-D sequences of any kind. However, the key challenge lies in bridging the modality gap so that they could generate strong features beneficial for out-of-domain tasks. This work focuses on leveraging the power of such pre-trained language models and discusses the challenges in predicting challenging handwritten symbols and alphabets.  
  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  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference ICDAR  
  Notes DAG Approved no  
  Call Number Admin @ si @ TBL2023 Serial 3908  
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 (down) 2023 Publication International Conference of the Cross-Language Evaluation Forum for European Languages Abbreviated Journal  
  Volume 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 Soumya Jahagirdar; Minesh Mathew; Dimosthenis Karatzas; CV Jawahar edit   pdf
url  openurl
  Title Understanding Video Scenes Through Text: Insights from Text-Based Video Question Answering Type Conference Article
  Year (down) 2023 Publication Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract Researchers have extensively studied the field of vision and language, discovering that both visual and textual content is crucial for understanding scenes effectively. Particularly, comprehending text in videos holds great significance, requiring both scene text understanding and temporal reasoning. This paper focuses on exploring two recently introduced datasets, NewsVideoQA and M4-ViteVQA, which aim to address video question answering based on textual content. The NewsVideoQA dataset contains question-answer pairs related to the text in news videos, while M4- ViteVQA comprises question-answer pairs from diverse categories like vlogging, traveling, and shopping. We provide an analysis of the formulation of these datasets on various levels, exploring the degree of visual understanding and multi-frame comprehension required for answering the questions. Additionally, the study includes experimentation with BERT-QA, a text-only model, which demonstrates comparable performance to the original methods on both datasets, indicating the shortcomings in the formulation of these datasets. Furthermore, we also look into the domain adaptation aspect by examining the effectiveness of training on M4-ViteVQA and evaluating on NewsVideoQA and vice-versa, thereby shedding light on the challenges and potential benefits of out-of-domain training.  
  Address Paris; France; October 2023  
  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 ICCVW  
  Notes DAG Approved no  
  Call Number Admin @ si @ JMK2023 Serial 3946  
Permanent link to this record
 

 
Author Jordy Van Landeghem; Ruben Tito; Lukasz Borchmann; Michal Pietruszka; Pawel Joziak; Rafal Powalski; Dawid Jurkiewicz; Mickael Coustaty; Bertrand Anckaert; Ernest Valveny; Matthew Blaschko; Sien Moens; Tomasz Stanislawek edit   pdf
url  openurl
  Title Document Understanding Dataset and Evaluation (DUDE) Type Conference Article
  Year (down) 2023 Publication 20th IEEE International Conference on Computer Vision Abbreviated Journal  
  Volume Issue Pages 19528-19540  
  Keywords  
  Abstract We call on the Document AI (DocAI) community to re-evaluate current methodologies and embrace the challenge of creating more practically-oriented benchmarks. Document Understanding Dataset and Evaluation (DUDE) seeks to remediate the halted research progress in understanding visually-rich documents (VRDs). We present a new dataset with novelties related to types of questions, answers, and document layouts based on multi-industry, multi-domain, and multi-page VRDs of various origins and dates. Moreover, we are pushing the boundaries of current methods by creating multi-task and multi-domain evaluation setups that more accurately simulate real-world situations where powerful generalization and adaptation under low-resource settings are desired. DUDE aims to set a new standard as a more practical, long-standing benchmark for the community, and we hope that it will lead to future extensions and contributions that address real-world challenges. Finally, our work illustrates the importance of finding more efficient ways to model language, images, and layout in DocAI.  
  Address Paris; France; October 2023  
  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 ICCV  
  Notes DAG Approved no  
  Call Number Admin @ si @ LTB2023 Serial 3948  
Permanent link to this record
 

 
Author Ruben Perez Tito edit  isbn
openurl 
  Title Exploring the role of Text in Visual Question Answering on Natural Scenes and Documents Type Book Whole
  Year (down) 2023 Publication PhD Thesis, Universitat Autonoma de Barcelona-CVC Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract Visual Question Answering (VQA) is the task where given an image and a natural language question, the objective is to generate a natural language answer. At the intersection between computer vision and natural language processing, this task can be seen as a measure of image understanding capabilities, as it requires to reason about objects, actions, colors, positions, the relations between the different elements as well as commonsense reasoning, world knowledge, arithmetic skills and natural language understanding. However, even though the text present in the images conveys important semantically rich information that is explicit and not available in any other form, most VQA methods remained illiterate, largely
ignoring the text despite its potential significance. In this thesis, we set out on a journey to bring reading capabilities to computer vision models applied to the VQA task, creating new datasets and methods that can read, reason and integrate the text with other visual cues in natural scene images and documents.
In Chapter 3, we address the combination of scene text with visual information to fully understand all the nuances of natural scene images. To achieve this objective, we define a new sub-task of VQA that requires reading the text in the image, and highlight the limitations of the current methods. In addition, we propose a new architecture that integrates both modalities and jointly reasons about textual and visual features. In Chapter 5, we shift the domain of VQA with reading capabilities and apply it on scanned industry document images, providing a high-level end-purpose perspective to Document Understanding, which has been
primarily focused on digitizing the document’s contents and extracting key values without considering the ultimate purpose of the extracted information. For this, we create a dataset which requires methods to reason about the unique and challenging elements of documents, such as text, images, tables, graphs and complex layouts, to provide accurate answers in natural language. However, we observed that explicit visual features provide a slight contribution in the overall performance, since the main information is usually conveyed within the text and its position. In consequence, in Chapter 6, we propose VQA on infographic images, seeking for document images with more visually rich elements that require to fully exploit visual information in order to answer the questions. We show the performance gap of
different methods when used over industry scanned and infographic images, and propose a new method that integrates the visual features in early stages, which allows the transformer architecture to exploit the visual features during the self-attention operation. Instead, in Chapter 7, we apply VQA on a big collection of single-page documents, where the methods must find which documents are relevant to answer the question, and provide the answer itself. Finally, in Chapter 8, mimicking real-world application problems where systems must process documents with multiple pages, we address the multipage document visual question answering task. We demonstrate the limitations of existing methods, including models specifically designed to process long sequences. To overcome these limitations, we propose
a hierarchical architecture that can process long documents, answer questions, and provide the index of the page where the information to answer the question is located as an explainability measure.
 
  Address  
  Corporate Author Thesis Ph.D. thesis  
  Publisher IMPRIMA Place of Publication Editor Ernest Valveny  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN 978-84-124793-5-5 Medium  
  Area Expedition Conference  
  Notes DAG Approved no  
  Call Number Admin @ si @ Per2023 Serial 3967  
Permanent link to this record
Select All    Deselect All
 |   | 
Details

Save Citations:
Export Records: