toggle visibility Search & Display Options
Select All    Deselect All << 1 2 3 4 5 6 7 8 9 10 >> [11–20]
List View
 | 
Citations
 | 
Details
  Records Links
Author Ruben Tito; Dimosthenis Karatzas; Ernest Valveny edit   pdf
url  openurl
  Title Hierarchical multimodal transformers for Multipage DocVQA Type Miscellaneous
  Year (down) 2023 Publication arxiv Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract  
  Address  
  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  
  Notes DAG Approved no  
  Call Number Admin @ si @ TKV2023 Serial 3836  
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 Souhail Bakkali; Sanket Biswas; Zuheng Ming; Mickael Coustaty; Marçal Rusiñol; Oriol Ramos Terrades; Josep Llados edit   pdf
url  openurl
  Title TransferDoc: A Self-Supervised Transferable Document Representation Learning Model Unifying Vision and Language Type Miscellaneous
  Year (down) 2023 Publication Arxiv Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract The field of visual document understanding has witnessed a rapid growth in emerging challenges and powerful multi-modal strategies. However, they rely on an extensive amount of document data to learn their pretext objectives in a ``pre-train-then-fine-tune'' paradigm and thus, suffer a significant performance drop in real-world online industrial settings. One major reason is the over-reliance on OCR engines to extract local positional information within a document page. Therefore, this hinders the model's generalizability, flexibility and robustness due to the lack of capturing global information within a document image. We introduce TransferDoc, a cross-modal transformer-based architecture pre-trained in a self-supervised fashion using three novel pretext objectives. TransferDoc learns richer semantic concepts by unifying language and visual representations, which enables the production of more transferable models. Besides, two novel downstream tasks have been introduced for a ``closer-to-real'' industrial evaluation scenario where TransferDoc outperforms other state-of-the-art approaches.  
  Address  
  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  
  Notes DAG Approved no  
  Call Number Admin @ si @ BBM2023 Serial 3995  
Permanent link to this record
 
 
Author Souhail Bakkali; Zuheng Ming; Mickael Coustaty; Marçal Rusiñol; Oriol Ramos Terrades edit   pdf
doi  openurl
  Title VLCDoC: Vision-Language Contrastive Pre-Training Model for Cross-Modal Document Classification Type Journal Article
  Year (down) 2023 Publication Pattern Recognition Abbreviated Journal PR  
  Volume 139 Issue Pages 109419  
  Keywords  
  Abstract Multimodal learning from document data has achieved great success lately as it allows to pre-train semantically meaningful features as a prior into a learnable downstream approach. In this paper, we approach the document classification problem by learning cross-modal representations through language and vision cues, considering intra- and inter-modality relationships. Instead of merging features from different modalities into a common representation space, the proposed method exploits high-level interactions and learns relevant semantic information from effective attention flows within and across modalities. The proposed learning objective is devised between intra- and inter-modality alignment tasks, where the similarity distribution per task is computed by contracting positive sample pairs while simultaneously contrasting negative ones in the common feature representation space}. Extensive experiments on public document classification datasets demonstrate the effectiveness and the generalization capacity of our model on both low-scale and large-scale datasets.  
  Address  
  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 ISSN 0031-3203 ISBN Medium  
  Area Expedition Conference  
  Notes DAG; 600.140; 600.121 Approved no  
  Call Number Admin @ si @ BMC2023 Serial 3826  
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 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; 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 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 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 (down) 2023 Publication 17th International Conference on Doccument Analysis and Recognition Abbreviated Journal  
  Volume 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 Weijia Wu; Yuzhong Zhao; Zhuang Li; Jiahong Li; Mike Zheng Shou; Umapada Pal; Dimosthenis Karatzas; Xiang Bai edit   pdf
url  openurl
  Title ICDAR 2023 Competition on Video Text Reading for Dense and Small Text Type Conference Article
  Year (down) 2023 Publication 17th International Conference on Document Analysis and Recognition Abbreviated Journal  
  Volume 14188 Issue Pages 405–419  
  Keywords Video Text Spotting; Small Text; Text Tracking; Dense Text  
  Abstract Recently, video text detection, tracking and recognition in natural scenes are becoming very popular in the computer vision community. However, most existing algorithms and benchmarks focus on common text cases (e.g., normal size, density) and single scenario, while ignore extreme video texts challenges, i.e., dense and small text in various scenarios. In this competition report, we establish a video text reading benchmark, named DSText, which focuses on dense and small text reading challenge in the video with various scenarios. Compared with the previous datasets, the proposed dataset mainly include three new challenges: 1) Dense video texts, new challenge for video text spotter. 2) High-proportioned small texts. 3) Various new scenarios, e.g., ‘Game’, ‘Sports’, etc. The proposed DSText includes 100 video clips from 12 open scenarios, supporting two tasks (i.e., video text tracking (Task 1) and end-to-end video text spotting (Task2)). During the competition period (opened on 15th February, 2023 and closed on 20th March, 2023), a total of 24 teams participated in the three proposed tasks with around 30 valid submissions, respectively. In this article, we describe detailed statistical information of the dataset, tasks, evaluation protocols and the results summaries of the ICDAR 2023 on DSText competition. Moreover, we hope the benchmark will promise the video text research in the community.  
  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 @ WZL2023 Serial 3898  
Permanent link to this record
Select All    Deselect All << 1 2 3 4 5 6 7 8 9 10 >> [11–20]
List View
 | 
Citations
 | 
Details
toggle visibility
Save Citations:
Export Records: