ICDAR Workshops最新文献

A Survey and Approach to Chart Classification 海图分类的综述与方法

ICDAR Workshops Pub Date : 2023-07-09 DOI: 10.48550/arXiv.2307.04147

Anurag Dhote, M. Javed, D. Doermann

引用次数: 0

Absformer: Transformer-based Model for Unsupervised Multi-Document Abstractive Summarization 基于变压器的无监督多文档抽象摘要模型

ICDAR Workshops Pub Date : 2023-06-07 DOI: 10.48550/arXiv.2306.04787

M. Trabelsi, H. Uzunalioglu

{"title":"Absformer: Transformer-based Model for Unsupervised Multi-Document Abstractive Summarization","authors":"M. Trabelsi, H. Uzunalioglu","doi":"10.48550/arXiv.2306.04787","DOIUrl":"https://doi.org/10.48550/arXiv.2306.04787","url":null,"abstract":"Multi-document summarization (MDS) refers to the task of summarizing the text in multiple documents into a concise summary. The generated summary can save the time of reading many documents by providing the important content in the form of a few sentences. Abstractive MDS aims to generate a coherent and fluent summary for multiple documents using natural language generation techniques. In this paper, we consider the unsupervised abstractive MDS setting where there are only documents with no groundtruh summaries provided, and we propose Absformer, a new Transformer-based method for unsupervised abstractive summary generation. Our method consists of a first step where we pretrain a Transformer-based encoder using the masked language modeling (MLM) objective as the pretraining task in order to cluster the documents into semantically similar groups; and a second step where we train a Transformer-based decoder to generate abstractive summaries for the clusters of documents. To our knowledge, we are the first to successfully incorporate a Transformer-based model to solve the unsupervised abstractive MDS task. We evaluate our approach using three real-world datasets from different domains, and we demonstrate both substantial improvements in terms of evaluation metrics over state-of-the-art abstractive-based methods, and generalization to datasets from different domains.","PeriodicalId":290651,"journal":{"name":"ICDAR Workshops","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125489617","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

BN-DRISHTI: Bangla Document Recognition through Instance-level Segmentation of Handwritten Text Images 手写体文本图像实例级分割的孟加拉语文档识别

ICDAR Workshops Pub Date : 2023-05-31 DOI: 10.48550/arXiv.2306.09351

Sheikh Mohammad Jubaer, Nazifa Tabassum, Md. Ataur Rahman, M. K. Islam

{"title":"BN-DRISHTI: Bangla Document Recognition through Instance-level Segmentation of Handwritten Text Images","authors":"Sheikh Mohammad Jubaer, Nazifa Tabassum, Md. Ataur Rahman, M. K. Islam","doi":"10.48550/arXiv.2306.09351","DOIUrl":"https://doi.org/10.48550/arXiv.2306.09351","url":null,"abstract":"Handwriting recognition remains challenging for some of the most spoken languages, like Bangla, due to the complexity of line and word segmentation brought by the curvilinear nature of writing and lack of quality datasets. This paper solves the segmentation problem by introducing a state-of-the-art method (BN-DRISHTI) that combines a deep learning-based object detection framework (YOLO) with Hough and Affine transformation for skew correction. However, training deep learning models requires a massive amount of data. Thus, we also present an extended version of the BN-HTRd dataset comprising 786 full-page handwritten Bangla document images, line and word-level annotation for segmentation, and corresponding ground truths for word recognition. Evaluation on the test portion of our dataset resulted in an F-score of 99.97% for line and 98% for word segmentation. For comparative analysis, we used three external Bangla handwritten datasets, namely BanglaWriting, WBSUBNdb_text, and ICDAR 2013, where our system outperformed by a significant margin, further justifying the performance of our approach on completely unseen samples.","PeriodicalId":290651,"journal":{"name":"ICDAR Workshops","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117206967","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Comprehensive Handwritten Paragraph Text Recognition System: LexiconNet 一个全面的手写段落文本识别系统:LexiconNet

ICDAR Workshops Pub Date : 2022-05-23 DOI: 10.1007/978-3-031-41501-2_16

Lalita Kumari, Sukhdeep Singh, V. Rathore, Anuj Sharma

引用次数: 2

Reconstruction of Power Lines from Point Clouds 从点云重建电力线

ICDAR Workshops Pub Date : 2022-01-29 DOI: 10.1007/978-3-031-41498-5_8

A. Gribov, Khalid Duri

引用次数: 0

Towards Boosting the Accuracy of Non-latin Scene Text Recognition 提高非拉丁场景文本识别准确率的研究

ICDAR Workshops Pub Date : 2022-01-10 DOI: 10.1007/978-3-030-86198-8_20

Sanjana Gunna, Rohit Saluja, C. V. Jawahar