Document Analysis and Recognition - Icdar 2021: 16th International Conference, Lausanne, Switzerland, September 5-10, 2021, Proceedings, Part II

ISBN-13: 9783030863302 / Angielski / Miękka / 2021 / 896 str.

Josep Llad?s; Daniel Lopresti; Seiichi Uchida

Spis treści

Document Analysis for Literature Search.- Towards Document Panoptic Segmentation with Pinpoint Accuracy: Method and Evaluation.- A Math Formula Extraction and Evaluation Framework for PDF Documents.- Toward Automatic Interpretation of 3D Plots.- Document Summarization and Translation.- Can Text Summarization Enhance the Headline Stance Detection Task? Benefits and Drawbacks.- The Biased Coin Flip Process for Nonparametric Topic Modeling.-CoMSum and SIBERT: A Dataset and Neural Model for Query-Based Multi-Document Summarization.- RTNet: An End-to-End Method for Handwritten Text Image Translation.- NTable: A Dataset for Camera-based Table Detection.- Multimedia document analysis.- Label Selection Algorithm Based on Boolean Interpolative Decomposition with Sequential Backward Selection for Multi-label Classification.- GSSF: A Generative Sequence Similarity Function based on a Seq2Seq model for clustering online handwritten mathematical answers.- C2VNet: A Deep Learning Framework Towards Comic Strip to Audio-Visual Scene Synthesis.- LSTMVAEF: Vivid Layout via LSTM-based Variational Autoencoder Framework.- Mobile Text Recognition.- HCRNN: A Novel Architecture for Fast Online Handwritten Stroke Classification.- RFDoc: memory efficient local descriptors for ID documents localization and classification.- Dynamic Receptive Field Adaptation for Attention-Based Text Recognition.- Context-Free TextSpotter for Real-Time and Mobile End-to-End Text Detection and Recognition.- MIDV-LAIT: a challenging dataset for recognition of IDs with Perso-Arabic, Thai, and Indian scripts,. Determining optimal frame processing strategies for real-time document recognition systems.- Document Analysis for Social Good.- Embedded Attributes for Cuneiform Sign Spotting.- Date Estimation in the Wild of Scanned Historical Photos: An Image Retrieval Approach.- Two-Step Fine-Tuned Convolutional Neural Networks for Multi-Label Classification of Children's Drawings.- DCINN: Deformable Convolution and Inception Based Neural Network for Tattoo Text Detection through Skin Region.- Sparse Document Analysis using Beta-Liouville Naive Bayes with Vocabulary Knowledge.- Automatic Signature-based Writer Identification in Mixed-script Scenarios.- Indexing and Retrieval of Documents.- Indexing and Retrieval of Documents.- Learning to Rank Words: Optimizing Ranking Metrics for Word Spotting.- A-VLAD: An End-to-End Attention-based Neural Network for Writer Identification in Historical Documents.- Manga-MMTL: multimodal multitask transfer learning for manga character analysis.- Probabilistic Indexing and Search for Hyphenated Words.- Physical and Logical Layout Analysis.- SandSlide: Automatic Slideshow Normalization.- Digital Editions as Distant Supervision for Layout Analysis of Printed Books.- Palmira: A Deep Deformable Network for Instance Segmentation of Dense and Uneven Layouts in Handwritten Manuscripts.- Page Layout Analysis System for Unconstrained Historic Documents.- Improved Graph Methods for Table Layout Understanding.- Unsupervised learning of text line segmentation by differentiating coarse patterns.- Recognition of Tables and Formulas.- Rethinking Table Structure Recognition Using Sequence Labeling Methods.- TabLeX: A Benchmark Dataset for Structure and Content Information Extraction from Scientific Tables.- Handwritten Mathematical Expression Recognition with Bidirectionally Trained Transformer.- TabAug: Data Driven Augmentation for Enhanced Table Structure Recognition.- An Encoder-Decoder Approach to Handwritten Mathematical Expression Recognition with Multi-Head Attention and Stacked Decoder.- Global Context for improving recognition of Online Handwritten Mathematical Expressions.- Image-based Relation Classification Approach for Table Structure Recognition.- Image to LaTeX with Graph Neural Network for Mathematical Formula Recognition.- NLP for Document Understanding.- A Novel Method for Automated Suggestion of Similar Software Incidents using 2-Stage Filtering: Findings on Primary Data.- Research on pseudo-label technology for multi-label news classification.- Information Extraction from Invoices.- Are You Really Complaining? A Multi-task Framework for Complaint Identification, Emotion and Sentiment Classification.- Going Full-TILT Boogie on Document Understanding with Text-Image-Layout Transformer.- Data Centric Domain Adaptation for Historical Text with OCR Errors.- Temporal Ordering of Events via Deep Neural Networks.- Document Collection Visual Question Answering.- Dialogue Act Recognition using Visual Information.- Are End-to-End Systems Really Necessary for NER on Handwritten Document Images?.- Training Bi-Encoders for Word Sense Disambiguation.- DeepCPCFG: Deep Learning and Context Free Grammars for End-to-End Information Extraction.- Consideration of the word’s neighborhood in GATs for information extraction in semi-structured documents.