非决定性
发表于 2025-3-21 16:54:45
书目名称Document Analysis and Recognition - ICDAR 2023影响因子(影响力)<br> http://figure.impactfactor.cn/if/?ISSN=BK0282306<br><br> <br><br>书目名称Document Analysis and Recognition - ICDAR 2023影响因子(影响力)学科排名<br> http://figure.impactfactor.cn/ifr/?ISSN=BK0282306<br><br> <br><br>书目名称Document Analysis and Recognition - ICDAR 2023网络公开度<br> http://figure.impactfactor.cn/at/?ISSN=BK0282306<br><br> <br><br>书目名称Document Analysis and Recognition - ICDAR 2023网络公开度学科排名<br> http://figure.impactfactor.cn/atr/?ISSN=BK0282306<br><br> <br><br>书目名称Document Analysis and Recognition - ICDAR 2023被引频次<br> http://figure.impactfactor.cn/tc/?ISSN=BK0282306<br><br> <br><br>书目名称Document Analysis and Recognition - ICDAR 2023被引频次学科排名<br> http://figure.impactfactor.cn/tcr/?ISSN=BK0282306<br><br> <br><br>书目名称Document Analysis and Recognition - ICDAR 2023年度引用<br> http://figure.impactfactor.cn/ii/?ISSN=BK0282306<br><br> <br><br>书目名称Document Analysis and Recognition - ICDAR 2023年度引用学科排名<br> http://figure.impactfactor.cn/iir/?ISSN=BK0282306<br><br> <br><br>书目名称Document Analysis and Recognition - ICDAR 2023读者反馈<br> http://figure.impactfactor.cn/5y/?ISSN=BK0282306<br><br> <br><br>书目名称Document Analysis and Recognition - ICDAR 2023读者反馈学科排名<br> http://figure.impactfactor.cn/5yr/?ISSN=BK0282306<br><br> <br><br>
休息
发表于 2025-3-21 22:24:10
An End-to-End Local Attention Based Model for Table Recognitiony powerful for table recognition. However, Transformer-based models usually struggle to process big tables due to the limitation of their global attention mechanism. In this paper, we propose a local attention mechanism to address the limitation of the global attention mechanism. We also present an
圣人
发表于 2025-3-22 00:43:51
Optimized Table Tokenization for Table Structure Recognitione-structure can be recognized with impressive accuracy using Image-to-Markup-Sequence (Im2Seq) approaches. Taking only the image of a table, such models predict a sequence of tokens (e.g. in HTML, LaTeX) which represent the structure of the table. Since the token representation of the table structur
ALE
发表于 2025-3-22 06:18:54
Towards End-to-End Semi-Supervised Table Detection with Deformable Transformerwe observe remarkable success in table detection. However, a significant amount of labeled data is required to train these models effectively. Many semi-supervised approaches are introduced to mitigate the need for a substantial amount of label data. These approaches use CNN-based detectors that rel
laxative
发表于 2025-3-22 12:43:47
SpaDen: Sparse and Dense Keypoint Estimation for Real-World Chart Understanding (KP), which are used to reconstruct the components within the plot area. Our novelty lies in detecting a fusion of continuous and discrete KP as predicted heatmaps. A combination of sparse and dense per-pixel objectives coupled with a uni-modal self-attention-based feature-fusion layer is applied t
羊齿
发表于 2025-3-22 16:40:42
Generalization of Fine Granular Extractions from ChartsAnnotating a dataset and retraining for every new chart type with a shift in the spatial composition of chart elements, text role regions, legend preview styles, chart element shapes and text-role definitions, is a time-consuming and costly affair. Current approaches struggle to generalize to new ch
羊齿
发表于 2025-3-22 20:56:38
http://reply.papertrans.cn/29/2824/282306/282306_7.png
表否定
发表于 2025-3-22 23:16:13
Language Independent Neuro-Symbolic Semantic Parsing for Form Understandingpre-training. In contrast, humans can usually identify key-value pairings from a form only by looking at layouts, even if they don’t comprehend the language used. No prior research has been conducted to investigate how helpful layout information alone is for form understanding. Hence, we propose a u
EXALT
发表于 2025-3-23 04:23:50
DocILE Benchmark for Document Information Localization and Extractions 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 granularit
wreathe
发表于 2025-3-23 08:14:16
Robustness Evaluation of Transformer-Based Form Field Extractors via Form Attacksm transformations to evaluate the vulnerability of the state-of-the-art field extractors against form attacks from both OCR level and form level, including OCR location/order rearrangement, form background manipulation and form field-value augmentation. We conduct robustness evaluation using real in