Search Results for author:
Found 17 papers, 5 papers with code
Sequence-to-Label Script Identification for Multilingual OCR
Therefore we reframe line script identification as a sequence-to-label problem and solve it using two components, trained end-toend: Encoder and Summarizer.
A Scalable Handwritten Text Recognition System
These constitute a solution to bring HTR capability into a large scale OCR system.
Towards Unconstrained End-to-End Text Spotting
We propose an end-to-end trainable network that can simultaneously detect and recognize text of arbitrary shape, making substantial progress on the open problem of reading scene text of irregular shape.
Instance Segmentation
Optical Character Recognition (OCR)
+3
Post-OCR Paragraph Recognition by Graph Convolutional Networks
We propose a new approach for paragraph recognition in document images by spatial graph convolutional networks (GCN) applied on OCR text boxes.
Rethinking Text Line Recognition Models
Unlike the more common Transformer-based models, this architecture can handle inputs of arbitrary length, a requirement for universal line recognition.
Ranked #2 on
Handwritten Text Recognition
on IAM
(using extra training data)
ROPE: Reading Order Equivariant Positional Encoding for Graph-based Document Information Extraction
Natural reading orders of words are crucial for information extraction from form-like documents.
FormNet: Structural Encoding beyond Sequential Modeling in Form Document Information Extraction
Sequence modeling has demonstrated state-of-the-art performance on natural language and document understanding tasks.
Unified Line and Paragraph Detection by Graph Convolutional Networks
We formulate the task of detecting lines and paragraphs in a document into a unified two-level clustering problem.
Towards End-to-End Unified Scene Text Detection and Layout Analysis
In this paper, we bring them together and introduce the task of unified scene text detection and layout analysis.
Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes
Third, we reduce both the model size and the amount of data required to outperform LLMs; our finetuned 770M T5 model outperforms the few-shot prompted 540B PaLM model using only 80% of available data on a benchmark, whereas standard finetuning the same T5 model struggles to match even by using 100% of the dataset.
Text Reading Order in Uncontrolled Conditions by Sparse Graph Segmentation
Text reading order is a crucial aspect in the output of an OCR engine, with a large impact on downstream tasks.
FormNetV2: Multimodal Graph Contrastive Learning for Form Document Information Extraction
In FormNetV2, we introduce a centralized multimodal graph contrastive learning strategy to unify self-supervised pre-training for all modalities in one loss.
ICDAR 2023 Competition on Hierarchical Text Detection and Recognition
We organize a competition on hierarchical text detection and recognition.
Tool Documentation Enables Zero-Shot Tool-Usage with Large Language Models
Today, large language models (LLMs) are taught to use new tools by providing a few demonstrations of the tool's usage.
OCR Language Models with Custom Vocabularies
Language models are useful adjuncts to optical models for producing accurate optical character recognition (OCR) results.
Hierarchical Text Spotter for Joint Text Spotting and Layout Analysis
We propose Hierarchical Text Spotter (HTS), a novel method for the joint task of word-level text spotting and geometric layout analysis.
Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding
We propose the Chain-of-Table framework, where tabular data is explicitly used in the reasoning chain as a proxy for intermediate thoughts.
Ranked #3 on
Table-based Fact Verification
on TabFact
