Related papers: HATFormer: Historic Handwritten Arabic Text Recogn…
Most existing cross-modal retrieval methods employ two-stream encoders with different architectures for images and texts, \textit{e.g.}, CNN for images and RNN/Transformer for texts. Such discrepancy in architectures may induce different…
Handwritten Text Recognition (HTR) is a relevant problem in computer vision, and implies unique challenges owing to its inherent variability and the rich contextualization required for its interpretation. Despite the success of…
The Handwritten Mathematical Expression Recognition (HMER) task is a critical branch in the field of OCR. Recent studies have demonstrated that incorporating bidirectional context information significantly improves the performance of HMER…
Online and offline handwritten Chinese text recognition (HTCR) has been studied for decades. Early methods adopted oversegmentation-based strategies but suffered from low speed, insufficient accuracy, and high cost of character segmentation…
Time-series data are critical in diverse applications, such as industrial monitoring, medical diagnostics, and climate research. However, effectively integrating these high-dimensional temporal signals with natural language for dynamic,…
Handwritten mathematical expression recognition (HMER) is a challenging task that has many potential applications. Recent methods for HMER have achieved outstanding performance with an encoder-decoder architecture. However, these methods…
In this paper, we study the problem of text line recognition. Unlike most approaches targeting specific domains such as scene-text or handwritten documents, we investigate the general problem of developing a universal architecture that can…
Traffic forecasting, which aims to predict traffic conditions based on historical observations, has been an enduring research topic and is widely recognized as an essential component of intelligent transportation. Recent proposals on…
Khmer is a low-resource language characterized by a complex script, presenting significant challenges for optical character recognition (OCR). While document printed text recognition has advanced because of available datasets, performance…
This paper explores the multi-scale aggregation strategy for scene text detection in natural images. We present the Aggregated Text TRansformer(ATTR), which is designed to represent texts in scene images with a multi-scale self-attention…
In this work we propose a hybrid NN/HMM model for online Arabic handwriting recognition. The proposed system is based on Hidden Markov Models (HMMs) and Multi Layer Perceptron Neural Networks (MLPNNs). The input signal is segmented to…
Transformer-based architectures have advanced medical image analysis by effectively modeling long-range dependencies, yet they often struggle in 3D settings due to substantial memory overhead and insufficient capture of fine-grained local…
This study addresses the critical gap in Arabic natural language processing by developing an effective Arabic Reverse Dictionary (RD) system that enables users to find words based on their descriptions or meanings. We present a novel…
Advances in English language representation enabled a more sample-efficient pre-training task by Efficiently Learning an Encoder that Classifies Token Replacements Accurately (ELECTRA). Which, instead of training a model to recover masked…
Encoder-only transformer models remain widely used for discriminative NLP tasks, yet recent architectural advances have largely focused on English. In this work, we present AraModernBERT, an adaptation of the ModernBERT encoder architecture…
In this paper, we propose the Hierarchical Document Transformer (HDT), a novel sparse Transformer architecture tailored for structured hierarchical documents. Such documents are extremely important in numerous domains, including science,…
Our study utilizes deep learning methods for the automated transcription of late nineteenth- and early twentieth-century periodicals written in Arabic script Ottoman Turkish (OT) using the Transkribus platform. We discuss the historical…
State-of-the-art approaches to spelling error correction problem include Transformer-based Seq2Seq models, which require large training sets and suffer from slow inference time; and sequence labeling models based on Transformer encoders…
Contextual Text Block Detection (CTBD) is the task of identifying coherent text blocks within the complexity of natural scenes. Previous methodologies have treated CTBD as either a visual relation extraction challenge within computer vision…
Unpaired image-to-image translation is to translate an image from a source domain to a target domain without paired training data. By utilizing CNN in extracting local semantics, various techniques have been developed to improve the…