Related papers: A tailored Handwritten-Text-Recognition System for…
Video-text retrieval (VTR) is an attractive yet challenging task for multi-modal understanding, which aims to search for relevant video (text) given a query (video). Existing methods typically employ completely heterogeneous visual-textual…
As large language models (LLMs) are trained on increasingly diverse and extensive multilingual corpora, they demonstrate cross-lingual transfer capabilities. However, these capabilities often fail to effectively extend to low-resource…
Existing methods enhance open-vocabulary object detection by leveraging the robust open-vocabulary recognition capabilities of Vision-Language Models (VLMs), such as CLIP.However, two main challenges emerge:(1) A deficiency in concept…
In this paper, we approach the problem of segmentation-free query-by-string word spotting for handwritten documents. In other words, we use methods inspired from computer vision and machine learning to search for words in large collections…
In recent years, deep learning techniques have been used to develop sign language recognition systems, potentially serving as a communication tool for millions of hearing-impaired individuals worldwide. However, there are inherent…
Despite Bengali being the sixth most spoken language in the world, handwritten text recognition (HTR) systems for Bengali remain severely underdeveloped. The complexity of Bengali script--featuring conjuncts, diacritics, and highly variable…
Offline handwritten text recognition from images is an important problem for enterprises attempting to digitize large volumes of handmarked scanned documents/reports. Deep recurrent models such as Multi-dimensional LSTMs have been shown to…
Purpose: Our research project focuses on improving the content update of the online European Smart Tourism Tools (STTs) Observatory by incorporating and categorizing STTs. The categorization is based on their taxonomy, and it facilitates…
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…
Handwritten mathematical expression recognition (HMER) is an important research direction in handwriting recognition. The performance of HMER suffers from the two-dimensional structure of mathematical expressions (MEs). To address this…
Seals are small coin-shaped artifacts, mostly made of lead, held with strings to seal letters. This work presents the first attempt towards automatic reading of text on Byzantine seal images.Byzantine seals are generally decorated with…
The massive scale and growth of textual biomedical data have made its indexing and classification increasingly important. However, existing research on this topic mainly utilized convolutional and recurrent neural networks, which generally…
Arabic handwriting is a consonantal and cursive writing. The analysis of Arabic script is further complicated due to obligatory dots/strokes that are placed above or below most letters and usually written delayed in order. Due to…
This article summarizes some mostly unsuccessful attempts to understand authorial style by examining the attention of various neural networks (LSTMs and CNNs) trained on a corpus of classical Latin verse that has been encoded to include…
Arabic Optical Character Recognition (OCR) and Handwriting Recognition (HWR) pose unique challenges due to the cursive and context-sensitive nature of the Arabic script. This study introduces Qalam, a novel foundation model designed for…
Handwritten Text Recognition remains challenging due to the limited data, high writing style variance, and scripts with complex diacritics. Existing approaches, though partially address these issues, often struggle to generalize without…
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…
Language Models (LMs) such as BERT, have been shown to perform well on the task of identifying Named Entities (NE) in text. A BERT LM is typically used as a classifier to classify individual tokens in the input text, or to classify spans of…
Historic variations of spelling poses a challenge for full-text search or natural language processing on historical digitized texts. To minimize the gap between the historic orthography and contemporary spelling, usually an automatic…
Manual digitisation of structured handwritten documents is slow and costly. We benchmark 17 leading frontier multi-modal large language models and open-source models against a very challenging real-world medical form that mixes dates;…