Related papers: TEXTRON: Weakly Supervised Multilingual Text Detec…

In the past decade, the amount of research being done in the fields of machine learning and deep learning, predominantly in the area of natural language processing (NLP), has risen dramatically. A well-liked method for developing…

Pretraining on large-scale datasets can boost the performance of object detectors while the annotated datasets for object detection are hard to scale up due to the high labor cost. What we possess are numerous isolated filed-specific…

Text detection enables us to extract rich information from images. In this paper, we focus on how to generate bounding boxes that are appropriate to grasp text areas on books to help implement automatic text detection. We attempt not to…

Handwritten word recognition and spotting of low-resource scripts are difficult as sufficient training data is not available and it is often expensive for collecting data of such scripts. This paper presents a novel cross language platform…

Natural Language Processing (NLP) is an important branch of artificial intelligence that studies how to enable computers to understand, process, and generate human language. Text classification is a fundamental task in NLP, which aims to…

Real-world text classification tasks often require many labeled training examples that are expensive to obtain. Recent advancements in machine teaching, specifically the data programming paradigm, facilitate the creation of training data…

Despite the impressive capabilities of Multimodal Large Language Models (MLLMs) in integrating text and image modalities, challenges remain in accurately interpreting detailed visual elements. Vision detection models excel at recognizing…

Text Recognition (TR) refers to the research area that focuses on retrieving textual information from images, a topic that has seen significant advancements in the last decade due to the use of Deep Neural Networks (DNN). However, these…

We propose a method to perform audio event detection under the common constraint that only limited training data are available. In training a deep learning system to perform audio event detection, two practical problems arise. Firstly, most…

Detecting text in natural scenes remains challenging, particularly for diverse scripts and arbitrarily shaped instances where visual cues alone are often insufficient. Existing methods do not fully leverage semantic context. This paper…

India is a multi-lingual country where Roman script is often used alongside different Indic scripts in a text document. To develop a script specific handwritten Optical Character Recognition (OCR) system, it is therefore necessary to…

Despite remarkable progress in text-to-SQL semantic parsing in recent years, the performance of existing parsers is still far from perfect. Specifically, modern text-to-SQL parsers based on deep learning are often over-confident, thus…

Inspired by the success of Deep Learning based approaches to English scene text recognition, we pose and benchmark scene text recognition for three Indic scripts - Devanagari, Telugu and Malayalam. Synthetic word images rendered from…

Visual text, a pivotal element in both document and scene images, speaks volumes and attracts significant attention in the computer vision domain. Beyond visual text detection and recognition, the field of visual text processing has…

This paper proposes a powerful Visual Speech Recognition (VSR) method for multiple languages, especially for low-resource languages that have a limited number of labeled data. Different from previous methods that tried to improve the VSR…

Scene text detection, which is one of the most popular topics in both academia and industry, can achieve remarkable performance with sufficient training data. However, the annotation costs of scene text detection are huge with traditional…

Text classification is a very classic NLP task, but it has two prominent shortcomings: On the one hand, text classification is deeply domain-dependent. That is, a classifier trained on the corpus of one domain may not perform so well in…

Currently, the destruction of the sequence structure in handwritten text has become one of the main bottlenecks restricting the recognition task. The typical situations include additional specific markers (the text swapping modification)…

At present, multi-oriented text detection methods based on deep neural network have achieved promising performances on various benchmarks. Nevertheless, there are still some difficulties for arbitrary shape text detection, especially for a…

Optical character recognition (OCR) systems performance have improved significantly in the deep learning era. This is especially true for handwritten text recognition (HTR), where each author has a unique style, unlike printed text, where…