Related papers: Training Protocol Matters: Towards Accurate Scene …

Scene text recognition (STR) methods have struggled to attain high accuracy and fast inference speed. Autoregressive (AR)-based models implement the recognition in a character-by-character manner, showing superiority in accuracy but with…

The use of deep learning techniques has exploded during the last few years, resulting in a direct contribution to the field of artificial intelligence. This work aims to be a review of the state-of-the-art in scene recognition with deep…

Due to the enormous technical challenges and wide range of applications, scene text recognition (STR) has been an active research topic in computer vision for years. To tackle this tough problem, numerous innovative methods have been…

Most NeRF-based models are designed for learning the entire scene, and complex scenes can lead to longer learning times and poorer rendering effects. This paper utilizes scene semantic priors to make improvements in fast training, allowing…

Connectionist Temporal Classification (CTC) and attention mechanism are two main approaches used in recent scene text recognition works. Compared with attention-based methods, CTC decoder has a much shorter inference time, yet a lower…

In this paper, we first provide a new perspective to divide existing high performance object detection methods into direct and indirect regressions. Direct regression performs boundary regression by predicting the offsets from a given…

In recent years, end-to-end scene text spotting approaches are evolving to the Transformer-based framework. While previous studies have shown the crucial importance of the intrinsic synergy between text detection and recognition, recent…

The requiring of large amounts of annotated training data has become a common constraint on various deep learning systems. In this paper, we propose a weakly supervised scene text detection method (WeText) that trains robust and accurate…

Deep neural networks (DNN) have achieved remarkable success in various fields, including computer vision and natural language processing. However, training an effective DNN model still poses challenges. This paper aims to propose a method…

Inspired by deep convolution segmentation algorithms, scene text detectors break the performance ceiling of datasets steadily. However, these methods often encounter threshold selection bottlenecks and have poor performance on text…

Many approaches have recently been proposed to detect irregular scene text and achieved promising results. However, their localization results may not well satisfy the following text recognition part mainly because of two reasons: 1)…

In-context learning$\unicode{x2013}$the ability to configure a model's behavior with different prompts$\unicode{x2013}$has revolutionized the field of natural language processing, alleviating the need for task-specific models and paving the…

Modern pattern recognition tasks use complex algorithms that take advantage of large datasets to make more accurate predictions than traditional algorithms such as decision trees or k-nearest-neighbor better suited to describe simple…

This paper presents a scene text detection technique that exploits bootstrapping and text border semantics for accurate localization of texts in scenes. A novel bootstrapping technique is designed which samples multiple 'subsections' of a…

We exploit the potential of the large-scale Contrastive Language-Image Pretraining (CLIP) model to enhance scene text detection and spotting tasks, transforming it into a robust backbone, FastTCM-CR50. This backbone utilizes visual prompt…

Object detection is a fundamental task for robots to operate in unstructured environments. Today, there are several deep learning algorithms that solve this task with remarkable performance. Unfortunately, training such systems requires…

The technological advancement and sophistication in cameras and gadgets prompt researchers to have focus on image analysis and text understanding. The deep learning techniques demonstrated well to assess the potential for classifying text…

Until recently, the number of public real-world text images was insufficient for training scene text recognizers. Therefore, most modern training methods rely on synthetic data and operate in a fully supervised manner. Nevertheless, the…

Scene text recognition (STR) is the task of recognizing character sequences in natural scenes. While there have been great advances in STR methods, current methods still fail to recognize texts in arbitrary shapes, such as heavily curved or…

Many scene text recognition approaches are based on purely visual information and ignore the semantic relation between scene and text. In this paper, we tackle this problem from natural language processing perspective to fill the gap…