Related papers: Boosting Semi-Supervised Scene Text Recognition vi…

Data simulation engines like Unity are becoming an increasingly important data source that allows us to acquire ground truth labels conveniently. Moreover, we can flexibly edit the content of an image in the engine, such as objects…

We present a contrasting learning approach with data augmentation techniques to learn document representations in an unsupervised manner. Inspired by recent contrastive self-supervised learning algorithms used for image and NLP pretraining,…

Inspired by the great success of language model (LM)-based pre-training, recent studies in visual document understanding have explored LM-based pre-training methods for modeling text within document images. Among them, pre-training that…

Despite the recent remarkable improvements in scene text recognition (STR), the majority of the studies focused mainly on the English language, which only includes few number of characters. However, STR models show a large performance…

Many new proposals for scene text recognition (STR) models have been introduced in recent years. While each claim to have pushed the boundary of the technology, a holistic and fair comparison has been largely missing in the field due to the…

Deep learning-based scene text detection can achieve preferable performance, powered with sufficient labeled training data. However, manual labeling is time consuming and laborious. At the extreme, the corresponding annotated data are…

Recently, self-supervised representation learning gives further development in multimedia technology. Most existing self-supervised learning methods are applicable to packaged data. However, when it comes to streamed data, they are…

Scene text recognition (STR) has been extensively studied in last few years. Many recently-proposed methods are specially designed to accommodate the arbitrary shape, layout and orientation of scene texts, but ignoring that various font (or…

Self-supervised instance discrimination is an effective contrastive pretext task to learn feature representations and address limited medical image annotations. The idea is to make features of transformed versions of the same images similar…

Context-aware STR methods typically use internal autoregressive (AR) language models (LM). Inherent limitations of AR models motivated two-stage methods which employ an external LM. The conditional independence of the external LM on the…

In this work, we propose CLUDA, a simple, yet novel method for performing unsupervised domain adaptation (UDA) for semantic segmentation by incorporating contrastive losses into a student-teacher learning paradigm, that makes use of…

Scene text recognition has attracted great interests from the computer vision and pattern recognition community in recent years. State-of-the-art methods use concolutional neural networks (CNNs), recurrent neural networks with long…

Dominant scene text recognition models commonly contain two building blocks, a visual model for feature extraction and a sequence model for text transcription. This hybrid architecture, although accurate, is complex and less efficient. In…

We propose to improve text recognition from a new perspective by separating the text content from complex backgrounds. As vanilla GANs are not sufficiently robust to generate sequence-like characters in natural images, we propose an…

State-of-the-art text spotting systems typically aim to detect isolated words or word-by-word text in images of natural scenes and ignore the semantic coherence within a region of text. However, when interpreted together, seemingly isolated…

Texture classification is a pivotal task in computer vision, presenting unique challenges due to high inter-class similarity and the sensitivity of structural patterns to scale and illumination changes. While Convolutional Neural Networks…

Scene text recognition (STR) has attracted much attention due to its broad applications. The previous works pay more attention to dealing with the recognition of Latin text images with complex backgrounds by introducing language models or…

Scene text editing aims to modify text content within scene images while maintaining style consistency. Traditional methods achieve this by explicitly disentangling style and content from the source image and then fusing the style with the…

Scene text detection methods based on neural networks have emerged recently and have shown promising results. Previous methods trained with rigid word-level bounding boxes exhibit limitations in representing the text region in an arbitrary…

Contrastive learning models have achieved great success in unsupervised visual representation learning, which maximize the similarities between feature representations of different views of the same image, while minimize the similarities…