Related papers: Pushing the Performance Limit of Scene Text Recogn…
Reading text in the wild is a very challenging task due to the diversity of text instances and the complexity of natural scenes. Recently, the community has paid increasing attention to the problem of recognizing text instances with…
Synthetic data has been a critical tool for training scene text detection and recognition models. On the one hand, synthetic word images have proven to be a successful substitute for real images in training scene text recognizers. On the…
Deep convolutional neural networks for semantic segmentation achieve outstanding accuracy, however they also have a couple of major drawbacks: first, they do not generalize well to distributions slightly different from the one of the…
Scene text recognition (STR) has been an active research topic in computer vision for years. To tackle this challenging problem, numerous innovative methods have been successively proposed and incorporating linguistic knowledge into STR…
Generative Adversarial Networks (GANs) are known to be difficult to train, despite considerable research effort. Several regularization techniques for stabilizing training have been proposed, but they introduce non-trivial computational…
When working with textual data, a natural application of disentangled representations is fair classification where the goal is to make predictions without being biased (or influenced) by sensitive attributes that may be present in the data…
Recent approaches for end-to-end text spotting have achieved promising results. However, most of the current spotters were plagued by the inconsistency problem between text detection and recognition. In this work, we introduce and prove the…
A large fraction of textual data available today contains various types of 'noise', such as OCR noise in digitized documents, noise due to informal writing style of users on microblogging sites, and so on. To enable tasks such as…
Prompt learning has emerged as a promising method for adapting pre-trained visual-language models (VLMs) to a range of downstream tasks. While optimizing the context can be effective for improving performance on specific tasks, it can often…
On-device Automatic Speech Recognition (ASR) models trained on speech data of a large population might underperform for individuals unseen during training. This is due to a domain shift between user data and the original training data,…
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…
Consistency regularization has recently been applied to semi-supervised sequence-to-sequence (S2S) automatic speech recognition (ASR). This principle encourages an ASR model to output similar predictions for the same input speech with…
Recognizing text in natural images is a challenging task with many unsolved problems. Different from those in documents, words in natural images often possess irregular shapes, which are caused by perspective distortion, curved character…
Image synthesis driven by computer graphics achieved recently a remarkable realism, yet synthetic image data generated this way reveals a significant domain gap with respect to real-world data. This is especially true in autonomous driving…
Consistency regularization is a commonly used practice to encourage the model to generate consistent representation from distorted input features and improve model generalization. It shows significant improvement on various speech…
This paper tackles critical challenges in traffic sign recognition (TSR), which is essential for road safety -- specifically, class imbalance and instance scarcity in datasets. We introduce tailored data augmentation techniques, including…
Recent efforts on scene text erasing have shown promising results. However, existing methods require rich yet costly label annotations to obtain robust models, which limits the use for practical applications. To this end, we study 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…
Scene text removal (STR) aims to erase textual elements from images. It was originally intended for removing privacy-sensitiveor undesired texts from natural scene images, but is now also appliedto typographic images. STR typically detects…
This paper introduces a novel synthetic dataset that captures urban scenes under a variety of weather conditions, providing pixel-perfect, ground-truth-aligned images to facilitate effective feature alignment across domains. Additionally,…