相关论文: Data Augmentation for Scene Text Recognition

Data augmentation (DA) is a crucial technique for enhancing the sample efficiency of visual reinforcement learning (RL) algorithms. Notably, employing simple observation transformations alone can yield outstanding performance without extra…

The requirement of large amounts of annotated images has become one grand challenge while training deep neural network models for various visual detection and recognition tasks. This paper presents a novel image synthesis technique that…

Text removal is a crucial task in computer vision with applications such as privacy preservation, image editing, and media reuse. While existing research has primarily focused on scene text removal in natural images, limitations in current…

Single-Domain Generalized Object Detection~(S-DGOD) aims to train on a single source domain for robust performance across a variety of unseen target domains by taking advantage of an object detector. Existing S-DGOD approaches often rely on…

The performance of generative adversarial networks (GANs) heavily deteriorates given a limited amount of training data. This is mainly because the discriminator is memorizing the exact training set. To combat it, we propose Differentiable…

Graph-level anomaly detection (GAD) is critical in diverse domains such as drug discovery, yet high labeling costs and dataset imbalance hamper the performance of Graph Neural Networks (GNNs). To address these issues, we propose FracAug, an…

Scene text recognition (STR) involves the task of reading text in cropped images of natural scenes. Conventional models in STR employ convolutional neural network (CNN) followed by recurrent neural network in an encoder-decoder framework.…

Language-augmented scene representations hold great promise for large-scale robotics applications such as search-and-rescue, smart cities, and mining. Many of these scenarios are time-sensitive, requiring rapid scene encoding while also…

We introduce InstaAug, a method for automatically learning input-specific augmentations from data. Previous methods for learning augmentations have typically assumed independence between the original input and the transformation applied to…

The success of training deep Convolutional Neural Networks (CNNs) heavily depends on a significant amount of labelled data. Recent research has found that neural style transfer algorithms can apply the artistic style of one image to another…

Although Deep Convolutional Neural Networks trained with strong pixel-level annotations have significantly pushed the performance in semantic segmentation, annotation efforts required for the creation of training data remains a roadblock…

Understanding and comprehending video content is crucial for many real-world applications such as search and recommendation systems. While recent progress of deep learning has boosted performance on various tasks using visual cues, deep…

We present a novel deep neural model for text detection in document images. For robust text detection in noisy scanned documents, the advantages of multi-task learning are adopted by adding an auxiliary task of text enhancement. Namely, our…

Recent works in the text recognition area have pushed forward the recognition results to the new horizons. But for a long time a lack of large human-labeled natural text recognition datasets has been forcing researchers to use synthetic…

Scene text detection based on deep neural networks have progressed substantially over the past years. However, previous state-of-the-art methods may still fall short when dealing with challenging public benchmarks because the performances…

Speech recognition systems often face challenges due to domain mismatch, particularly in real-world applications where domain-specific data is unavailable because of data accessibility and confidentiality constraints. Inspired by…

Scene text images have different shapes and are subjected to various distortions, e.g. perspective distortions. To handle these challenges, the state-of-the-art methods rely on a rectification network, which is connected to the text…

Scene Text Recognition (STR) is an important and challenging upstream task for building structured information databases, that involves recognizing text within images of natural scenes. Although current state-of-the-art (SOTA) models for…

This paper addresses the challenges of registering two rigid semantic scene graphs, an essential capability when an autonomous agent needs to register its map against a remote agent, or against a prior map. The hand-crafted descriptors in…

One of the key shortcomings in current text-to-image (T2I) models is their inability to consistently generate images which faithfully follow the spatial relationships specified in the text prompt. In this paper, we offer a comprehensive…