Related papers: STR-Cert: Robustness Certification for Deep Text R…

Scene Text Image Super-Resolution (STISR) aims to enhance the resolution and legibility of text within low-resolution (LR) images, consequently elevating recognition accuracy in Scene Text Recognition (STR). Previous methods predominantly…

Deep Networks have been shown to provide state-of-the-art performance in many machine learning challenges. Unfortunately, they are susceptible to various types of noise, including adversarial attacks and corrupted inputs. In this work we…

The diversity in length constitutes a significant characteristic of text. Due to the long-tail distribution of text lengths, most existing methods for scene text recognition (STR) only work well on short or seen-length text, lacking the…

Scene text recognition has attracted a great many researches due to its importance to various applications. Existing methods mainly adopt recurrence or convolution based networks. Though have obtained good performance, these methods still…

Deep neural networks (DNNs) are vulnerable to adversarial noises, which motivates the benchmark of model robustness. Existing benchmarks mainly focus on evaluating defenses, but there are no comprehensive studies of how architecture design…

Scene Text Recognition (STR) remains challenging due to real-world complexities, where decoupled visual-linguistic optimization in existing frameworks amplifies error propagation through cross-modal misalignment. Visual encoders exhibit…

Our work explores the utilization of deep learning, specifically leveraging the CodeBERT model, to enhance code security testing for Python applications by detecting SQL injection vulnerabilities. Unlike traditional security testing methods…

We introduce the structured scene-text spotting task, which requires a scene-text OCR system to spot text in the wild according to a query regular expression. Contrary to generic scene text OCR, structured scene-text spotting seeks to…

Neural networks have become increasingly popular in controller design due to their versatility and efficiency. However, their integration into feedback systems can pose stability challenges, particularly in the presence of uncertainties.…

In the last years, AI systems, in particular neural networks, have seen a tremendous increase in performance, and they are now used in a broad range of applications. Unlike classical symbolic AI systems, neural networks are trained using…

Graph structure learning aims to learn connectivity in a graph from data. It is particularly important for many computer vision related tasks since no explicit graph structure is available for images for most cases. A natural way to…

ML models are typically trained using large datasets of high quality. However, training datasets often contain inconsistent or incomplete data. To tackle this issue, one solution is to develop algorithms that can check whether a prediction…

Recent deep learning models have demonstrated strong capabilities for classifying text and non-text components in natural images. They extract a high-level feature computed globally from a whole image component (patch), where the cluttered…

The language models, especially the basic text classification models, have been shown to be susceptible to textual adversarial attacks such as synonym substitution and word insertion attacks. To defend against such attacks, a growing body…

Visual Foundation Models (VFMs) are becoming ubiquitous in computer vision, powering systems for diverse tasks such as object detection, image classification, segmentation, pose estimation, and motion tracking. VFMs are capitalizing on…

Ensuring robustness in image watermarking is crucial for and maintaining content integrity under diverse transformations. Recent self-supervised learning (SSL) approaches, such as DINO, have been leveraged for watermarking but primarily…

Recent studies show that deep neural networks (DNN) are vulnerable to adversarial examples, which aim to mislead DNNs by adding perturbations with small magnitude. To defend against such attacks, both empirical and theoretical defense…

We describe a method for verifying the output of a deep neural network for medical image segmentation that is robust to several classes of random as well as worst-case perturbations i.e. adversarial attacks. This method is based on a…

The prosperity of deep learning contributes to the rapid progress in scene text detection. Among all the methods with convolutional networks, segmentation-based ones have drawn extensive attention due to their superiority in detecting text…

Effective crack detection is pivotal for the structural health monitoring and inspection of buildings. This task presents a formidable challenge to computer vision techniques due to the inherently subtle nature of cracks, which often…