相关论文: Adversarial Training with OCR Modality Perturbatio…

We propose a novel multimodal architecture for Scene Text Visual Question Answering (STVQA), named Layout-Aware Transformer (LaTr). The task of STVQA requires models to reason over different modalities. Thus, we first investigate the impact…

Test automation has become increasingly important as the complexity of both design and content in Human Machine Interface (HMI) software continues to grow. Current standard practice uses Optical Character Recognition (OCR) techniques to…

In the field of scene text spotting, previous OCR methods primarily relied on image encoders and pre-trained text information, but they often overlooked the advantages of incorporating human language instructions. To address this gap, we…

Textual cues are essential for everyday tasks like buying groceries and using public transport. To develop this assistive technology, we study the TextVQA task, i.e., reasoning about text in images to answer a question. Existing approaches…

Variational Autoencoders (VAEs) have played a key role in scaling up diffusion-based generative models, as in Stable Diffusion, yet questions regarding their robustness remain largely underexplored. Although adversarial training has been an…

Visual Question Answering (VQA) is a fundamental task in computer vision and natural language process fields. Although the ``pre-training & finetuning'' learning paradigm significantly improves the VQA performance, the adversarial…

Adversarial training (AT) as a regularization method has proved its effectiveness in various tasks, such as image classification and text classification. Though there are successful applications of AT in many tasks of natural language…

The Visual Question Answering (VQA) system offers a user-friendly interface and enables human-computer interaction. However, VQA models commonly face the challenge of language bias, resulting from the learned superficial correlation between…

Visual Document Understanding (VDU) systems have achieved strong performance in information extraction by integrating textual, layout, and visual signals. However, their robustness under realistic adversarial perturbations remains…

Optical character recognition (OCR) and multilingual text understanding remain major failure modes of multimodal large language models (MLLMs), particularly in real-world images containing cluttered layouts, small fonts, blur, occlusion,…

Recent studies have shown that state-of-the-art deep learning models are vulnerable to the inputs with small perturbations (adversarial examples). We observe two critical obstacles in adversarial examples: (i) Strong adversarial attacks…

Texts in scene images convey critical information for scene understanding and reasoning. The abilities of reading and reasoning matter for the model in the text-based visual question answering (TextVQA) process. However, current TextVQA…

Scene text recognition (STR) and handwritten text recognition (HTR) face significant challenges in accurately transcribing textual content from images into machine-readable formats. Conventional OCR models often predict transcriptions…

Adversarial continual learning is effective for continual learning problems because of the presence of feature alignment process generating task-invariant features having low susceptibility to the catastrophic forgetting problem.…

Drawing upon the intuition that aligning different modalities to the same semantic embedding space would allow models to understand states and actions more easily, we propose a new perspective to the offline reinforcement learning (RL)…

Spoken question answering (SQA) is challenging due to complex reasoning on top of the spoken documents. The recent studies have also shown the catastrophic impact of automatic speech recognition (ASR) errors on SQA. Therefore, this work…

The open-ended question answering task of Text-VQA often requires reading and reasoning about rarely seen or completely unseen scene-text content of an image. We address this zero-shot nature of the problem by proposing the generalized use…

In this paper, we propose Text-Aware Pre-training (TAP) for Text-VQA and Text-Caption tasks. These two tasks aim at reading and understanding scene text in images for question answering and image caption generation, respectively. In…

The ability to recognize and reason about text embedded in visual inputs is often lacking in vision-and-language (V&L) models, perhaps because V&L pre-training methods have often failed to include such an ability in their training…

Adversarial training is wildly considered as one of the most effective way to defend against adversarial examples. However, existing adversarial training methods consume unbearable time, due to the fact that they need to generate…