English
Related papers

Related papers: An Effective Data Augmentation Method by Asking Qu…

200 papers

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…

Computer Vision and Pattern Recognition · Computer Science 2022-07-15 Darwin Bautista , Rowel Atienza

Texts appearing in daily scenes that can be recognized by OCR (Optical Character Recognition) tools contain significant information, such as street name, product brand and prices. Two tasks -- text-based visual question answering and…

Computer Vision and Pattern Recognition · Computer Science 2020-12-10 Qi Zhu , Chenyu Gao , Peng Wang , Qi Wu

Query rewriting (QR) systems are widely used to reduce the friction caused by errors in a spoken language understanding pipeline. However, the underlying supervised models require a large number of labeled pairs, and these pairs are hard…

Computation and Language · Computer Science 2020-12-22 Yunmo Chen , Sixing Lu , Fan Yang , Xiaojiang Huang , Xing Fan , Chenlei Guo

Business Process Modeling projects often require formal process models as a central component. High costs associated with the creation of such formal process models motivated many different fields of research aimed at automated generation…

Computation and Language · Computer Science 2024-04-12 Julian Neuberger , Leonie Doll , Benedict Engelmann , Lars Ackermann , Stefan Jablonski

In recent years, text-image joint pre-training techniques have shown promising results in various tasks. However, in Optical Character Recognition (OCR) tasks, aligning text instances with their corresponding text regions in images poses a…

Computer Vision and Pattern Recognition · Computer Science 2024-04-18 Chen Duan , Pei Fu , Shan Guo , Qianyi Jiang , Xiaoming Wei

Scene text image super-resolution (STISR) is an important pre-processing technique for text recognition from low-resolution scene images. Nowadays, various methods have been proposed to extract text-specific information from high-resolution…

Computer Vision and Pattern Recognition · Computer Science 2023-08-01 Minyi Zhao , Yi Xu , Bingjia Li , Jie Wang , Jihong Guan , Shuigeng Zhou

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…

Computer Vision and Pattern Recognition · Computer Science 2024-06-07 Ulan Alsiyeu , Zhasdauren Duisebekov

Image captioning, an important vision-language task, often requires a tremendous number of finely labeled image-caption pairs for learning the underlying alignment between images and texts. In this paper, we proposed a multimodal data…

Computer Vision and Pattern Recognition · Computer Science 2023-11-14 Changrong Xiao , Sean Xin Xu , Kunpeng Zhang

Creation of large-scale databases for Visual Question Answering tasks pertaining to the text data in a scene (text-VQA) involves skilful human annotation, which is tedious and challenging. With the advent of foundation models that handle…

Computer Vision and Pattern Recognition · Computer Science 2025-11-05 Soham Joshi , Shwet Kamal Mishra , Viswanath Gopalakrishnan

Many scene text recognition approaches are based on purely visual information and ignore the semantic relation between scene and text. In this paper, we tackle this problem from natural language processing perspective to fill the gap…

Computer Vision and Pattern Recognition · Computer Science 2018-10-31 Ahmed Sabir , Francesc Moreno-Noguer , Lluís Padró

Data Augmentation (DA) -- generating extra training samples beyond original training set -- has been widely-used in today's unbiased VQA models to mitigate the language biases. Current mainstream DA strategies are synthetic-based methods,…

Computer Vision and Pattern Recognition · Computer Science 2022-09-16 Long Chen , Yuhang Zheng , Jun Xiao

Acquiring high-quality knowledge is a central focus in Knowledge-Based Visual Question Answering (KB-VQA). Recent methods use large language models (LLMs) as knowledge engines for answering. These methods generally employ image captions as…

Computer Vision and Pattern Recognition · Computer Science 2025-09-26 Yan Zhang , Jiaqing Lin , Miao Zhang , Kui Xiao , Xiaoju Hou , Yue Zhao , Zhifei Li

Performing data augmentation for learning deep neural networks is well known to be important for training visual recognition systems. By artificially increasing the number of training examples, it helps reducing overfitting and improves…

Computer Vision and Pattern Recognition · Computer Science 2018-07-20 Nikita Dvornik , Julien Mairal , Cordelia Schmid

Data augmentation is an effective way to improve the performance of many neural text generation models. However, current data augmentation methods need to define or choose proper data mapping functions that map the original samples into the…

Computation and Language · Computer Science 2021-05-31 Wei Bi , Huayang Li , Jiacheng Huang

Despite the rapid advancements in Multimodal Large Language Models (MLLMs), a critical question regarding their visual grounding mechanism remains unanswered: do these models genuinely ``read'' text embedded in images, or do they merely…

Computer Vision and Pattern Recognition · Computer Science 2026-02-27 Yibo Peng , Peng Xia , Ding Zhong , Kaide Zeng , Siwei Han , Yiyang Zhou , Jiaqi Liu , Ruiyi Zhang , Huaxiu Yao

Automatic recognition of disordered speech remains a highly challenging task to date due to data scarcity. This paper presents a reinforcement learning (RL) based on-the-fly data augmentation approach for training state-of-the-art PyChain…

Audio and Speech Processing · Electrical Eng. & Systems 2023-12-15 Zengrui Jin , Xurong Xie , Tianzi Wang , Mengzhe Geng , Jiajun Deng , Guinan Li , Shujie Hu , Xunying Liu

Logical reasoning of text requires understanding critical logical information in the text and performing inference over them. Large-scale pre-trained models for logical reasoning mainly focus on word-level semantics of text while struggling…

Computation and Language · Computer Science 2021-05-11 Siyuan Wang , Wanjun Zhong , Duyu Tang , Zhongyu Wei , Zhihao Fan , Daxin Jiang , Ming Zhou , Nan Duan

In this paper, we explore the artificial generation of typographical errors based on real-world statistics. We first draw on a small set of annotated data to compute spelling error statistics. These are then invoked to introduce errors into…

Computation and Language · Computer Science 2020-05-05 Kshitij Shah , Gerard de Melo

This paper aims to re-assess scene text recognition (STR) from a data-oriented perspective. We begin by revisiting the six commonly used benchmarks in STR and observe a trend of performance saturation, whereby only 2.91% of the benchmark…

Computer Vision and Pattern Recognition · Computer Science 2023-07-20 Qing Jiang , Jiapeng Wang , Dezhi Peng , Chongyu Liu , Lianwen Jin

Typography and layout lead to the hierarchical organisation of text in words, text lines, paragraphs. This inherent structure is a key property of text in any script and language, which has nonetheless been minimally leveraged by existing…

Computer Vision and Pattern Recognition · Computer Science 2024-10-30 Lluis Gomez , Dimosthenis Karatzas
‹ Prev 1 3 4 5 6 7 10 Next ›