English
Related papers

Related papers: Pushing the Performance Limit of Scene Text Recogn…

200 papers

We address the issue of domain gap when making use of synthetic data to train a scene-specific object detector and pose estimator. While previous works have shown that the constraints of learning a scene-specific model can be leveraged to…

Computer Vision and Pattern Recognition · Computer Science 2018-11-15 Rawal Khirodkar , Donghyun Yoo , Kris M. Kitani

Fine-tuning well-aligned large language models (LLMs) on new domains often degrades their safety alignment, even when using benign datasets. Existing safety alignment techniques primarily focus on pretraining, leaving fine-tuned models…

Machine Learning · Computer Science 2026-04-21 Thong Bach , Truyen Tran

Convolution neural networks have achieved remarkable performance in many tasks of computing vision. However, CNN tends to bias to low frequency components. They prioritize capturing low frequency patterns which lead them fail when suffering…

Machine Learning · Computer Science 2020-07-08 Weiyu Guo , Yidong Ouyang

We propose an extended framework for marginalized domain adaptation, aimed at addressing unsupervised, supervised and semi-supervised scenarios. We argue that the denoising principle should be extended to explicitly promote domain-invariant…

Computer Vision and Pattern Recognition · Computer Science 2017-02-21 Gabriela Csurka , Boris Chidlovski , Stephane Clinchant , Sophia Michel

Scene Text Recognition (STR), the task of recognizing text against complex image backgrounds, is an active area of research. Current state-of-the-art (SOTA) methods still struggle to recognize text written in arbitrary shapes. In this…

Computer Vision and Pattern Recognition · Computer Science 2020-03-26 Ron Litman , Oron Anschel , Shahar Tsiper , Roee Litman , Shai Mazor , R. Manmatha

For pixel-level crowd understanding, it is time-consuming and laborious in data collection and annotation. Some domain adaptation algorithms try to liberate it by training models with synthetic data, and the results in some recent works…

Computer Vision and Pattern Recognition · Computer Science 2020-02-21 Tao Han , Junyu Gao , Yuan Yuan , Qi Wang

The usefulness of deep learning models in robotics is largely dependent on the availability of training data. Manual annotation of training data is often infeasible. Synthetic data is a viable alternative, but suffers from domain gap. We…

Computer Vision and Pattern Recognition · Computer Science 2022-11-18 Benedikt T. Imbusch , Max Schwarz , Sven Behnke

A large number of works view the automatic assessment of speech from an utterance- or system-level perspective. While such approaches are good in judging overall quality, they cannot adequately explain why a certain score was assigned to an…

Audio and Speech Processing · Electrical Eng. & Systems 2026-01-30 Michael Kuhlmann , Alexander Werning , Thilo von Neumann , Reinhold Haeb-Umbach

Numerous scene text detection methods have been proposed in recent years. Most of them declare they have achieved state-of-the-art performances. However, the performance comparison is unfair, due to lots of inconsistent settings (e.g.,…

Computer Vision and Pattern Recognition · Computer Science 2021-07-27 Pengwen Dai , Xiaochun Cao

Semi-Supervised image classification is one of the most fundamental problem in computer vision, which significantly reduces the need for human labor. In this paper, we introduce a new semi-supervised learning algorithm - SimMatchV2, which…

Computer Vision and Pattern Recognition · Computer Science 2023-08-15 Mingkai Zheng , Shan You , Lang Huang , Chen Luo , Fei Wang , Chen Qian , Chang Xu

Consistency regularization describes a class of approaches that have yielded state-of-the-art results for semi-supervised classification. While semi-supervised semantic segmentation proved to be more challenging, a number of successful…

Computer Vision and Pattern Recognition · Computer Science 2021-10-12 Geoff French , Michal Mackiewicz

Automatic Music Transcription (AMT) is a vital technology in the field of music information processing. Despite recent enhancements in performance due to machine learning techniques, current methods typically attain high accuracy in domains…

Sound · Computer Science 2024-07-04 Gakusei Sato , Taketo Akama

Scene text detection, which is one of the most popular topics in both academia and industry, can achieve remarkable performance with sufficient training data. However, the annotation costs of scene text detection are huge with traditional…

Computer Vision and Pattern Recognition · Computer Science 2020-12-11 Wenqing Zhang , Yang Qiu , Minghui Liao , Rui Zhang , Xiaolin Wei , Xiang Bai

Deep learning models obtain impressive accuracy in road scenes understanding, however they need a large quantity of labeled samples for their training. Additionally, such models do not generalise well to environments where the statistical…

Computer Vision and Pattern Recognition · Computer Science 2021-10-28 Francesco Barbato , Umberto Michieli , Marco Toldo , Pietro Zanuttigh

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…

Computer Vision and Pattern Recognition · Computer Science 2018-09-27 Fangneng Zhan , Shijian Lu , Chuhui Xue

Scene Text Editing (STE) is a challenging research problem, that primarily aims towards modifying existing texts in an image while preserving the background and the font style of the original text. Despite its utility in numerous real-world…

Computer Vision and Pattern Recognition · Computer Science 2024-11-06 Alloy Das , Sanket Biswas , Prasun Roy , Subhankar Ghosh , Umapada Pal , Michael Blumenstein , Josep Lladós , Saumik Bhattacharya

Deep learning algorithms have obtained great success in semantic segmentation of very high-resolution (VHR) images. Nevertheless, training these models generally requires a large amount of accurate pixel-wise annotations, which is very…

Computer Vision and Pattern Recognition · Computer Science 2022-09-07 Yonghao Xu , Pedram Ghamisi

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…

Computer Vision and Pattern Recognition · Computer Science 2026-03-05 Xu Yao , Lei Kang

Detecting curved text in the wild is very challenging. Recently, most state-of-the-art methods are segmentation based and require pixel-level annotations. We propose a novel scheme to train an accurate text detector using only a small…

Computer Vision and Pattern Recognition · Computer Science 2019-08-28 Xugong Qin , Yu Zhou , Dongbao Yang , Weiping Wang

Abstractive text summarization is a highly difficult problem, and the sequence-to-sequence model has shown success in improving the performance on the task. However, the generated summaries are often inconsistent with the source content in…

Computation and Language · Computer Science 2018-05-11 Bingzhen Wei , Xuancheng Ren , Xu Sun , Yi Zhang , Xiaoyan Cai , Qi Su