检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

作者： Peng, Dezhi Yang, Zhenhua Zhang, Jiaxin Liu, Chongyu Shi, Yongxin Ding, Kai Guo, Fengjun Jin, Lianwen South China University of Technology China INTSIG-SCUT Joint Lab of Document Image Analysis and Recognition China INTSIG Information Co. Ltd. Singapore

Existing optical character recognition (OCR) methods rely on task-specific designs with divergent paradigms, architectures, and training strategies, which significantly increases the complexity of research and maintenance and hinders the fast deployment in applications. To this end, we propose UPOCR, a simple-yet-effective generalist model for Unified Pixel-level OCR interface. Specifically, the UPOCR unifies the paradigm of diverse OCR tasks as image-to-image transformation and the architecture as a vision Transformer (ViT)-based encoder-decoder with learnable task prompts. The prompts push the general feature representations extracted by the encoder towards task-specific spaces, endowing the decoder with task awareness. Moreover, the model training is uniformly aimed at minimizing the discrepancy between the predicted and ground-truth images regardless of the inhomogeneity among tasks. Experiments are conducted on three pixel-level OCR tasks including text removal, text segmentation, and tampered text detection. Without bells and whistles, the experimental results showcase that the proposed method can simultaneously achieve state-of-the-art performance on three tasks with a unified single model, which provides valuable strategies and insights for future research on generalist OCR models. Code is available at https://***/shannanyinxiang/UPOCR. Copyright 2024 by the author(s)

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

WenMind: A Comprehensive Benchmark for Evaluating Large Language Models in Chinese Classical Literature and Language Arts 38

WenMind: A Comprehensive Benchmark for Evaluating Large Lang...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Cao, Jiahuan Liu, Yang Shi, Yongxin Ding, Kai Jin, Lianwen South China University of Technology China INTSIG Information Co. Ltd. China INTSIG-SCUT Joint Lab on Document Analysis and Recognition China

Large Language Models (LLMs) have made significant advancements across numerous domains, but their capabilities in Chinese Classical Literature and Language Arts (CCLLA) remain largely unexplored due to the limited scope and tasks of existing benchmarks. To fill this gap, we propose WenMind, a comprehensive benchmark dedicated for evaluating LLMs in CCLLA. WenMind covers the sub-domains of Ancient Prose, Ancient Poetry, and Ancient Literary Culture, comprising 4,875 question-answer pairs, spanning 42 fine-grained tasks, 3 question formats, and 2 evaluation scenarios: domain-oriented and capability-oriented. Based on WenMind, we conduct a thorough evaluation of 31 representative LLMs, including general-purpose models and ancient Chinese LLMs. The results reveal that even the best-performing model, ERNIE-4.0, only achieves a total score of 64.3, indicating significant room for improvement of LLMs in the CCLLA domain. We also provide insights into the strengths and weaknesses of different LLMs and highlight the importance of pre-training data in achieving better results. Overall, WenMind serves as a standardized and comprehensive baseline, providing valuable insights for future CCLLA research. Our benchmark and related code are available at https://***/scut-DLVClab/WenMind. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TongGu: Mastering Classical Chinese Understanding with Knowledge-Grounded Large Language Models

TongGu: Mastering Classical Chinese Understanding with Knowl...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Cao, Jiahuan Peng, Dezhi Zhang, Peirong Shi, Yongxin Liu, Yang Ding, Kai Jin, Lianwen South China University of Technology China Intsig Information Co. Ltd. Singapore INTSIG-SCUT Joint Lab on Document Analysis and Recognition China

ISBN: (纸本)9798891761681

Classical Chinese is a gateway to the rich heritage and wisdom of ancient China, yet its complexities pose formidable comprehension barriers for most modern people without specialized knowledge. While Large Language Models (LLMs) have shown remarkable capabilities in Natural Language Processing (NLP), they struggle with Classical Chinese Understanding (CCU), especially in data-demanding and knowledge-intensive tasks. In response to this dilemma, we propose TongGu (mean understanding ancient and modern), the first CCU-specific LLM, underpinned by three core contributions. First, we construct a two-stage instruction-tuning dataset ACCN-INS derived from rich classical Chinese corpora, aiming to unlock the full CCU potential of LLMs. Second, we propose Redundancy-Aware Tuning (RAT) to prevent catastrophic forgetting, enabling TongGu to acquire new capabilities while preserving its foundational knowledge. Third, we present a CCU Retrieval-Augmented Generation (CCU-RAG) technique to reduce hallucinations based on knowledge-grounding. Extensive experiments across 24 diverse CCU tasks validate TongGu's superior ability, underscoring the effectiveness of RAT and CCU-RAG. The model and dataset are available at https://***/scut-DLVClab/TongGu-LLM. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

WenMind: a comprehensive benchmark for evaluating large language models in Chinese classical literature and language arts 24

WenMind: a comprehensive benchmark for evaluating large lang...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Jiahuan Cao Yang Liu Yongxin Shi Kai Ding Lianwen Jin South China University of Technology and INTSIG-SCUT Joint Lab on Document Analysis and Recognition INTSIG Information Co. Ltd and INTSIG-SCUT Joint Lab on Document Analysis and Recognition

ISBN: (纸本)9798331314385

关键词：

来源：评论

学校读者我要写书评

暂无评论

UPOCR: towards unified pixel-level OCR interface 24

UPOCR: towards unified pixel-level OCR interface

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Dezhi Peng Zhenhua Yang Jiaxin Zhang Chongyu Liu Yongxin Shi Kai Ding Fengjun Guo Lianwen Jin South China University of Technology and INTSIG-SCUT Joint Lab of Document Image Analysis and Recognition NTSIG Information Co. Ltd. and INTSIG-SCUT Joint Lab of Document Image Analysis and Recognition

关键词：

来源：评论

学校读者我要写书评

暂无评论

DocRes: A Generalist Model Toward Unifying document image Restoration Tasks

DocRes: A Generalist Model Toward Unifying Document Image Re...

引用

Conference on Computer Vision and Pattern recognition (CVPR)

作者： Jiaxin Zhang Dezhi Peng Chongyu Liu Peirong Zhang Lianwen Jin South China University of Technology INTSIG-SCUT Joint Lab on Document Analysis and Recognition

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

document image restoration is a crucial aspect of document AI systems, as the quality of document images significantly influences the overall performance. Prevailing methods address distinct restoration tasks independently, leading to intricate systems and the incapability to harness the potential synergies of multi-task learning. To overcome this challenge, we propose DocRes, a generalist model that unifies five document image restoration tasks including dewarping, deshadowing, appearance enhancement, deblurring, and binarization. To instruct DocRes to perform various restoration tasks, we propose a novel visual prompt approach called Dynamic Task-Specific Prompt (DTSPrompt). The DTSPrompt for different tasks comprises distinct prior features, which are additional characteristics extracted from the input image. Beyond its role as a cue for task-specific execution, DTSPrompt can also serve as supplementary information to enhance the model's performance. Moreover, DTSPrompt is more flexible than prior visual prompt approaches as it can be seamlessly applied and adapted to inputs with high and variable resolutions. Experimental results demonstrate that DocRes achieves competitive or superior performance compared to existing state-of-the-art task-specific models. This under-scores the potential of DocRes across a broader spectrum of document image restoration tasks. The source code is publicly available at https://***/ZZZHANGjx/DocRes.

关键词： Adaptation models Visualization Computer vision image resolution Computational modeling Source coding Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Predicting the Original Appearance of Damaged Historical documents

arXiv

引用

arXiv 2024年

作者： Yang, Zhenhua Peng, Dezhi Shi, Yongxin Zhang, Yuyi Liu, Chongyu Jin, Lianwen South China University of Technology China INTSIG-SCUT Joint Lab on Document Analysis and Recognition China

Historical documents encompass a wealth of cultural treasures but suffer from severe damages including character missing, paper damage, and ink erosion over time. However, existing document processing methods primarily focus on binarization, enhancement, etc., neglecting the repair of these damages. To this end, we present a new task, termed Historical document Repair (HDR), which aims to predict the original appearance of damaged historical documents. To fill the gap in this field, we propose a large-scale dataset HDR28K and a diffusion-based network DiffHDR for historical document repair. Specifically, HDR28K contains 28,552 damaged-repaired image pairs with character-level annotations and multi-style degradations. Moreover, DiffHDR augments the vanilla diffusion framework with semantic and spatial information and a meticulously designed character perceptual loss for contextual and visual coherence. Experimental results demonstrate that the proposed DiffHDR trained using HDR28K significantly surpasses existing approaches and exhibits remarkable performance in handling real damaged documents. Notably, DiffHDR can also be extended to document editing and text block generation, showcasing its high flexibility and generalization capacity. We believe this study could pioneer a new direction of document processing and contribute to the inheritance of invaluable cultures and civilizations. The dataset and code is available at https://***/yeungchenwa/HDR. Copyright © 2024, The Authors. All rights reserved.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

DocRes: A Generalist Model Toward Unifying document image Restoration Tasks

arXiv

引用

arXiv 2024年

作者： Zhang, Jiaxin Peng, Dezhi Liu, Chongyu Zhang, Peirong Jin, Lianwen South China University of Technology China INTSIG-SCUT Joint Lab on Document Analysis and Recognition China

document image restoration is a crucial aspect of document AI systems, as the quality of document images significantly influences the overall performance. Prevailing methods address distinct restoration tasks independently, leading to intricate systems and the incapability to harness the potential synergies of multi-task learning. To overcome this challenge, we propose DocRes, a generalist model that unifies five document image restoration tasks including dewarping, deshadowing, appearance enhancement, deblurring, and binarization. To instruct DocRes to perform various restoration tasks, we propose a novel visual prompt approach called Dynamic Task-Specific Prompt (DTSPrompt). The DTSPrompt for different tasks comprises distinct prior features, which are additional characteristics extracted from the input image. Beyond its role as a cue for task-specific execution, DTSPrompt can also serve as supplementary information to enhance the model's performance. Moreover, DTSPrompt is more flexible than prior visual prompt approaches as it can be seamlessly applied and adapted to inputs with high and variable resolutions. Experimental results demonstrate that DocRes achieves competitive or superior performance compared to existing state-of-the-art task-specific models. This underscores the potential of DocRes across a broader spectrum of document image restoration tasks. The source code is publicly available at https://***/ZZZHANGjx/DocRes. © 2024, CC BY.

关键词： Restoration

来源：评论

学校读者我要写书评

暂无评论

Bridging the Gap Between End-to-End and Two-Step Text Spotting

Bridging the Gap Between End-to-End and Two-Step Text Spotti...

引用

Conference on Computer Vision and Pattern recognition (CVPR)

作者： Mingxin Huang Hongliang Li Yuliang Liu Xiang Bai Lianwen Jin South China University of Technology Huazhong University of Science and Technology INTSIG-SCUT Joint Lab on Document Analysis and Recognition

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Modularity plays a crucial role in the development and maintenance of complex systems. While end-to-end text spotting efficiently mitigates the issues of error accumulation and sub-optimal performance seen in traditional two-step methodologies, the two-step methods continue to be favored in many competitions and practical settings due to their superior modularity. In this paper, we introduce Bridging Text Spotting, a novel approach that resolves the error accumulation and suboptimal performance issues in two-step methods while retaining modularity. To achieve this, we adopt a well-trained detector and recognizer that are developed and trained independently and then lock their parameters to preserve their already acquired capabilities. Subsequently, we introduce a Bridge that connects the locked detector and recognizer through a zero-initialized neural network. This zero-initialized neural network, initialized with weights set to zeros, ensures seamless integration of the large receptive field features in detection into the locked recognizer. Further-more, since the fixed detector and recognizer cannot naturally acquire end-to-end optimization features, we adopt the Adapter to facilitate their efficient learning of these features. We demonstrate the effectiveness of the proposed method through extensive experiments: Connecting the latest detector and recognizer through Bridging Text Spotting, we achieved an accuracy of 83.3% on Total-Text, 69.8% on CTW1500, and 89.5% on ICDAR 2015. The code is available at https://***/mxin262/Bridging-Text-Spottinge

关键词： Bridges Computer vision Codes Text recognition Neural networks Detectors Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Towards Modern image Manipulation Localization: A Large-Scale Dataset and Novel Methods

Towards Modern Image Manipulation Localization: A Large-Scal...

引用

Conference on Computer Vision and Pattern recognition (CVPR)

作者： Chenfan Qu Yiwu Zhong Chongyu Liu Guitao Xu Dezhi Peng Fengjun Guo Lianwen Jin South China University of Technology University of Wisconsin INTSIG Information Co. Ltd INTSIG-SCUT Joint Lab on Document Analysis and Recognition

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

In recent years, image manipulation localization has attracted increasing attention due to its pivotal role in guaranteeing social media security. However, how to accurately identify the forged regions remains an open challenge. One of the main bottlenecks lies in the severe scarcity of high-quality data, due to its costly creation process. To address this limitation, we propose a novel paradigm, termed as CAAA, to automatically and precisely annotate the numerous manually forged images from the web at the pixel level. We further propose a novel metric QES to facilitate the automatic filtering of unreliable annotations. With CAAA and QES, we construct a large-scale, diverse, and high-quality dataset comprising 123,150 manually forged images with mask annotations. Besides, we develop a new model APSC-Net for accurate image manipulation localization. According to extensive experiments, our dataset significantly improves the performance of various models on the widely-used benchmarks and such improvements are attributed to our proposed effective methods. The dataset and code are publicly available at https://***/qcf-568/MIML.

关键词： Location awareness Measurement Annotations Social networking (online) Filtering Computational modeling Forensics

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：