检索结果-内蒙古大学图书馆

information disentanglement for unsupervised domain adaptive oracle bone inscriptions detection

Signal processing: Image Communication 2025年 138卷

作者： Gao, Feng Liu, Yongge Li, Deng Chen, Xu Jiang, Runhua Han, Yahong School of Computer and Information Engineering Anyang Normal University Henan Anyang455000 China Key Laboratory of Oracle Bone Inscriptions Information Processing Ministry of Education Henan Anyang455000 China College of Intelligence and Computing Tianjin University Tianjin300350 China

The detection of oracle bone inscriptions (OBIs) is the foundation of studying the OBIs via computer technology. oracle bone inscription data includes rubbings, handwriting, and photos. Currently, most detection methods primarily focus on rubbings and rely on large-scale annotated datasets. However, it is necessary to detect oracle bone inscriptions on both handwriting and photo domains in practical applications. Additionally, annotating handwriting and photos is time-consuming and requires expert knowledge. An effective solution is to directly transfer the knowledge learned from the existing public dataset to the unlabeled target domain. However, the domain shift between domains heavily degrades the performance of this solution. To alleviate this problem and based on the characteristics of different domains of oracle bone, in this paper, we propose an information disentanglement method for the Unsupervised Domain Adaptive (UDA) OBIs detection to improve the detection performance of OBIs in both handwriting and photos. Specifically, we construct an image content encoder and a style encoder module to decouple the oracle bone image information. Then, a reconstruction decoder is constructed to reconstruct the source domain image guided by the target domain image information to reduce the shift between domains. To demonstrate the effectiveness of our method, we constructed an OBI detection benchmark that contains three domains: rubbing, handwriting, and photo. Extensive experiments verified the effectiveness and generality of our method on domain adaptive OBIs detection. Compared to other state-of-the-art UDAOD methods, our approach achieves an improvement of 0.5% and 0.6% in mAP for handwriting and photos, respectively. © 2025 Elsevier B.V.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Graph Contrastive Learning with Decoupled Augmentation

Graph Contrastive Learning with Decoupled Augmentation

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal processing, ICASSP 2025

作者： Gao, Shihao Li, Caoshuo Mao, Cunli Zhang, Xulong Qu, Xiaoyang Jin, Taisong Wang, Jianzong Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China School of Informatics Xiamen University China Faculty of Information Engineering and Automation Kunming University of Science and Technology China Yunnan Key Laboratory of Artificial Intelligence Kunming University of Science and Technology China Key Laboratory of Oracle Bone Inscriptions Information Processing Ministry of Education of China Anyang Normal University China Ping An Technology Co. Ltd. Shenzhen China

ISBN: (纸本)9798350368741

Graph contrastive learning based on augmentation strategies has recently demonstrated remarkable performance. Existing methods typically jointly leverage attribute and structural augmentations to generate graph views, learning data invariance information through contrasting sample pairs. However, this joint approach may deviate from the expectation of semantically similar before and after augmentation. The propagation of attribute information in graphs usually occurs through their structure, meaning that structural and attribute augmentations can interfere with each other and potentially distort the graph's semantics. To address this, we propose a decoupled augmentation framework for graph contrastive learning, which eliminates the mutual interference between the two levels of augmentation while fully exploring graph information. Specifically, our framework employs separate encoders to learn data invariance under different augmentation levels, and it considers the positive gains generated between these levels. Experimental results on five public datasets show that the proposed method is more competitive than state-of-the-art approaches. © 2025 IEEE.

关键词： Contrastive learning Graph representation Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

oracle Character Prototype-Guided Cyclic Disentanglement for oracle bone inscriptions Detection 4th

Oracle Character Prototype-Guided Cyclic Disentanglement for...

引用

4th International Conference on Pattern Recognition and Artificial Intelligence, ICPRAI 2024

作者： Li, Bang Zhang, Jingping Yu, Nana Zhang, Zihao Liu, Yongge Han, Yahong School of Computer and Information Engineering Anyang Normal University Anyang455000 China Key Laboratory of Oracle Bone Inscriptions Information Processing Ministry of Education Anyang455000 China Digital Media Art Department Shanghai Theatre Academy Shanghai200040 China Key Laboratory of Integrated Innovation of Digital Performing Arts Ministry of Culture and Tourism Shanghai200040 China College of Intelligence and Computing Tianjin University Tianjin300072 China

ISBN: (纸本)9789819787043

oracle bone inscriptions (OBI), as the oldest form of Chinese writing, bears the precious heritage of ancient Chinese civilization. Deciphering OBI has been a monumental challenge in archaeology and philology. However, the preservation method of OBI through rubbings faces significant challenges due to severe noise interference, adversely affecting the accuracy of OBI detection. Additionally, existing traditional object detection algorithms inadequately consider the unique characteristics of OBI, making it difficult to effectively identify oracle characters on OBI rubbings. To address these challenges, this paper proposes a novel approach to OBI detection, oracle Character Prototype-guided cyclic disentanglement for OBI detection. These features are amalgamated into distinct character structure prototypes by capturing shared character structure features among different oracle characters. This approach highlights the distinctive forms of oracle characters, enhancing feature clarity and recognition. The oracle Character Prototypes enable the model to learn common features across different character forms, improving its adaptability to various oracle character structures and enhancing its capability to handle complexity. Moreover, to mitigate the impact of noise on detection, we introduce a cyclic disentanglement method for oracle bone inscriptions. This process, utilizing the oracle Character Prototypes and contrastive loss as supervisory signals, cyclically decouples oracle features, isolating information rich in character structure features. This effectively mitigates the influence of noise on OBI detection. Comprehensive evaluations were conducted, comparing our method with state-of-the-art object detection algorithms, validating its effectiveness both qualitatively and quantitatively. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Graph Contrastive Learning with Decoupled Augmentation

Graph Contrastive Learning with Decoupled Augmentation

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Shihao Gao Caoshuo Li Cunli Mao Xulong Zhang Xiaoyang Qu Taisong Jin Jianzong Wang Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China School of Informatics Xiamen University China Ping An Technology Co. Ltd. Shenzhen China Faculty of Information Engineering and Automation Kunming University of Science and Technology China Yunnan Key Laboratory of Artificial Intelligence Kunming University of Science and Technology China Key Laboratory of Oracle Bone Inscriptions Information Processing Ministry of Education of China Anyang Normal University China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Graph contrastive learning based on augmentation strategies has recently demonstrated remarkable performance. Existing methods typically jointly leverage attribute and structural augmentations to generate graph views, learning data invariance information through contrasting sample pairs. However, this joint approach may deviate from the expectation of semantically similar before and after augmentation. The propagation of attribute information in graphs usually occurs through their structure, meaning that structural and attribute augmentations can interfere with each other and potentially distort the graph’s semantics. To address this, we propose a decoupled augmentation framework for graph contrastive learning, which eliminates the mutual interference between the two levels of augmentation while fully exploring graph information. Specifically, our framework employs separate encoders to learn data invariance under different augmentation levels, and it considers the positive gains generated between these levels. Experimental results on five public datasets show that the proposed method is more competitive than state-of-the-art approaches.

关键词： Acoustic distortion Semantics Contrastive learning Interference Signal processing Acoustics Speech processing

来源：评论

学校读者我要写书评

暂无评论

Enhanced oracle bone corrosion detection using attention-guided YOLO with ghost convolution

引用

Discover Artificial Intelligence 2024年第1期4卷 1-13页

作者： Gao, Feng Yang, Ziheng Liu, Qiyu Zhang, Zhan Li, Bang Zhang, Han Key Laboratory of Oracle Bone Inscriptions Information Processing Ministry of Education Anyang455000 China School of Computer & Information Engineering Anyang Normal University Henan Anyang455000 China

oracle bone inscriptions (OBIs), as the important records of early Chinese characters, possess profound cultural and historical significance. However, These fragments are susceptible to further damage due to corrosion. Consequently, the identification and localization of corroded regions on these fragments to prevent further deterioration has emerged as a critical task. Current object detection algorithms exhibit limitations in identifying corroded regions on oracle bone fragments, which is manifested by suboptimal detection accuracy, F1 scores, and average precision (AP) values. This deficiency hinders their capability to effectively manage the complexity and diversity of corrosion patterns present on oracle bone fragments. To tackle this challenge, this study incorporates advanced attention mechanisms, including Squeeze-and-Excitation Networks (SE), Coordinate attention, and Convolutional Block Attention Module (CBAM), into the YOLOv5 detection architecture. Additionally, we introduce Ghost convolution into the backbone network to effectively retain critical feature map information while optimizing computational efficiency. Our experimental results indicate that the integration of CBAM attention and Ghost convolution within the YOLOv5 backbone markedly improves the detection accuracy of corroded regions on oracle bone fragments. Specifically, compared to the baseline YOLOv5 model, the proposed models incorporating SE, CBAM, and Ghost convolution obtain the improvements of 2.2%, 6.3%, and 8.5% in AP, respectively. This improvement in detection performance not only facilitates the identification of corroded areas but also contributes to the preservation of oracle bone heritage and the continuity of cultural knowledge. © The Author(s) 2024.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Plasmon-enhanced photoresponse of deep-subwavelength GaAs NW photodetector

引用

Optoelectronics Letters 2021年第7期17卷 385-389页

作者： LI Bang TANG Yanni YAN Xin ZHANG Xia LIU Yongg School of Computer&Information Engineering Anyang Normal UniversityAnyang 455000China Key Laboratory of Oracle Bone Inscriptions Information Processing Ministry of Education of ChinaAnyang 455000China Henan Key Laboratory of Oracle Bone Inscriptions Information Processing Anyang 455000China State Key Laboratory of Information Photonics and Optical Communications Beijing University of Posts and TelecommunicationsBeijing 100876China

According to optical diffraction limit, the photoresponsity of nanowire(NW)-based photodetector exponentially decreases when its NW diameter reduces to the range of deep subwavelength. In this paper, we demonstrate a photoresponse-enhanced method of the deep-subwavelength Ga As NW photodetector by using a plasmon-driven dipole antenna. Considering that the enhancement is extremely influenced by the shape and size of antenna, the structure of antenna is optimized by finite difference time domain(FDTD) solutions. The optimal structure of antenna optimizes the responsivity-enhanced factors to 1123.3 and 224.7 in NW photodetectors with NW diameters of 20 nm and 60 nm, respectively. This photoresponse-enhanced method is promising for easy-integration high-performance nanoscale photodetectors.

关键词： antenna photoresponse photodetector

来源：评论

学校读者我要写书评

暂无评论

Food Material Consumption Prediction of Catering Enterprises Based on Time Series Model 5

Food Material Consumption Prediction of Catering Enterprises...

引用

5th IEEE Advanced information Technology, Electronic and Automation Control Conference, IAEAC 2021

作者： Wang, Nan Liu, Zan Anyang Normal University School of Computer and Information Engineering Anyang455000 China Key Laboratory of Oracle Bone Inscriptions Information Processing Ministry of Education of China Anyang Henan455000 China Key Laboratory of Oracle Information Processing in Henan Province Anyang Henan455000 China

Food material management plays an important role in catering enterprises. Accurately predicting the consumption of each kind of food materials in the future can reduce the cost and improve the operation efficiency of catering enterprises. Based on ARMA and ARIMA models, we took the actual operation data of a big hot pot restaurant as the research object, and tried to forecast the food materials consumption of the restaurant in a relatively short future time. The experimental results show that although there is still room for improvement, the time series model can be used to help the material management of each catering enterprise. © 2021 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

OBC306: A large-scale oracle bone character recognition dataset 15

OBC306: A large-scale oracle bone character recognition data...

引用

15th IAPR International Conference on Document Analysis and Recognition, ICDAR 2019

作者： Huang, Shuangping Wang, Haobin Liu, Yongge Shi, Xiaosong Jin, Lianwen South China University of Technology Anyang Normal University China Henan Key Laboratory of Oracle Bone Inscriptions Information Processing Anyang Normal University China

ISBN: (纸本)9781728128610

The oracle bone script from ancient China is among the world's most famous ancient writing systems. Identifying and deciphering oracle bone scripts is one of the most important topics in oracle bone study and requires a deep familiarity with the culture of ancient China. This task remains very challenging for two reasons. The first is that it is executed mainly by humans and requires a high level of experience, aptitude, and commitment. The second is due to the scarcity of domain-specific data, which hinders the advancement of automatic recognition research. A collection of well-labeled oracle-bone data is necessary to bridge the oracle bone and information processing fields;however, such a dataset has not yet been presented. Hence, in this paper, we construct a new large-scale dataset of oracle bone characters called OBC306. We also present the standard deep convolutional neural network-based evaluation for this dataset to serve as a benchmark. Through statistical and visual analyses, we describe the inherent difficulties of oracle bone recognition and propose future challenges for and extensions of oracle bone study using information processing. This dataset contains more than 300,000 character-level samples cropped from oracle-bone rubbings or images. It covers 306 glyph classes and is the largest existing raw oracle-bone character set, to the best of our knowledge. It is anticipated the publication of this dataset will facilitate the development of oracle bone research and lead to optimal algorithmic solutions. © 2019 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Research on inscription rubbings text detection based on deep learning 2021

Research on inscription rubbings text detection based on dee...

引用

4th International Conference on information Systems and Computer Aided Education, ICISCAE 2021

作者： Song, Xu Liu, Guoying Wang, Zhiyin School of Computer and Information Engineering Anyang Normal University Anyang China Key Laboratory of Oracle Bone Inscriptions Information Processing Ministry of Education Anyang China

ISBN: (纸本)9781450390255

It is of great practical significance to use advanced digital and intelligent technology to digitally apply and effectively protect China's ancient cultural heritage and resolve the problems that cannot be solved by manpower in a faster and more efficient way. Based on the YOLOv4 target detection algorithm, this paper effectively expands the collected data according to the data characteristics of inscription rubbings and text images, and carries out many training and verification tests. The accuracy of the detection model is 92.3%, so as to improve the speed and quality of rubbing arrangement of inscriptions. © 2021 ACM.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

ViT-based Classification of oracle bones for Periodization of the Shang Dynasty

ViT-based Classification of Oracle Bones for Periodization o...

引用

2023 International Conference on Algorithms, High Performance Computing, and Artificial Intelligence, AHPCAI 2023

作者： Li, Bang Ding, Zengmao Zheng, Rongxin Han, Shengwei Zhang, Han Zhang, Zhan Guo, An Wang, Nan Gao, Feng Liu, Yongge School of Computer & Information Engineering Anyang Normal University Henan Anyang455000 China Key Laboratory of Oracle Bone Inscriptions Information Processing Ministry of Education of China Henan Anyang455000 China International Joint Research Laboratory for Perception Data Intelligent Processing of Henan Anyang Normal University Henan Anyang455000 China

ISBN: (纸本)9781510671881

oracle bone inscriptions are the oldest systematically written characters in China, and their periodization and chronology are essential tasks in historical research. However, current deep-learning models face significant challenges when they are used to recognize oracle bone images directly. These models can only achieve an accuracy of no more than 45%. As the research on the periodization of oracle bones mainly relies on the characters inscribed on the bones, a domain knowledge-based oracle bone classification model is proposed that improves the recognition accuracy of Vision Transformer (ViT) by 5.28%. The proposed approach incorporates results obtained from oracle bone character detection to provide a more effective recognition object. Moreover, a novel model with a style network and category embedding is proposed in this paper that focuses on characters, resulting in a notable improvement in recognition accuracy of 16.01%. Our study reveals the importance of domain knowledge in the classification of historical documents, and it presents new insights into using artificial intelligence for assisting in historical document organization tasks. © 2023 SPIE. All rights reserved.

关键词： Domain Knowledge

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：