检索结果-内蒙古大学图书馆

lab.l distribution learning for scene text detection

Frontiers of computer Science 2023年第6期17卷 5-12页

作者： Haoyu MA Ningning LU Junjun MEI Tao GUAN Yu ZHANG Xin GENG School of Computer Science and Engineering and the Key Lab of Computer Network and Information Integration(Ministry of Education)Southeast UniversityNanjing 211189China ZTE Corporation Nanjing 210012China

Recently,segmentation-based scene text detection has drawn a wide research interest due to its flexibility in describing scene text instance of arbitrary shapes such as curved ***,existing methods usually need complex post-processing stages to process ambiguous lab.ls,i.e.,the lab.ls of the pixels near the text boundary,which may belong to the text or *** this paper,we present a framework for segmentation-based scene text detection by learning from ambiguous *** use the lab.l distribution learning method to process the lab.l ambiguity of text annotation,which achieves a good performance without using additional post-processing *** on benchmark datasets demonstrate that our method produces better results than state-of-the-art methods for segmentation-based scene text detection.

关键词： scene text detection multi-task learning lab.l distribution learning

来源：评论

学校读者我要写书评

暂无评论

Robust Hashing with Deep Features and Meixner Moments for Image Copy Detection

引用

ACM Transactions on Multimedia Computing, Communications and Applications 2024年第12期20卷 1-23页

作者： Yu, Mengzhu Tang, Zhenjun Liang, Xiaoping Zhang, Xianquan Li, Zhixin Zhang, Xinpeng Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Key Lab of Multi-Source Information Mining and Security Guangxi Normal University Guilin China School of Computer Science Fudan University Shanghai China

Copy detection is a key task of image copyright protection. Most robust hashing schemes do not make satisfied performance of image copy detection yet. To address this, a robust hashing scheme with deep features and Meixner moments is proposed for image copy detection. In the proposed hashing, global deep features are extracted by applying tensor Singular Value Decomposition (t-SVD) to the three-order tensor constructed in the DWT domain of the feature maps calculated by the pre-trained VGG16. Since the feature maps in the DWT domain are slightly disturbed by digital operations, the constructed three-order tensor is stable and thus the desirable robustness is guaranteed. Moreover, since t-SVD can decompose a three-order tensor into multiple low-dimensional matrices reflecting intrinsic structure, the global deep feature calculation from the low-dimensional matrices can provide good discrimination. Local features are calculated by the block-based Meixner moments. As the Meixner moments are resistant to geometric transformation and can efficiently discriminate various images, the use of the block-based Meixner moments can make discriminative and robust local features. Hash is ultimately determined by quantifying and combining global deep features and local features. The results of extensive experiments on open image datasets demonstrate that the proposed robust hashing outperforms some state-of-the-art robust hashing schemes in terms of classification and copy detection performances. © 2024 Copyright held by the owner/author(s).

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

Fusion of Time-Frequency Features in Contrastive Learning for Shipboard Wind Speed Correction

引用

Journal of Ocean University of China 2025年第2期24卷 377-386页

作者： SONG Jian HUANG Meng LI Xiang ZHANG Zhenqiang WANG Chunxiao ZHAO Zhigang Key Laboratory of Computing Power Network and Information Security Ministry of EducationShandong Computer Science Center(National Supercomputer Center in Jinan)Qilu University of Technology(Shandong Academy of Sciences)Jinan 250000China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer ScienceJinan 250000China

Accurate wind speed measurements on maritime vessels are crucial for weather forecasting,sea state prediction,and safe ***,vessel motion and challenging environmental conditions often affect measurement *** address this issue,this study proposes an innovative framework for correcting and predicting shipborne wind *** integrating a main network with a momentum updating network,the proposed framework effectively extracts features from the time and frequency domains,thereby allowing for precise adjustments and predictions of shipborne wind speed *** using real sensor data collected at the Qingdao Oceanographic Institute demonstrates that the proposed method outperforms existing approaches in single-and multi-step predictions compared to existing methods,achieving higher accuracy in wind speed *** proposed innovative approach offers a promising direction for future validation in more realistic maritime onboard scenarios.

关键词： time series prediction wind speed correction comparative learning shipborne sensor

来源：评论

学校读者我要写书评

暂无评论

Cross-chain Transaction Tracking Protocol based on Multi-dimensional Digital Watermarking Fingerprints 6

Cross-chain Transaction Tracking Protocol based on Multi-dim...

引用

6th International Conference on Frontier Technologies of information and computer, ICFTIC 2024

作者： Li, Duanzhen Xu, Shujiang He, Haochen Xue, Hongrui Key Laboratory of Computing Power Network and Information Security Ministry of Education Jinan250014 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Industrial Network and Information System Security Jinan250014 China

ISBN: (纸本)9798331541750

Cross-chain technology plays a critical role in the process of interconnecting blockchains. However, all attention has been focused on how to achieve efficient cross-chain interoperability protocols, thus neglecting the most important security issues in cross-chain data interaction. Frequent network attacks and data privacy leaks have sounded the alarm for the safety of cross-chain data transactions. How to solve the problem of data ownership tracking in cross-chain transactions has become the top priority. This paper designs a cross-chain transaction tracking protocol based on multi-dimensional digital watermark fingerprints, using robust watermark, fragile watermark, and user identity key to achieve multi-dimensional tracking and supervision of cross-chain data transactions. Finally, this paper analyzes the feasibility and efficiency of the proposed protocol through experiments. © 2024 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

The Study of Multi-type Computing Power Trading Mechanism in Computing Power network Based on Blockchain and Combinatorial Double Auction 24

The Study of Multi-type Computing Power Trading Mechanism in...

引用

4th International Conference on Artificial Intelligence, Big Data and Algorithms, CAIBDA 2024

作者： Zhao, Yue Wang, Jizhi Kong, Lingrui Sui, Tongtong Shandong Computer Science Center National Supercomputer Center in Jinan Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Provincial Key Laboratory of Industrial Network and Information System Security Qilu University of Technology Shandong Academy of Sciences Jinan Shandong China Quancheng Laboratory Jinan Key Laboratory of Digital Security Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center National Supercomputer Center in Jinan Qilu University of Technology Shandong Academy of Sciences Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan Shandong China

ISBN: (纸本)9798400710247

The advancement of 5G and mobile internet technologies has propelled the development of emerging businesses and applications, demanding higher requirements for network bandwidth and computational resources. To address this challenge, the computing power network (CPN) has emerged. The CPN integrates computing and networking in depth, achieving collab.rative allocation of distributed computing resources, enhancing the efficient utilization of computing resources, and improving user experiences in network services. However, in the development of fields such as Extended Reality (XR), Smart Healthcare, Connected Vehicles, and Artificial Intelligence (AI), there is a multidimensional, complex, and rapidly growing demand for computing resources. Therefore, it is crucial to establish a trading mechanism that integrates multiple computing resources in CPN. In this paper, a computing power trading scheme based on blockchain and combinatorial double auction is proposed. Firstly, a computing power trading system based on blockchain was designed, leveraging the decentralized and highly secure characteristics of blockchain technology to enhance the security of computing power transactions. Furthermore, a multi-type computing power trading mechanism (MCPT) based on blockchain and combinatorial double auction was introduced. The use of combinatorial double auctions as an incentive mechanism enables the trading of multiple computing power resources and results in high social welfare. Moreover, a discrete rime optimization algorithm (DRIME) is designed in the proposed mechanism (MCPT) to better solve the computing trading problem. Through simulation experiments, the effectiveness of the approach is validated. © 2024 Copyright held by the owner/author(s).

关键词： Computing power

来源：评论

学校读者我要写书评

暂无评论

BTP-CAResNet: An Encrypted Traffic Classification Method Based on Byte Transfer Probability and Coordinate Attention Mechanism

BTP-CAResNet: An Encrypted Traffic Classification Method Bas...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Li, Junhao Shi, Huiling Zhang, Wei Key Laboratory of Computing Power Network and Information Security Ministry of Education Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (纸本)9781665410205

With the extensive application of network traffic encryption technology, the accurate and efficient classification of encrypted traffic has become a critical need for network management. Deep learning has become the predominant method for traffic classification, primarily involving the transformation of network traffic into grayscale images and their subsequent classification using Convolutional Neural networks (CNNs). However, traditional grayscale image generation methods are plagued with issues of redundant and lost information, and conventional channel attention mechanisms are still insufficient in capturing key traffic features, collectively hindering the enhancement of classification performance. To tackle these issues, this paper introduces a classification method based on Byte Transfer Probability and Coordinate Attention Mechanism in Residual network (BTP-CAResNet). This method, on the foundation of the classic ResNet architecture, incorporates a new grayscale image generation method that utilizes Byte Transfer Probability, effectively overcoming the deficiencies of traditional approaches. Additionally, this paper integrates a Coordinate Attention Mechanism into the ResNet model, which effectively overcomes the limitations of traditional channel attention mechanisms and further improves the performance of traffic classification. Experimental validation on the ISCX VPN-nonVPN dataset demonstrates that, compared to previous CNN-based methods, the method proposed in this paper exhibits superior performance in key metrics such as accuracy, precision, recall, and F1 score. It provides a new perspective for traffic classification based on convolutional neural networks. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

RFSD-YOLO: An Enhanced X-Ray Object Detection Model for Prohibited Items

RFSD-YOLO: An Enhanced X-Ray Object Detection Model for Proh...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Kong, Xiaotong Li, Aimin Li, Wenqiang Li, Zhiyao Zhang, Yuechen Key Laboratory of Computing Power Network and Information Security Ministry of Education Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan China

ISBN: (纸本)9781665410205

X-ray image detection is essential for ensuring public safety, but traditional methods rely heavily on human analysis and are relatively inefficient. To address this issue, this paper proposes a new object detection model called RFSD-YOLO, which is based on the YOLOv8 model and is specifically designed for detecting prohibited items in X-ray images. The model adopts the RFCAConv structure instead of the conventional convolutional operation. This allows for independent parameterisation among the convolutional kernels, enhancing the model's ability to capture and express potential prohibited item features. The neck section of the model includes the GSConv and VoVgscspdesigns, which aim to balance complexity and parameter size while maintaining detection performance and reducing computational burden. Additionally, we have introduced a dynamic head structure, DyHead, which replaces the traditional detection head design and improves detection accuracy without adding computational cost. The experimental results demonstrate that our enhanced model surpasses the current state-of-the-art object detection models in detecting prohibited items. Additionally, we introduce a simplified version of the RFSD-YOLOnano model to cater to resource-constrained environments. This streamlined model improves AP, AR, and mAP by 4.4%, 14.6%, and 3.4%, respectively, compared to YOLOv8n. This series of innovations not only validates the superiority of our model, but also provides new solutions in the field of automated detection of prohibited items for X-ray security screening. © 2024 IEEE.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

CB-YOLO: A Small Object Detection Algorithm for Industrial Scenarios

CB-YOLO: A Small Object Detection Algorithm for Industrial S...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Chen, Hao Wu, Xiaoming Su, Zhanzhi Zhao, Ying Dong, Yunfeng Liu, Xiangzhi Key Laboratory of Computing Power Network and Information Security Ministry of Education Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (纸本)9781665410205

In certain specific industrial scenarios, smoking and cellphone usage are strictly prohibited behaviors. In these scenarios, it is crucial to rapidly and accurately detect smoking and cell phone usage, and promptly issue warnings, to ensure industrial safety. The detection of prohibited behaviors using computer vision has gained attention from researchers with the development of artificial intelligence. However, detecting small objects like cigarettes and cell phones in complex backgrounds and varying angles poses a challenge due to their changing shapes. In this paper, we propose a detection model called CB-YOLO, which utilizes YOLOv7 as the baseline model, for detecting smoking and mobile phone usage behavior. Firstly, we propose a new channel space pyramid network called CSPPF that pools features at different scales and introduces scale focusing on improving the perceptual ability of the network to better handle targets at various scales and locations. Secondly, we propose an enhanced feature pyramid called AWBFPN. This introduces additional learnable weight parameters to improve the model's ability to fuse multi-scale features effectively. Finally, we have also proposed a new loss function called Size-IoU. The experimental results demonstrate that our algorithm outperforms the baseline model. Specifically, it achieves a 3.9% improvement in Precision, a 2.1% improvement in Recall, a 6.4% improvement in mAP@0.5, and a 2% improvement in mAP@0.5:0.95 on the Phone_check dataset. Similarly, on the Smoking dataset, our algorithm achieves a 3.3% improvement in Precision, a 1.9% improvement in Recall, a 1.7% improvement in mAP@0.5, and a 0.3% improvement in mAP@0.5:0.95. © 2024 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

MUNE: A Multi-Level User-News Embedding Model for Personalised News Recommendations 24

MUNE: A Multi-Level User-News Embedding Model for Personalis...

引用

8th International Conference on computer Science and Artificial Intelligence, CSAI 2024

作者： Long, Haixiang Luo, Xudong School of Computer Science and Engineering Guangxi Key Lab of Multi-Source Information Mining & Security Key Lab of Education Blockchain and Intelligent Technology of Ministry of Education Guangxi Normal University Guangxi Guilin China

ISBN: (纸本)9798400718182

Personalised news recommendation systems are critical for delivering relevant content, but effectively capturing and modelling users’ diverse and evolving interests is challenging. In this paper, we introduce a Multi-level User-News Embedding (MUNE) model for personalised news recommendations. MUNE uses pre-trained BERT embeddings to generate contextual representations, enabling dynamic, multi-level interaction modelling between users and candidate news. It incorporates a Dynamic Multi-Level Interaction Attention (DMIA) module for capturing complex interactions and a Dynamic Similarity Unit (DSU) for enhancing feature fusion using cosine similarity and non-linear transformations. Evaluated on large-scale datasets (MIND and EB-NeRD), MUNE significantly outperforms state-of-the-art baselines in key metrics, with ablation studies validating the importance of DMIA and DSU in improving user interest modelling and recommendation quality. MUNE’s integration of multi-level features makes it highly effective in capturing user behaviours and understanding news content. © 2024 Copyright held by the owner/author(s).

关键词： Linear transformations

来源：评论

学校读者我要写书评

暂无评论

DP-GenFL: a local differentially private federated learning system through generative data

引用

Science China(information Sciences) 2023年第8期66卷 275-276页

作者： Jun LI Kang WEI Chuan MA Feng SHU School of Electronic and Optical Engineering Nanjing University of Science and Technology Zhejiang Lab Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education School of Information and Communication Engineering Hainan University

With the rapid development of the Internet of Things(Io T),the amount of data from intelligent devices is propagating at unprecedented scales. Meanwhile, machine learning(ML),which relies heavily on such data, is revolutionizing many aspects of our lives [1]. However, conventional centralized ML offers little scalab.lity for efficiently processing this huge amount of data.

关键词： Learning systems

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：