检索结果-内蒙古大学图书馆

2nd IEEE International Conference on Signal, information and Data processing, ICSIDP 2024

作者： Wang, Shu Han, Jianhong Wang, Ying Hao, Xinyuan Luo, Zhaoyi Wang, Yupei Chen, Liang Beijing Institute of Technology National Key Laboratory for Science and Technology on Space-Born Intelligent Information Processing Beijing China Shanghai Academy of Spaceflight Technology Shanghai China

ISBN: (纸本)9798331515669

Unsupervised Domain Adaptation (UDA) techniques are crucial for remote sensing object detection, designed to address performance degradation caused by the domain gap between training and test data. These methods leverage unlabeled target domain data, thus alleviating the high costs associated with data annotation. Recent developments in Detection Transformers (DETR) have simplified the detection pipeline and attracted significant research interest. Building on this architecture, we introduce an unsupervised domain adaptation detector for remote sensing object detection. Specifically, we introduce a multi-view adaptive feature alignment module that initially captures domain-specific features in complex backgrounds by leveraging a cross-attention mechanism. Subsequently, we employ contrastive learning to enforce the aggregation of domain-specific features from various perspectives, thereby improving the accuracy of feature alignment. Moreover, we demonstrate that integrating the self-training framework into DETR-based detectors can significantly mitigate the domain gap by further utilizing unlabeled data in the target domain. We validated the effectiveness and generalizability of our method across two remote sensing cross-domain detection scenarios using four public datasets. © 2024 IEEE.

关键词： object detection remote sensing imagery Unsupervised domain adaptation

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Table-to-Text Generation with Structural Bias Attention 20th

Few-Shot Table-to-Text Generation with Structural Bias Atten...

引用

20th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2023

作者： Liu, Di Wang, Weihua Bao, Feilong Gaov, Guanglai College of Computer Science Inner Mongolia University Hohhot China National and Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Hohhot China Inner Mongolia Key Laboratory of Mongolian Information Processing Technology Hohhot China

ISBN: (纸本)9789819970216

Table-to-text generation task refers to converting tabular data into language text to facilitate easier understanding and analysis of the table. Recently, pre-trained models have made significant advancements in this kind of tasks. However, the inherent structural differences between tabular data and text, and the lack of domain-specific knowledge in few-shot datasets, make it challenging for pre-trained models to generate faithful text. To solve these problems, we proposed a framework that encodes tables by obtaining structural bias attention through pruning full self-attention, distinguishing the importance of cells from a structural perspective. We use the pre-trained model with the structural bias framework to the generation component of Prototype-to-Generation. To encourage prototype memory to adhere to the table content and generate more accurate and aligned sentences, we employ Reinforcement Learning. We conducted extensive experiments on three few-shot table datasets. Compared to previous advanced methods, our model achieved superior performance across multiple evaluation metrics. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Pretrained Models and Evaluation Data for the Khmer Language

引用

Tsinghua Science and Technology 2022年第4期27卷 709-718页

作者： Shengyi Jiang Sihui Fu Nankai Lin Yingwen Fu School of Information Science and Technology Guangdong University of Foreign StudiesGuangzhou 510000China Guangzhou Key Laboratory of Multilingual Intelligent Processing Guangdong University of Foreign StudiesGuangzhou 510000China

Trained on a large corpus,pretrained models(PTMs)can capture different levels of concepts in context and hence generate universal language representations,which greatly benefit downstream natural language processing(NLP)*** recent years,PTMs have been widely used in most NLP applications,especially for high-resource languages,such as English and ***,scarce resources have discouraged the progress of PTMs for low-resource ***-based PTMs for the Khmer language are presented in this work for the first *** evaluate our models on two downstream tasks:Part-of-speech tagging and news *** dataset for the latter task is *** demonstrate the effectiveness of the Khmer *** addition,we find that the current Khmer word segmentation technology does not aid performance *** aim to release our models and datasets to the community in hopes of facilitating the future development of Khmer NLP applications.

关键词： pretrained models Khmer language word segmentation part-of-speech(POS)tagging news categorization

来源：评论

学校读者我要写书评

暂无评论

Covert Communication-Assisted Computation Offloading Schemes in Blockchain-Enabled IoT*

Covert Communication-Assisted Computation Offloading Schemes...

引用

2023 International Conference on Networking and Network Applications, NaNA 2023

作者： Wang, Yutong Jiang, Yu'e Feng, Yu University Key Laboratory of Intelligent Perception and Computing of Anhui Province School of Computer and Information Anqing Normal University Anqing China

ISBN: (纸本)9798350327380

Blockchain-enabled Internet of Things (IoT) can ensure security and trust in distributed environments through consensus mechanisms, becoming important application scenarios for secure computation offloading of smart devices. In the IoT, smart devices usually upload complex computing tasks to the base station (BS), and then obtain corresponding mobile edge computing (MEC) servers to perform computing tasks. However, considering the broadcast characteristics of wireless links and the limited resources of smart devices, task upload links with weak security protection are easy to be monitored by adversaries. Since traditional information encryption technology and physical layer security (PLS) technology focus on protecting information content, the existence of upload links is difficult to be protected, which may attract potential adversaries to launch serious attacks after discovering links. Due to the fact that physical layer covert communications aim to complete information transmission without being discovered by adversaries, we propose covert communication-assisted computation offloading schemes in blockchain-enabled IoT for smart devices. The energy consumption of the computation offload schemes is optimized while ensuring the covertness of the task upload link, the matching satisfaction of sensors and MEC servers. Numerical results show that the proposed schemes can obtain the maximum effective covert rate while reducing the energy consumption of computation offloading. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Virtual Machine Migration Algorithm in Data Centers 3

Energy-Efficient Virtual Machine Migration Algorithm in Data...

引用

3rd International conference on Computer, Big Data and Artificial Intelligence, ICCBDAI 2022

作者： Wu, Xiaodong Zeng, Taisheng School of Mathmatics and Computer Science Quanzhou Normal University Fujian Province Quanzhou362000 China Fujian Provincial Key Laboratory of Intensive Computing Fujian Province Quanzhou362000 China Key Laboratory of Intelligent Computing and Information Processing Fujian Province University Fujian Province Quanzhou362000 China

The issue of data center power consumption is becoming increasingly serious. One of the most effective techniques for increasing resource utilization and lowering power consumption is virtual machine consolidation. This paper proposes a threshold-based energy-efficient and SLA-aware algorithm for virtual machine migration and consolidation. Based on statistics and analysis of historical virtual machine status, the algorithm dynamically obtains the upper CPU utilization threshold of the physical servers and identifies whether to perform the virtual machine migration, so as to reduce the number of active hosts to save energy. The experimental results demonstrate that the proposed algorithm has better comprehensive performance. When compared to the existing algorithm, our method can effectively decrease energy consumption and SLA violations. © Published under licence by IOP Publishing Ltd.

关键词： Electric power utilization

来源：评论

学校读者我要写书评

暂无评论

Lightweight spatial pyramid pooling network for real-time semantic segmentation

Lightweight spatial pyramid pooling network for real-time se...

引用

2021 International Symposium on intelligent Robotics and Systems, ISoIRS 2021

作者： Jiang, Peilong Ke, Xiao Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing College of Computer and Data Science Fuzhou University Fuzhou350116 China

In recent years, the state-of-the-art semantic segmentation models have made extremely successful in various challenging scenes. However, the high computation costs of these models make it difficult to deploy to mobile devices. To better serve in computation constraint scenes, the semantic segmentation model should not only have high segmentation performance, but also fast inference speed. In this paper, we proposed an efficient multi-scale context module named LSPPM, which can gather abundant context information at a low computation cost. Base on this, we present a real-time semantic segmentation model called LSPPNet which is specially designed for real-time application. We have done an exhaustive experiment to evaluate LSPPNet in the challenge urban street scenes datasets Cityscapes. Extensive experiment shows that LSPPNet gets a better trade-off between segmentation performance and inference speed. We test LSPPNet on an NVIDIA 2080 super graphics card and it can achieve 75.8% MIoU in Cityscapes test set in real-time speed. © Published under licence by IOP Publishing Ltd.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Solo Adaptation for Distributed Synchronization With Application to Event-Triggered Linear Multi-Agent Systems

引用

IEEE Transactions on Automatic Control 2025年第6期70卷 4225-4232页

作者： Chen, Ci Zheng, Zhiyang Lewis, Frank L. Xie, Kan Xie, Shengli Guangdong University of Technology Guangdong Provincial Key Laboratory of Intelligent Systems and Optimization Integration Key Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of Education School of Automation Guangzhou510006 China Guangdong University of Technology School of Automation Guangdong Guangzhou510006 China The University of Texas at Arlington UTA Research Institute Fort Worth76118 United States Guangdong University of Technology 111 Center for Intelligent Batch Manufacturing Based on IoT Technology School of Automation Guangzhou China Guangdong University of Technology Key Laboratory of Intelligent Detection and The Internet of Things in Manufacturing Ministry of Education School of Automation Guangzhou510006 China

We study a solo adaptation-based protocol design problem for distributed synchronization of event-triggered linear multi-agent systems (MAS) over general directed graphs. We show that a solo adaptive gain, a locally static control gain matrix, and a distributed state measurement are sufficient for obtaining adaptive distributed synchronization of linear MAS over directed graphs without any prior knowledge of the global communication network. We then extend the solo adaptation structure to formulate an event-triggered synchronization control protocol. The main feature of our result is that the time for triggering a subsequent event is now computed using the distributed event-triggered state measurement, rather than the continuous-time state measurement. © 1963-2012 IEEE.

关键词： Continuous time systems

来源：评论

学校读者我要写书评

暂无评论

Knowledge Graph-Enhanced Recommendation with Box Embeddings 23

引用

23rd Chinese National Conference on Computational Linguistics, CCL 2024

作者： Liang, Qiuyu Wang, Weihua Lv, Lei Bao, Feilong College of Computer Science Inner Mongolia University Hohhot China National and Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Hohhot China Inner Mongolia Key Laboratory of Mongolian Information Processing Technology Hohhot China

ISBN: (纸本)9780000000002

Knowledge graphs are used to alleviate the problems of data sparsity and cold starts in recommendation systems. However, most existing approaches ignore the hierarchical structure of the knowledge graph. In this paper, we propose a box embedding method for knowledge graph-enhanced recommendation system. Specifically, the box embedding represents not only the interaction between the user and the item, but also the head entity, the tail entity and the relation between them in the knowledge graph. Then the interaction between the item and the corresponding entity is calculated by the multi-task attention unit. Experimental results show that our method provides a large improvement over previous models in terms of Area Under Curve (AUC) and accuracy in publicly available recommendation datasets with three different domains. © 2024 China National Conference on Computational Linguistics.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Contrastive Subspace Clustering with Dissimilarity Regularization

Contrastive Subspace Clustering with Dissimilarity Regulariz...

引用

2023 International Conference on Machine Learning and Cybernetics, ICMLC 2023

作者： Chen, Yu-Jie Wu, Wen-Hui Ou-Yang, Le College of Electronics and Information Engineering Shenzhen University Shenzhen518060 China Shenzhen University Guangdong Key Laboratory of Intelligent Information Processing Shenzhen518060 China

ISBN: (纸本)9798350303780

Subspace Clustering (SC) aims at clustering the data according to its underlying subspaces. However, existing subspace clustering methods fail to make full use of available information. Inspired by advances that contrastive learning has achieved in unsupervised representation learning, we propose a method, namely contrastive subspace clustering with dissimilarity regularization (CSCDR), incorporating contrastive learning into subspace clustering. Specifically, we first construct another view of data through augmentation. Then, the deep subspace clustering networks (DSC-Nets) are used to learn the self-expressive coefficients of data and its augmentation, which further interact with each other by contrastive learning. Moreover, a dissimilarity matrix is formulated based on the latent feature of data to further calibrate the noisy connections in the self-expressive coefficient. And we also utilize the relevant similarity matrix contributing to the multi-positive contrasitve learning, which ameliorates the cluster-collapse problem of representation. Experimental results on several data sets demonstrate the efficacy of the proposed method. © 2023 IEEE.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

Guided-YNet: Saliency Feature-Guided Interactive Feature Enhancement Lung Tumor Segmentation Network

引用

Computers, Materials & Continua 2024年第9期80卷 4813-4832页

作者： Tao Zhou Yunfeng Pan Huiling Lu Pei Dang Yujie Guo Yaxing Wang School of Computer Science and Engineering North Minzu UniversityYinchuan750021China School of Medical Information&Engineering Ningxia Medical UniversityYinchuan750004China Key Laboratory of Image and Graphics Intelligent Processing of State Ethnic Affairs Commission NorthMinzuUniversityYinchuan750021China

Multimodal lung tumor medical images can provide anatomical and functional information for the same *** as Positron Emission Computed Tomography(PET),Computed Tomography(CT),and *** to utilize the lesion anatomical and functional information effectively and improve the network segmentation performance are key *** solve the problem,the Saliency Feature-Guided Interactive Feature Enhancement Lung Tumor Segmentation Network(Guide-YNet)is proposed in this ***,a double-encoder single-decoder U-Net is used as the backbone in this model,a single-coder single-decoder U-Net is used to generate the saliency guided feature using PET image and transmit it into the skip connection of the backbone,and the high sensitivity of PET images to tumors is used to guide the network to accurately locate ***,a Cross Scale Feature Enhancement Module(CSFEM)is designed to extract multi-scale fusion features after ***,a Cross-Layer Interactive Feature Enhancement Module(CIFEM)is designed in the encoder to enhance the spatial position information and semantic ***,a Cross-Dimension Cross-Layer Feature Enhancement Module(CCFEM)is proposed in the decoder,which effectively extractsmultimodal image features through global attention and multi-dimension local *** proposed method is verified on the lung multimodal medical image datasets,and the results showthat theMean Intersection overUnion(MIoU),Accuracy(Acc),Dice Similarity Coefficient(Dice),Volumetric overlap error(Voe),Relative volume difference(Rvd)of the proposed method on lung lesion segmentation are 87.27%,93.08%,97.77%,95.92%,89.28%,and 88.68%,*** is of great significance for computer-aided diagnosis.

关键词： Medical image segmentation U-Net saliency feature guidance cross-modal feature enhancement cross-dimension feature enhancement

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：