检索结果-内蒙古大学图书馆

International Joint Conference on Neural networks (IJCNN)

作者： Mingle Zhou Rui Xing Min Li Delong Han Gang Li 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) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Shandong SCICOM Information and Economy Research Institute Co. Ltd Jinan China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

The field weed detection task under the perspective of Plant Protection UAVs (PPU) is characterized by multi-scale targets and rich background semantic information, which belongs to the target detection task in complex scenarios. Blindly boosting the network size and overusing the attention mechanism in such tasks are not effective in improving the model accuracy. The core of the problem lies in the fact that the covariate features of the target are shifted during the transfer of the three layers of image semantic information (visual, object and conceptual layers). This phenomenon is particularly evident at the conceptual level, resulting in models that do not accurately understand the target information. Redundant semantic information and irrational attention mechanisms for complex scenarios are the cause of the problem. In this paper, we propose the Color and Feature Space Classification (CFSC) method, which aims to construct a covariate semantic information matrix that spans the visual, object and conceptual layers. Mitigating the problem of offsetting semantic information of covariate features in complex scenarios. The color and feature space classification method is applied to a one-stage detection model, YOLOv8, and experiments are conducted on three complex scene PPU weed datasets. The experimental results show that the CFSC method can improve the model accuracy, loss computation capability and accelerate the gradient descent.

关键词： Visualization Attention mechanisms Accuracy Image color analysis Computational modeling Semantics Object detection

来源：评论

学校读者我要写书评

暂无评论

A Prediction Method for Atmospheric Monitoring Data Based on Transformer and GAN

A Prediction Method for Atmospheric Monitoring Data Based on...

引用

IEEE Information technology, networking, Electronic and Automation Control Conference

作者： Hongge Zhao Jingli Wang Tixiang Zhang Huijuan Hao 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) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Jinan Eco-environmental Bureau Pingyin Branch Office Jinan China Shandong Unite Environmental Technology Co Jinan China

ISBN: (数字)9798350370805

ISBN: (纸本)9798350370812

With the rapid development of urbanization and industrialization, atmospheric pollution has become a major environmental problem of global concern. The problem of atmospheric pollution not only destroys the ecological en-vironment of the earth, but also has a serious impact on people's health and development. Therefore, accurate prediction of atmospheric monitoring data is of great significance to environmental management as well as public health. To improve the accuracy of prediction, we propose a prediction method for atmospheric monitoring data based on Trans-former and Generative Adversarial network (GAN). Firstly, data pre-processing is performed on the collected atmospheric monitoring data, and then, constructing a prediction model based on Transformer and GAN for atmospheric monitoring data, aiming at extracting the data features of atmospheric monitoring data by Transformer and generating the data by using the generator of GAN. In addition, we improve the position encoding (PE) of the Transformer in order to it can efficiently extract temporal features of atmospheric monitoring data. Finally, the effectiveness of the proposed method is verified by data from three air monitoring stations in a city.

关键词： Accuracy Pollution Atmospheric modeling Urban areas Predictive models Generative adversarial networks Transformers Feature extraction Data models Monitoring

来源：评论

学校读者我要写书评

暂无评论

Gradient-YOLO: Exploring the integration of gradient architecture into the YOLO network

Gradient-YOLO: Exploring the integration of gradient archite...

引用

International Joint Conference on Neural networks (IJCNN)

作者： Gang Li Cheng Zhang Delong Han Letian Gao Mingle Zhou 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) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China SHANDONG SCICOM Information and Economy Research Institute Co. Ltd Jinan China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Object detection is an essential task in the field of computer vision. The one-stage object detection model directly completes object detection through a single forward propagation and has fast real-time object detection capabilities, making it widely used—especially the model of the You Only Look Once (YOLO) series. Improving the detection accuracy of the YOLO model has always been a research topic. The gradient architecture cascades feature information extraction and aggregates all features at the end, which can improve the feature fusion ability of the network. Combining the idea of gradient architecture, this paper proposes a YOLO based on gradient architecture: Gradient-YOLO. Specifically, this paper integrates gradient architecture into the backbone, neck, and bottleneck structures in the YOLO network, obtaining gradient backbone, gradient neck, and gradient bottleneck, respectively. By combining gradient architecture, various network parts in Gradient-YOLO can fully aggregate multi-layer features, reduce feature loss, and thus improve detection accuracy. This paper takes the mature YOLOv5 model and the latest YOLOv8 model as the baseline and combines gradient thinking to obtain Gradient-YOLOv5 and GradientYOLOv8. Moreover, conduct experimental testing on the MS COCO dataset. Regarding the mAP@.5 detection indicator, compared to YOLOv5s, Gradient-YOLOv5s increased by 5.07%. Compared to YOLOv8n, Gradient-YOLOv8n has increased by 4.63%. Therefore, the combination of gradient architecture can improve the detection accuracy of YOLO networks.

关键词： YOLO Accuracy Aggregates Computational modeling Computer architecture Feature extraction Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Illumination-Enhanced Infrared and Low-Light Visible Image Fusion

Illumination-Enhanced Infrared and Low-Light Visible Image F...

引用

IEEE International Conference on Image Processing

作者： Guohua Lv Xinyue Fu Chaoqun Sima Yanlong Xu Baodong Zhang Hanju Bao 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) Jinan China Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Lianxin Intelligent Technology (Shandong) Co. Ltd Jinan China

ISBN: (数字)9798350349399

ISBN: (纸本)9798350349405

Infrared and visible image fusion aims to generate fused images with rich texture details and salient targets. However, existing methods often ignore illumination conditions, and the fusion results under low-light conditions lack texture details. To solve this problem, we propose an illumination-enhanced infrared and visible image fusion method, named IEFusion. Specifically, we first design a feature decomposition network based on retinex theory to obtain enhanced features of infrared and visible images. Then, the cross-modal feature fusion module is used to fuse important features. Finally, a gradient-enhanced image reconstructor is designed to enhance the gradient and generate a fused image. In addition, we design a contrastive learning module to guide the network to focus on deep features and maximize the mutual information of fused and enhanced images. Extensive experiments demonstrate the superiority of our IEFusion over the state-of-the-art methods, in both qualitative and quantitative metrics.

关键词： Measurement Fuses Lighting Contrastive learning Feature extraction Image fusion Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

引用

Proceedings of the Fortieth Conference on Uncertainty in Artificial Intelligence

作者： Zhiqiang Zhang Yongqiang Jiang Qian Gao Zhipeng Wang Key Laboratory of Computing Power Network and information Security Ministry of Eaucation Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China and Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China and Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China China Telecom Digital Intelligence Techonology Co Jinan China

Existing multimodal recommendation research still faces some challenges, such as not being able to fully mine the implicit relevance information of neighbor nodes, and the unreasonable weight allocation to imbalanced nodes. To address the aforementioned challenges, this paper introduces a new multimodal recommendation model called NS-MAR+. Specifically, the model firstly constructs a neighbor similarity graph convolutional network to capture the implicit relevance information and reasonably assigns the attention weights through the graph attention mechanism. Secondly, the model introduces a modal alignment and fusion mechanism by using a multilayer perceptron (MLP) to map image and text features into a shared space for comparison and fusion. In addition, the model constructs a user co-interaction graph and an item semantic graph based on the original information and performs graph convolution operations to enhance the preference information of users and items, and to better capture the interactions and internal features between users and items. Finally, MLP is employed to aggregate user and item representations and predict personalized recommendation rankings. To validate the experiment's efficacy, this paper compares with several leading multimodal recommendation models on public datasets with a performance improvement of 1% to 3%. The experimental outcomes indicate that the model in this paper has good superiority and accuracy in multimodal recommendation tasks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generalization Boosted Adapter for Open-Vocabulary Segmentation

arXiv

引用

arXiv 2024年

作者： Xu, Wenhao Wang, Changwei Feng, Xuxiang Xu, Rongtao Huang, Longzhao Zhang, Zherui Guo, Li Xu, Shibiao School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China The 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 Jinan250013 China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan China The Aerospace Information Research Institute Chinese Academy of Sciences China The State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China

Vision-language models (VLMs) have demonstrated remarkable open-vocabulary object recognition capabilities, motivating their adaptation for dense prediction tasks like segmentation. However, directly applying VLMs to such tasks remains challenging due to their lack of pixel-level granularity and the limited data available for fine-tuning, leading to overfitting and poor generalization. To address these limitations, we propose Generalization Boosted Adapter (GBA), a novel adapter strategy that enhances the generalization and robustness of VLMs for open-vocabulary segmentation. GBA comprises two core components: (1) a Style Diversification Adapter (SDA) that decouples features into amplitude and phase components, operating solely on the amplitude to enrich the feature space representation while preserving semantic consistency;and (2) a Correlation Constraint Adapter (CCA) that employs cross-attention to establish tighter semantic associations between text categories and target regions, suppressing irrelevant low-frequency "noise" information and avoiding erroneous associations. Through the synergistic effect of the shallow SDA and the deep CCA, GBA effectively alleviates overfitting issues and enhances the semantic relevance of feature representations. As a simple, efficient, and plug-and-play component, GBA can be flexibly integrated into various CLIP-based methods, demonstrating broad applicability and achieving state-of-the-art performance on multiple open-vocabulary segmentation benchmarks. © 2024, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Rafmnet:Reinforced Attention Fusion and Multiscale network For Noisy Infrared and Visible Image Fusion

Rafmnet:Reinforced Attention Fusion and Multiscale Network F...

引用

IEEE International Conference on Image Processing

作者： Guohua Lv Xiyan Wang Yongbiao Gao Yi Zhai Guixin Zhao Guangxiao Ma 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) Jinan China Faculty of Comuter Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China College of Computer Science and Engineering Shandong University of Science and Technology Qingdao China

ISBN: (数字)9798350349399

ISBN: (纸本)9798350349405

The purpose of infrared and visible image fusion is to combine the advantages of different types of images to produce more robust and informative images. However, if the source images are noisy, existing fusion methods may not produce clear results. To address this issue, we propose a novel method for infrared and visible image fusion with noise reduction. This method enhances the visual perception of fused images by integrating features of different scales extracted by the denoising network into the fusion network. By using deformable convolutional denoising networks, noise in images can be removed and features can be enhanced. Then, a set of reinforced attention fusion modules (RAFM) are designed to fuse the features extracted by the denoising network. Experimental results demonstrate the effectiveness of our proposed method, which outperforms existing state-of-the-art methods in terms of fusion accuracy and visual perception.

关键词： Couplings Fuses Noise reduction Noise Feature extraction Noise measurement Task analysis

来源：评论

学校读者我要写书评

暂无评论

Improvement of Low-Contrast Objective Detecting Capability for YOLOv5 Based on Receptive Field Enhancement and Redundant Feature Reuse

Improvement of Low-Contrast Objective Detecting Capability f...

引用

International Joint Conference on Neural networks (IJCNN)

作者： Qingyu Xu Jiguo Yu Anming Dong 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) Jinan China School of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Big Data Institute Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

YOLOv5s is a classic deep learning target detection framework with balanced speed and performance in recognition, which is widely used in industrial defect inspections. YOLOv5s relies on the residual structure in the C3 module for feature extraction, but due to its simple structure and the small, fixed convolution kernel, it is difficult to accurately and completely extract target features when applied to the detection of defects with inconspicuous features and irregular shapes, which results in a decrease in recognition accuracy. To solve this problem, this paper proposes an improved YOLO architecture based on receptive field enhancement and redundant feature reuse. Firstly, the method designs a redundant feature reuse module (RFRM) to replace the residual structure in the C3 module for feature extraction. This module can deepen the network with a smaller cost and enhance the network’s ability to extract features. Furthermore, the feature reuse process allows the network to deepen while retaining detailed information, enabling the network to classify and localize more accurately. Secondly, a simplified convolutional block attention module (SCBAM) is designed and embedded into the neck of the detection network. This module directs the detection network to focus more on inconspicuous defect features and reduce interference from background noise in the feature map, thereby improving the accuracy of defect classification and localization. Finally, a receptive field enhancement module (RFEM) is designed and inserted between the neck and head of the detection network. This module adds only a small computational cost to expand the receptive field of the network, enabling it to further extract and comb irregular features from the neck in a comprehensive manner, making the features reaching the detection head more complete. Applying the above improvements to defect detection, the experimental results show that the improved YOLO architecture based on receptive field enhancem

关键词： YOLO Head Accuracy Target recognition Shape Computer architecture Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Thinking the Importance of Patient’s Chief Complaint in TCM Syndrome Differentiation

Thinking the Importance of Patient’s Chief Complaint in TCM...

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Zhizhuo Zhao Xueping Peng Yong Li Hao Wu Weiyu Zhang Wenpeng Lu 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) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Australian Artificial Intelligence Institute University of Technology Sydney Australia Jinan ChangQing District People’s Hospital School of Computer Science and Technology Beijing Institute of Technology Beijing China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Traditional Chinese Medicine (TCM) is a natural, safe, and effective therapeutic approach with widespread application worldwide. The unique diagnostic methods of TCM often require a comprehensive analysis of patient information, much of which is contained in clinical text. Numerous studies have demonstrated the effectiveness of natural language processing (NLP) techniques in TCM disease classification. Therefore, this paper focuses on the task of TCM syndrome differentiation, proposing a novel matching score calculation method and a new label attention calculation method to assist the model in focusing on the relationship between TCM syndrome and disease symptom. Specifically, we enhance the model’s attention to the uniqueness of the relationship between TCM syndrome and symptom by introducing a finer-grained token-level matching score. Simultaneously, we improve the model’s attention to the generality of the relationship between TCM syndrome and symptom through a more global label attention mechanism. Additionally, we observe a severe long-tail problem in the dataset. To alleviate this issue, we propose the use of focal loss to help the model pay more attention to challenging samples. Extensive experiments on the TCM-SD dataset indicate that our approach significantly outperforms state-of-the-art baselines 1 .

关键词： Attention mechanisms Federated learning Focusing Natural language processing Task analysis Medical diagnostic imaging Diseases

来源：评论

学校读者我要写书评

暂无评论

Domestic Violence Crisis Recognition Method based on Bi-LSTM+Attention 8

Domestic Violence Crisis Recognition Method based on Bi-LSTM...

引用

8th Annual International Conference on network and Information Systems for Computers, ICNISC 2022

作者： Wang, Zhixiao Yan, Wenyao Li, Zhuochun Huang, Min Fan, Qinyuan Wang, Xin Xi'an University of Technology Xi'an China Shaanxi Key Laboratory of Network Computing and Security Xi'an China College of Xi'an Innovation Yan'an University Xi'an710100 China University of Pittsburgh PittsburghPA15260 United States Art and Design Xi'an University of Technology Xi'an710048 China Fakultät Verkehrs- und Maschinensysteme Technische Universität Berlin Berlin13353 Germany Xi'an University of Technology Computer Science and Engineering Xi'an710048 China

ISBN: (纸本)9781665453516

Domestic violence (DV) is getting more and more attention due to the critical trouble and danger that pose great challenge to human rights and health. The popularity of various social medias can help these victims to share their experiences and obtain more possible support from numerous open communities. However, it is not only inefficient but also laborious and time-consuming to manually access and browse through a great deal of available posts on the Internet and social media space. Therefore, considering the advantages of Deep Learning (DL) technology in Natural Language Processing, adopting DL as an efficient strategy for automatic recognition and evaluation of DV victims is in the urgent requirements. This paper takes social media Facebook posts about domestic violence as the research object and uses Word2Vec to build word vector model. The paper uses Bi-LSTM+self-Attention deep learning models to accomplish DV crisis recognition task and compares it with CNN, RNN and LSTM. The assessment of experimental results show that the accuracy of CNN and LSTM are both above 90% which is better than RNN;And the accuracy of Bi-LSTM is the highest after using the Attention mechanism. The research results of this article will provide reference and help for public DVCS to rescue DV victims. © 2022 IEEE.

关键词： Long short-term memory

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：