检索结果-内蒙古大学图书馆

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Zaixi Zhang Qi Liu Qingyong Hu Chee-Kong Lee Anhui Province Key Lab of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China and State Key Laboratory of Cognitive Intelligence Hefei Anhui China Hong Kong University of Science and Technology Tencent America

ISBN: (纸本)9781713871088

The Transformer architecture has achieved remarkable success in a number of domains including natural language processing and computer vision. However, when it comes to graph-structured data, transformers have not achieved competitive performance, especially on large graphs. In this paper, we identify the main deficiencies of current graph transformers: (1) Existing node sampling strategies in Graph Transformers are agnostic to the graph characteristics and the training process. (2) Most sampling strategies only focus on local neighbors and neglect the long-range dependencies in the graph. We conduct experimental investigations on synthetic datasets to show that existing sampling strategies are sub-optimal. To tackle the aforementioned problems, we formulate the optimization strategies of node sampling in Graph Transformer as an adversary bandit problem, where the rewards are related to the attention weights and can vary in the training procedure. Meanwhile, we propose a hierarchical attention scheme with graph coarsening to capture the long-range interactions while reducing computational complexity. Finally, we conduct extensive experiments on real-world datasets to demonstrate the superiority of our method over existing graph transformers and popular GNNs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Neural Network Algorithm of Multi-team Game and Its application in Parallel-Link Communication Networks Flow Control 12th

Neural Network Algorithm of Multi-team Game and Its Applicat...

引用

12th EAI International Conference on Simulation Tools and Techniques, SIMUtools 2020

作者： Liu, Zixin Yang, Huawei Xiong, Lianglin School of Mathematics and Statistics Guizhou University of Finance and Economics Guiyang China Guizhou Key Laboratory of Big Data Statistics Analysis Guizhou University of Finance and Economics Guiyang China School of Big Data Application and Economics Guizhou University of Finance and Economics Guiyang China School of Mathematics and Computer Science Yunnan Minzu University Kunming China

ISBN: (纸本)9783030727918

This paper investigates the approximate calculation problem of noninferior Nash equilibrium (NNE) in multi-team game. Combined with variational inequalities theory, Nash equilibrium theory, and dynamic system theory, a projection neural network (PNN) algorithm for computing NNE of multi-team game with smooth payoff functions is derived. Utilizing stable theory, stability criteria of NNE in multi-team game are further given. As an application, a flow control model of parallel-link communication networks based on multi-team game and neural network algorithm is elaborated. Finally, a simulation result for two teams, two communication links, and two users in each team parallel-linkcommunication network is also given to illustrate the effectiveness of the PNN algorithm proposed in this paper. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2021.

关键词： Flow control

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised Segmentation and Quantization Algorithm for Infarct Size Measurement of Rat Heart Sections

Semi-supervised Segmentation and Quantization Algorithm for ...

引用

International Conference on Computer and Communications (ICCC)

作者： Xiaoke Zhu Yulong Cai Xiaopan Chen Qi Hu Lingyun Dong Caihong Yuan School of Computer and Information Engineering Henan University Kaifeng China Henan Engineering Research Center of Intelligent Technology and Application Henan University Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China

Segmentation of rat heart section images and infarct area quantization are essential components of infarct size measurement in processing data from animal experiments on ischemic heart disease. Previously, the task of measuring the infarct size of rat heart sections was performed manually by experienced researchers, which was very costly and time-consuming. In this paper, we propose a two-stage semi-supervised approach to solve the task of ischemic heart infarct size calculation in images of rat section images. The approach uses a semi-supervised semantic segmentation model and a semi-automated quantization algorithm to separate the differently stained regions of rat heart sections. We demonstrate the results of the approach on a rat heart section dataset, and experiments on this dataset emphasize the effectiveness of our approach compared to other methods.

关键词： Heart Training Quantization (signal) Semantic segmentation Manuals Rats Size measurement

来源：评论

学校读者我要写书评

暂无评论

Lightweight Transformer Network and Self-supervised Task for Kinship Verification

Lightweight Transformer Network and Self-supervised Task for...

引用

International Conference on Computer and Communications (ICCC)

作者： Xiaoke Zhu Yunwei Li Danyang Li Lingyun Dong Xiaopan Chen School of Computer and Information Engineering Henan University Kaifeng China Henan Engineering Research Center of Intelligent Technology and Application Henan University Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China

Kinship verification is one of the interesting and critical problems in computer vision research, with significant progress in the past decades. Meanwhile, Vision Transformer (VIT) has recently achieved impressive success in many domains, including object detection, image recognition, and semantic segmentation, among others. Most of the previous work on kinship verification are based on convolutional or recurrent neural networks. Compared with the local processing of images like convolutions, transformers can effectively understand and process images globally. However, due to overuse, there are many Transformer layers of fully connected layers, and VIT speed is still an issue. Therefore, in this paper, inspired by the recent success of Transformer models in vision tasks, we propose a Transformer-based kinship verification for training and optimizing kinship verification models. We first train the basic vision transformer (VIT-B) with 12 transformer layers, then we reduce the transformer layers to 6 layers, namely VIT-S (Small Vit) and 4 layers, namely VIT-T (Tiny Vit), to make a tradeoff between optimization accuracy and efficiency. As the first attempt to apply Transformer to the kinship verification task, it provides a feasible strategy for kinship research topics and verifies the effectiveness of the method in terms of the accuracy of the experimental results.

关键词： Training Knowledge engineering Recurrent neural networks Semantic segmentation Self-supervised learning Object detection Transformers

来源：评论

学校读者我要写书评

暂无评论

Point-Level and Set-Level Deep Representation Learning for Cross-Modal Person Re-identification

Point-Level and Set-Level Deep Representation Learning for C...

引用

International Conference on Computer and Communications (ICCC)

作者： Jihui Hu Pengfei Ye Danyang Li Lingyun Dong Xiaopan Chen Xiaoke Zhu Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China School of Computer and Information Engineering Henan University Kaifeng China Henan Engineering Research Center of Intelligent Technology and Application Henan University

In practice, significant modality differences usually exist between visible and infrared images, which makes visible-infrared Person Re-Identification (VI-ReID) a challenging research task. Due to the existing influence of pose variation, background changes, and occlusion, there are often outlier samples within the set of images from the same person. These outlier samples can adversely affect the process of learning the cross-modal matching model. The existing VI-ReID methods mainly focus on learning cross-modal feature representation by using image-level discriminant constraints, i.e., the distance between the truly-matching cross-modal images should be smaller than that between wrong-matching cross-modal images. However, most of these methods ignore the adverse influence caused by outliers. To solve the above problems, we proposed a Point-level and Set-level Deep Representation Learning (PSDRL) approach for VI-ReID in this paper. By using the set-level constraint in the process of deep representation learning, the discrepancy between visible and infrared modalities can be decreased, and the adverse effect of outliers can be weakened. By employing the image-level constraint, the discriminability of the obtained deep feature representations can be improved. Extensive experiments are conducted on the publicly available cross-modal Person Re-Identification datasets, including SYSU-MM01 and RegDB. Experimental results demonstrate the effectiveness of the proposed approach.

关键词： Representation learning Training Image color analysis Computational modeling Task analysis

来源：评论

学校读者我要写书评

暂无评论

Identification of soybean in Argentina using Sentinel-2 composite images

引用

International Journal of Agricultural and Biological Engineering 2024年第5期17卷 266-274页

作者： Linsheng Huang Yue Chen Yuhao Pan Zihang Lou Shijun Zheng Xiaoyang Zhang Le Yu Shengwei Liu Dailiang Peng National Engineering Research Center for Agro-Ecological Big Data Analysis&Application Anhui UniversityHefei 230601China Key Laboratory of Digital Earth Science Aerospace Information Research InstituteChinese Academy of SciencesBeijing 100094China Research Area of Ecology and Biodiversity School of Biological SciencesThe University of Hong KongPokfulamHong KongChina College of Environmental and Resource Sciences Zhejiang UniversityHangzhou 310058China Department of Earth System Science Ministry of Education Key Laboratory for Earth System ModelingInstitute for Global Change StudiesTsinghua UniversityBeijing 100084China Geospatial Sciences Center of Excellence Department of Geography&Geospatial SciencesSouth Dakota State UniversityBrookingsSD 57007USA Ministry of Education Ecological Field Station for East Asian Migratory Birds Beijing 100084China Tsinghua University(Department of Earth System Science)-Xi’an Institute of Surveying and Mapping Joint Research Center for Next-Generation Smart Mapping Beijing 100084China School of Surveying and Land Information Engineering Henan Polytechnic UniversityJiaozuo 454000HenanChina

Soybean is one of the most important oil crops, and Argentina is the third-largest soybean producer in the world, accounting for 17% of the global soybean yield. Timely and accurate information on soybean spatial distribution is critical for ensuring global food security. Sentinel-2 multispectral data and machine learning classification models are used to investigate the potential of soybean identification in the early stage of the growing season in Argentina, with the help of Google Earth Engine (GEE). The earliest time window and optimal feature set for soybean identification are explored. Results are as follows: 1) the random forest (RF) classification model demonstrated the highest level of classification accuracy compared to the backpropagation neural network (BPNN), support vector machine (SVM), and naive Bayes (NB) models;2) Soybean can be accurately identified as early as the end of February (filling stage), which is approximately one month before harvest;3) The optimal feature-subset can reduce the amount of input data by 80% while maintaining high classification accuracy. The overall accuracy (OA) of the RF classification model is 85.87%, and the relative error between the estimated soybean planting area and the agricultural statistics is 3.45%. This study provided a high-precision method for early-season identification of soybeans over large scales. The results can provide a data support for early futures trading and agricultural insurance, as well as a reference for policy-making to ensure global soybean food security.

关键词： soybean machine learning time window feature selection Sentinel-2 Google Earth Engine

来源：评论

学校读者我要写书评

暂无评论

Leveraging proficiency and preference for online Karaoke recommendation

引用

Frontiers of Computer Science 2020年第2期14卷 273-290页

作者： Ming HE Hao GUO Guangyi LV Le WU Yong GE Enhong CHEN Haiping MA Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of ChinaHefei 230027China School of Computer and Information Hefei University of TechnologyHefei 230026China Eller College of Management The University of ArizonaArizona 85721-0108USA iFlyTek Research Hefei 230026China

Recently,many online Karaoke(KTV)platforms have been released,where music lovers sing songs on these *** the meantime,the system automatically evaluates user proficiency according to their singing *** approximate songs to users can initialize singers5 participation and improve users,loyalty to these ***,this is not an easy task due to the unique characteristics of these ***,since users may be not achieving high scores evaluated by the system on their favorite songs,how to balance user preferences with user proficiency on singing for song recommendation is still ***,the sparsity of the user-song interaction behavior may greatly impact the recommendation *** solve the above two challenges,in this paper,we propose an informationfused song recommendation model by considering the unique characteristics of the singing ***,we first devise a pseudo-rating matrix by combing users’singing behavior and the system evaluations,thus users'preferences and proficiency are *** we mitigate the data sparsity problem by fusing users*and songs'rich information in the matrix factorization process of the pseudo-rating ***,extensive experimental results on a real-world dataset show the effectiveness of our proposed model.

关键词： KTV matrix factorization recommendation system

来源：评论

学校读者我要写书评

暂无评论

Estimating China's poverty reduction efficiency by integrating multi-source geospatial data and deep learning techniques

引用

地球空间信息科学学报（英文版） 2024年第4期27卷 1000-1016页

作者： Yao Yao Jianfeng Zhou Zhenhui Sun Qingfeng Guan Zhiqiang Guo Yin Xu Jinbao Zhang Ye Hong Yuyang Cai Ruoyu Wang School of Geography and Information Engineering China University of GeosciencesWuhanChina Center for Spatial Information Science The University of TokyoChibaJapan Alibaba Group HangzhouChina Foshan Surveying Mapping and Geoinformation Research Institute FoshanChina Key Laboratory of Spatial-Temporal Big Data Analysis and Application of Natural Resources in Megacities(Ministry of Natural Resources) School of Geographic SciencesEast China Normal UniversityShanghaChina School of Geography and Information Engineering China University of GeosciencesWuhanChina Institute of International Rivers and Eco-Security Yunnan UniversityKunmingChina Institute of Geography and Spatial Information School of Earth SciencesZhejiang UniversityHangzhouChina School of Geography and Planning Sun Yat-Sen UniversityGuangzhouChina Institute of Cartography and Geoinformation ETH ZurichZürichSwitzerland Department of Civil Environmental and Geomatic Engineering School of EngineeringUniversity College LondonLondonUK Centre for Public Health Queen's University BelfastBelfastNorthern IrelandUK

Poverty threatens human development especially for developing countries,so ending poverty has become one of the most important United Nations Sustainable Development Goals(SDGs).This study aims to explore China's progress in poverty reduction from 2016 to 2019 through time-series multi-source geospatial data and a deep learning *** poverty reduction efficiency(PRE)is measured by the difference in the out-of-poverty rates(which measures the probability of being not poor)of 2016 and *** study shows that the probability of poverty in all regions of China has shown an overall decreasing trend(PRE=0.264),which indicates that the progress in poverty reduction during this period is *** Hu Huanyong Line(Hu Line)shows an uneven geographical pattern of out-of-poverty rate between Southeast and Northwest *** 2016 to 2019,the centroid of China's out-of-poverty rate moved 105.786 km to the northeast while the standard deviation ellipse of the out-of-poverty rate moved 3 degrees away from the Hu Line,indicating that the regions with high out-of-poverty rates are more concentrated on the east side of the Hu Line from 2016 to *** results imply that the government's future poverty reduction policies should pay attention to the infrastructure construction in poor areas and appropriately increase the population density in poor *** study fills the gap in the research on poverty reduction under multiple scales and provides useful implications for the government's poverty reduction policy.

关键词： Poverty reduction efficiency(PRE) driving forces multisource big data deep learning random forest(RF)

来源：评论

学校读者我要写书评

暂无评论

Dual Test-time Training for Out-of-distribution Recommender System

arXiv

引用

arXiv 2024年

作者： Yang, Xihong Wang, Yiqi Chen, Jin Fan, Wenqi Zhao, Xiangyu Zhu, En Liu, Xinwang Lian, Defu School of Computer National University of Defense Technology Changsha410073 China School of Business and Management Hong Kong University of Science and Technology Hong Kong The Hong Kong Polytechnic University Hong Kong Department of Data Science City University of Hong Kong Hong Kong Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China Anhui Hefei230000 China

Deep learning has been widely applied in recommender systems, which has recently achieved revolutionary progress. However, most existing learning-based methods assume that the user and item distributions remain unchanged between the training phase and the test phase. However, the distribution of user and item features can naturally shift in real-world scenarios, potentially resulting in a substantial decrease in recommendation performance. This phenomenon can be formulated as an Out-Of-Distribution (OOD) recommendation problem. To address this challenge, we propose a novel Dual Test-Time-Training framework for OOD Recommendation, termed DT3OR. In DT3OR, we incorporate a model adaptation mechanism during the test-time phase to carefully update the recommendation model, allowing the model to adapt specially to the shifting user and item features. To be specific, we propose a self-distillation task and a contrastive task to assist the model learning both the user’s invariant interest preferences and the variant user/item characteristics during the test-time phase, thus facilitating a smooth adaptation to the shifting features. Furthermore, we provide theoretical analysis to support the rationale behind our dual test-time training framework. To the best of our knowledge, this paper is the first work to address OOD recommendation via a test-time-training strategy. We conduct experiments on five datasets with various backbones. Comprehensive experimental results have demonstrated the effectiveness of DT3OR compared to other state-of-the-art baselines. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Xiaoke Zhu Danyang Li Xiaopan Chen Fumin Qi Fan Zhang Xiao-Yuan Jing School of Computer and Information Engineering Henan University Kaifeng China Henan Engineering Research Center of Intelligent Technology and Application Henan University Kaifeng China Department of System Operation National Supercomuting Center in Shenzhen Shenzhen China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China School of Computer Science Wuhan University Wuhan China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Facial image based kinship verification aims to decide whether there exists kinship between the given facial images. In practice, the cross-generation differences will cause adverse effects on kinship verification, which limits the performance. Therefore, how to mine the implied similarity from facial images with large cross-generation divergence is an important problem in kinship verification, which has not yet been well studied. In view of this, we propose a Similarity Mining via Implicit matching pattern LEarning (SMILE) approach for kinship verification. Specifically, SMILE mainly consists of two modules, including a Semi-coupled Multi-pattern Similarity Learning (SMSL) module and a Cross-Generation Feature Normalization (CGFN) module. The SMSL module is designed to learn multiple semi-coupled matching patterns for mining the implicit facial similarity information from different perspectives. The CGFN module aims to reduce the divergence between facial images of parent and child. Extensive experiments demonstrate that the proposed approach outperforms the existing state-of-the-art methods.

关键词： Pattern matching Similarity learning

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：