检索结果-内蒙古大学图书馆

Simplifying graph contrastive learning with single feature fusion and column vector orthogonal noise

Expert systems with applications 2025年 288卷

作者： Lan You Zhen Zhang Qingxi Peng Christophe Claramunt Xing Zeng Hong Jin School of Computer Science and Information Engineering Hubei University Wuhan430062 Key Laboratory of Intelligent Sensing System and Security (Hubei University) Ministry of Education Wuhan 430062 Hubei Key Laboratory of Big Data Intelligent Analysis and Application (Hubei University) Wuhan 430062 School of Information Engineering Wuhan College Wuhan 430212 China Computer Science Naval Academy Research Institute Lanveoc-Poulmic BP 600 Brest 29240 France Okinawa Institute of Science and Technology Japan

Graph Contrastive Learning (GCL) has shown promise in recommendation systems by improving representation quality through data augmentation and consistency objectives. However, conventional GCL frameworks rely on multi-channel augmentation, which introduces significant computational overhead and limits scalability. To address this, we propose Single Feature Fusion Graph Contrastive Learning (S-GCL), a non-parametric and lightweight framework that simplifies contrastive learning by applying single feature fusion to the final prediction embeddings within each mini-batch. To further enhance S-GCL, we introduce Column Vector Orthogonal Noise (CVON), a feature-level augmentation strategy that injects orthogonal noise into each dimensional feature within the embedding space. CVON enriches representations while preserving semantic integrity, and incurs minimal computational overhead. Its integration within the S-GCL framework yields the proposed SCGCL method. Extensive experiments conducted on six publicly available benchmark datasets validate the effectiveness and generalizability of SCGCL. Notably, integrating SCGCL into LightGCN leads to substantial gains in both training efficiency and recommendation accuracy. For example, on the large-scale Alibaba-iFashion dataset, our method improves Recall@20 by 29 % and NDCG@20 by 33 %, while reducing training time by an impressive 84 %.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sequential reinforced 360-degree video adaptive streaming with cross-user attentive network

arXiv

引用

arXiv 2020年

作者： Fu, Jun Chen, Zhibo Chen, Xiaoming Li, Weiping CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System University of Science and Technology of China Hefei230027 China School of Computer Science and Engineering Beijing Technology and Business University China

In the tile-based 360-degree video streaming, predicting user’s future viewpoints and developing adaptive bitrate (ABR) algorithms are essential for optimizing user’s quality of experience (QoE). Traditional single-user based viewpoint prediction methods fail to achieve good performance in long-term prediction, and the recently proposed reinforcement learning (RL) based ABR schemes applied in traditional video streaming can not be directly applied in the tile-based 360-degree video streaming due to the exponential action space. Therefore, we propose a sequential reinforced 360-degree video streaming scheme with cross-user attentive network. Firstly, considering different users may have the similar viewing preference on the same video, we propose a cross-user attentive network (CUAN), boosting the performance of long-term viewpoint prediction by selectively utilizing cross-user information. Secondly, we propose a sequential RL-based (360SRL) ABR approach, transforming action space size of each decision step from exponential to linear via introducing a sequential decision structure. We evaluate the proposed CUAN and 360SRL using trace-driven experiments and experimental results demonstrate that CUAN and 360SRL outperform existing viewpoint prediction and ABR approaches with a noticeable margin. Copyright © 2020, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Phase Transition Analysis for Compressive Sensing Based DoA Estimation in Automotive Radar

Phase Transition Analysis for Compressive Sensing Based DoA ...

引用

International Radar Symposium (IRS)

作者： Yan Zhang Silin Gao Mingqian Liu Bingchen Zhang Yirong Wu Chinese Academy of Sciences Aerospace Information Research Institute Beijing China University of Chinese Academy of Sciences Beijing China Key Laboratory of Technology in Geo-spatial Information and Processing Application System Beijing China

ISBN: (数字)9788394942151

ISBN: (纸本)9781728157863

In automotive radar applications, the compressive sensing (CS) based DoA estimation is used in array signal processing in recent years. Sparse reconstruction has the potential to estimate the direction of arrival (DoA) with super resolution. However, failed results may be acquired via sparse reconstruction in inappropriate conditions, namely the critical condition determining success or failure must be taken into consideration. In this paper, the sparsity of the scenario and the signal-to-noise ratio (SNR) are analyzed as the main factors via phase transition diagrams. Other factors affecting the success or failure are also investigated, such as the array configuration and the sparse recovery algorithm. Simulated and experimental results demonstrate the critical conditions, in which the DoA estimation is successful or failed.

关键词： Direction-of-arrival estimation Estimation Radar applications Compressed sensing Signal resolution Signal to noise ratio Automotive engineering

来源：评论

学校读者我要写书评

暂无评论

Flood Monitoring of Heilongjiang River Basin in China and Russia Transboundary Region based on SAR Backscattering Characteristics

引用

Journal of Geo-information Science 2022年第4期24卷 802-813页

作者： Zhangwenxuan Wang, Juanle College of Geoscience and Surveying Engineering China University of Mining and Technology Beijing100083 China State Key Laboratory of Resources and Environmental Information System Institute of Geographic Sciences and Natural Resources Research Chinese Academy of Sciences Beijing100101 China Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application Nanjing210023 China

In recent years, Heilongjiang (Amur) River, a border river between China and Russia, is frequently flooded, which brings huge population casualties and economic losses to China and Russia in the basin. Strengthening flood monitoring in the basin is an urgent need for both countries. Influenced by terrible cloudy and rainy weather during the flooding season, the function of traditional optical remote sensing images are restricted. Thus, it is difficult to obtain cloud-free images during the flood. In this paper, through making full use of the advantages of all-weather radar data, a method of monitoring flood in large area based on Sentinel-1 synthetic aperture radar data is proposed. The probability density distribution of backscattering coefficient of SAR image is fitted by Gamma distribution and Gaussian distribution. The global threshold is obtained automatically to segment the initial water by iterating a posteriori probability difference. The misclassification type that looks like water in the initial water classification is refined and removed based on auxiliary data. Moreover, the uniformity of the extracted flood is improved by the post-processing of morphological operation. It can be concluded from the results that, firstly, compared with the traditional segmentation algorithm, the method proposed in this paper carries out the piecewise fitting of the probability density function based on the distribution law of the backscattering coefficient of the SAR image. It also divides the global statistics into local relations, which significantly improves the poor performance, caused by the large difference between water and non-water pixels, of the conventional segmentation algorithm. The flood distribution year by year from 2017 to 2020 is obtained. The overall accuracy of the results is between 87.78% and 94.89% while the Kappa coefficient is between 0.76 and 0.89. Secondly, especially for large semi-arid areas, this paper uses the relationships among backscatter

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Self-Tuning Asynchronous Filter for Linear Gaussian system and applications

引用

IEEE/CAA Journal of Automatica Sinica 2018年第6期5卷 1054-1061页

作者： Wenjun Lv Yu Kang Yunbo Zhao Department of Automation University of Science and Technology of ChinaHefei 230027China State Key Laboratory of Fire Science Department of Automation and Institute of Advanced TechnologyUniversity of Science and Technology of ChinaHefei 230027China Key Laboratory of Technology in GeoSpatial Information Processing and Application System Chinese Academy of SciencesBeijing 100190China College of Information Engineering Zhejiang University of TechnologyHangzhou 310023China

In this paper, optimal filtering problem for a class of linear Gaussian systems is studied. The system states are updated at a fast uniform sampling rate and the measurements are sampled at a slow uniform sampling rate. The updating rate of system states is several times the sampling rate of measurements and the multiple is constant. To solve the problem,we will propose a self-tuning asynchronous filter whose contributions are twofold. First, the optimal filter at the sampling times when the measurements are available is derived in the linear minimum variance sense. Furthermore, considering the variation of noise statistics, a regulator is introduced to adjust the filtering coefficients adaptively. The case studies of wheeled robot navigation system and air quality evaluation system will show the effectiveness and practicability in engineering.

关键词： Air quality evaluation system linear Gaussian system wheeled robot navigation system

来源：评论

学校读者我要写书评

暂无评论

Camouflaged Object Detection via Context-aware Cross-level Fusion

arXiv

引用

arXiv 2022年

作者： Chen, Geng Liu, Si-Jie Sun, Yu-Jia Ji, Ge-Peng Wu, Ya-Feng Zhou, Tao Northwestern Polytechnical University Xi’an710072 China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering China Data Processing Center School of Power and Energy China Key Laboratory of System Control and Information Processing Ministry of Education Shanghai200240 China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China School of Computer Science Inner Mongolia University Hohhot010021 China Artificial Intelligence Institute School of Computer Science Wuhan University Wuhan430072 China

Camouflaged object detection (COD) aims to identify the objects that conceal themselves in natural scenes. Accurate COD suffers from a number of challenges associated with low boundary contrast and the large variation of object appearances, e.g., object size and shape. To address these challenges, we propose a novel Context-aware Cross-level Fusion Network (C2F-Net), which fuses context-aware cross-level features for accurately identifying camouflaged objects. Specifically, we compute informative attention coefficients from multi-level features with our Attention-induced Cross-level Fusion Module (ACFM), which further integrates the features under the guidance of attention coefficients. We then propose a Dual-branch Global Context Module (DGCM) to refine the fused features for informative feature representations by exploiting rich global context information. Multiple ACFMs and DGCMs are integrated in a cascaded manner for generating a coarse prediction from high-level features. The coarse prediction acts as an attention map to refine the low-level features before passing them to our Camouflage Inference Module (CIM) to generate the final prediction. We perform extensive experiments on three widely used benchmark datasets and compare C2F-Net with state-of-the-art (SOTA) models. The results show that C2F-Net is an effective COD model and outperforms SOTA models remarkably. Further, an evaluation on polyp segmentation datasets demonstrates the promising potentials of our C2F-Net in COD downstream applications. Our code is publicly available at: https://***/Ben57882/C2FNet-TSCVT. Copyright © 2022, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

AN ANISOTROPIC SCATTERING ANALYSIS METHOD BASED ON LIKELIHOOD RATIO USING CIRCULAR SAR DATA

AN ANISOTROPIC SCATTERING ANALYSIS METHOD BASED ON LIKELIHOO...

引用

IEEE International Geoscience and Remote Sensing Symposium

作者： Fei Teng Wen Hong Yun Lin Bing Han Yanping Wang Wenjie Shen Shanshan Feng Key Laboratory of Technology in Geospatial Information Processing and Application System Chinese Academy of Sciences Beijing China North China University of Technology Beijing China

The scattering of an anisotropic target is aspect dependent. Circular SAR (CSAR) can observe the scattering behavior in different aspect angles. In this paper, we propose an anisotropy scattering analysis method based on the likelihood ratio using CSAR data. CSAR data is used to provide sub-aperture images in different aspect angles. The likelihood ratio is defined as the ratio of the conditional probability under two hypotheses, anisotropic and isotropic. Anisotropic and isotropic scatterings can be discriminated by the value of the likelihood ratio. The scattering direction of the anisotropic scattering can be obtained by using our method too. We use a C-band CSAR data, which is acquired by the Institute of Electronics, Chinese Academy of Sciences (IECAS) to validate our method.

关键词： Apertures Image color analysis Radar polarimetry Trajectory Optical imaging Optical scattering

来源：评论

学校读者我要写书评

暂无评论

On the Use of Axial Ratio to Analysis Transmit Distortions in Hybrid Polarimetry and Their Influence to Canonical Scattering Mechanisms 6

On the Use of Axial Ratio to Analysis Transmit Distortions i...

引用

6th Asia-Pacific Conference on Synthetic Aperture Radar, APSAR 2019

作者： Chen, Shiqiang Hong, Wen Key Laboratory of Technology in Geo-spatial Information Processing and Application System Beijing China Institute of Electronics Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781728129129

Transmit distortions in the hybrid polarimetric (HP) SAR cannot be compensated simply with external calibration methods. Therefore, it is necessary to analysis their influence on HP data. In this study, we have proposed an analysis method based on the Axial Ratio (AR) of the real transmitted polarized wave. Firstly, impact of different distortion sources is quantified with the AR parameter. Next, a case study is illustrated using real GF-3 measured data. At last, the influence of transmit distortions to canonical scattering mechanisms is analyzed. © 2019 IEEE.

关键词： Polarimeters

来源：评论

学校读者我要写书评

暂无评论

Prior-enlightened and motion-robust video deblurring

arXiv

引用

arXiv 2020年

作者： Zhou, Ya Xu, Jianfeng Tasaka, Kazuyuki Chena, Zhibo Li, Weiping CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei230026 China KDDI Research Inc. Fujimino-shi Saitama356-8502 Japan

Various blur distortions in video will cause negative impact on both human viewing and video-based applications, which makes motion-robust deblurring methods urgently needed. Most existing works have strong dataset dependency and limited generalization ability in handling challenging scenarios, like blur in low contrast or severe motion areas, and non-uniform blur. Therefore, we propose a PRiOr-enlightened and MOTION-robust video deblurring model (PROMOTION) suitable for challenging blurs. On the one hand, we use 3D group convolution to efficiently encode heterogeneous prior information, explicitly enhancing the scenes’ perception while mitigating the output’s artifacts. On the other hand, we design the priors representing blur distribution, to better handle non-uniform blur in spatio-temporal domain. Besides the classical camera shake caused global blurry, we also prove the generalization for the downstream task suffering from local blur. Extensive experiments demonstrate we can achieve the state-of-the-art performance on well-known REDS and GoPro datasets, and bring machine task gain. Copyright © 2020, The Authors. All rights reserved.

关键词： Motion estimation

来源：评论

学校读者我要写书评

暂无评论

Learning to Infer Weather States Using Partial Observations

Journal of Geophysical Research: Machine Learning and Comput...

引用

Journal of Geophysical Research: Machine Learning and Computation 2025年第1期2卷

作者： Jie Chao Baoxiang Pan Quanliang Chen Shangshang Yang Jingnan Wang Congyi Nai Yue Zheng Xichen Li Huiling Yuan Xi Chen Bo Lu Ziniu Xiao National Key Laboratory of Earth System Numerical Modeling and Application Institute of Atmospheric Physics Chinese Academy of Science Beijing China School of Atmospheric Sciences Chengdu University of Information Technology Chengdu China Key Laboratory of Mesoscale Severe Weather Ministry of Education and School of Atmospheric Sciences Nanjing University Nanjing China College of Computer National University of Defense Technology Hunan China Clustertech LTD Hong Kong China National Climate Center China Meteorological Administration Beijing China

Accurate state estimation of the high-dimensional, chaotic Earth's atmosphere marks a Sisyphean task, yet is indispensable for initiating weather forecasts and gauging climate variability. While much effort is devoted to assimilating observations and forecasts to infer weather states, the inherent low-dimensional statistical structure in atmospheric circulation, shaped by geophysical laws and geographic boundaries, is underutilized as an informative prior for state inference, or as reference for assessing representative of existing observations and planning new ones. We realize these potential by learning climatological distribution from climate reanalysis/simulation, using a deep generative model. For a case study of estimating 2 m temperature spatial patterns, the learned distribution faithfully reproduces climatology statistics. A combination of the learned climatological prior with few station observations yields strong posterior of spatial pattern estimates, which are spatially coherent, faithful and adaptive to observational constraints, and uncertainty-aware. This allows us to evaluate each observation's value in reducing pattern estimation uncertainty, and guide optimal observation network design by pinpointing the most informative sites. Our study showcases how generative models can extract and utilize information produced in the chaotic evolution of climate system. Deep generative model enables accurate spatial interpolation of weather variables from sparse observations The generative model produces spatially coherent and uncertainty-aware estimates, effectively constrained by observational data The approach provides a framework to quantify observation impact on uncertainty reduction, enabling optimization of observation networks Accurate estimation of weather conditions across a large area is crucial but challenging due to the complex and chaotic nature of the atmosphere. Traditional methods rely on combining observations with forecasts, which can be comp

关键词：

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：