检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Sheng, Qiang Cao, Juan Zhang, Xueyao Li, Xirong Zhong, Lei Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China Key Lab of Data Engineering and Knowledge Engineering Renmin University of China China

False claims that have been previously fact-checked can still spread on social media. To mitigate their continual spread, detecting previously fact-checked claims is indispensable. Given a claim, existing works retrieve fact-checking articles (FC-articles) for detection and focus on reranking candidate articles in the typical two-stage retrieval framework. However, their performance may be limited as they ignore the following characteristics of FC-articles: (1) claims are often quoted to describe the checked events, providing lexical information besides semantics;and (2) sentence templates to introduce or debunk claims are common across articles, providing pattern information. In this paper, we propose a novel reranker, MTM (Memoryenhanced Transformers for Matching), to rank FC-articles using key sentences selected using event (lexical and semantic) and pattern information. For event information, we propose to finetune the Transformer with regression of ROUGE. For pattern information, we generate pattern vectors as a memory bank to match with the parts containing patterns. By fusing event and pattern information, we select key sentences to represent an article and then predict if the article fact-checks the given claim using the claim, key sentences, and patterns. Experiments on two real-world datasets show that MTM outperforms existing methods. Human evaluation proves that MTM can capture key sentences for explanations. The code and the dataset are at https://***/ICTMCG/MTM. © 2021, CC BY-SA.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A High Slope Efficiency Ring-cavity Single-frequency Fiber Laser Based on Yb: YAG Crystal-derived Silica Fiber

A High Slope Efficiency Ring-cavity Single-frequency Fiber L...

引用

2021 Asia Communications and Photonics Conference, ACP 2021

作者： Wan, Ying Wen, Jianxiang Zou, Kai Jiang, Chen Pang, Fufei Wang, Tingyun Key Lab of Specialty Fiber Optics and Optical Access Networks Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication Shanghai Institute for Advanced Communication and Data Science School of Communication and Information Engineering Shanghai University 99 Shangda Road Shanghai200444 China

A high-concentration Yb-doped YAG crystal-derived silica fiber (YCDSF) is fabricated using the melt-in-tube method. Based on this fiber, a ring-cavity single-frequency fiber laser (SFFL) has been accomplished, and its... 详细信息

ISBN: (纸本)9781957171005

关键词： Fibers

来源：评论

学校读者我要写书评

暂无评论

The 2023 report of the synergetic roadmap on carbon neutrality and clean air for China: Carbon reduction, pollution mitigation, greening, and growth

引用

Environmental Science and Ecotechnology 2025年第1期23卷 1-18页

作者： Jicheng Gong Zhicong Yin Yu Lei Xi Lu Qiang Zhang Cilan Cai Qimin Chai Huopo Chen Renjie Chen Wenhui Chen Jing Cheng Xiyuan Chi Hancheng Dai Zhanfeng Dong Guannan Geng Jianlin Hu Shan Hu Cunrui Huang Tiantian Li Wei Li Xiaomei Li Yongsheng Lin Jun Liu Jinghui Ma Yue Qin Weiqi Tang Dan Tong Jiaxing Wang Lijuan Wang Qian Wang Xuhui Wang Xuying Wang Libo Wu Rui Wu Qingyang Xiao Yang Xie Xiaolong Xu Tao Xue Haipeng Yu Da Zhang Li Zhang Ning Zhang Shaohui Zhang Shaojun Zhang Xian Zhang Zengkai Zhang Hongyan Zhao Bo Zheng Yixuan Zheng Tong Zhu Huijun Wang Jinnan Wang Kebin He State Key Joint Laboratory for Environment Simulation and Pollution Control College of Environmental Sciences and Engineering and Center for Environment and HealthPeking UniversityBeijing100871China Key Laboratory of Meteorological Disaster Ministry of Education/Joint International Research Laboratory of Climate and Environment Change(ILCEC)/Collaborative Innovation Center on Forecast and Evaluation of Meteorological Disasters(CIC-FEMD)Nanjing University of Information Science&TechnologyNanjing210044China Center of Air Quality Simulation and System Analysis Chinese Academy of Environmental PlanningBeijing100041China Center for Carbon Neutrality Chinese Academy of Environmental PlanningBeijing100041China State Key Joint Laboratory of Environment Simulation and Pollution Control School of EnvironmentTsinghua UniversityBeijing100084China Institute for Carbon Neutrality Tsinghua UniversityBeijing100084China Ministry of Education Key Laboratory for Earth System Modelling Department of Earth System ScienceTsinghua UniversityBeijing100084China National Center for Climate Change Strategy and International CooperationBeijing100035China Nansen-Zhu International Research Centre Institute of Atmospheric PhysicsChinese Academy of SciencesBeijing100029China School of Public Health Key Lab of Public Health Safety of the Ministry of Education and Key Lab of Health Technology Assessment of the Ministry of HealthFudan UniversityShanghai200032China School of Economics and Management Beijing University of Chemical TechnologyBeijing100029China Department of Earth System Science University of CaliforniaIrvineIrvineCA92697USA National Meteorological Center China Meteorological AdministrationBeijing100081China College of Environmental Sciences and Engineering Peking UniversityBeijing100871China Institute of Eco-Environmental Management and Policy Chinese Academy of Environmental PlanningBeijing100041China Jiangsu Key Laboratory of Atmospheric Environment Monitoring and Pollution Contr

The response to climate change and air pollution control demonstrates strong synergy across scientific mechanisms,targets,strategies,and governance *** report,based on a monitoring indicator system for coordinated governance of air pollution and climate change,employs an interdisciplinary approach combining natural and social *** establishes 20 indicators across five key areas:air pollution and climate change,governance systems and practices,structural transformation and technologies,atmospheric components and emission reduction pathways,and health impacts and *** report tries to provide actionable insights into the interconnectedness of air pollution and climate *** highlights key policy gaps,presents updated indicators,and offers a refined monitoring framework to track progress toward China's dual goals of reducing emissions and improving air *** to previous editions,this year's report has updated four key indicators:meteorological impacts on air quality,climate change and its effects,governance policies,and low-carbon building energy *** aim is to further refine the monitoring framework,track progress,and establish a comprehensive theory for collaborative governance while identifying challenges and proposing solutions for China's pathway to carbon neutrality and clean *** report comprises six *** executive summary chapter is followed by analyzing air pollution and climate change *** systems and practices are discussed in the third chapter,focusing on policy implementation and local *** fourth chapter addresses structural transformations and emission reduction technologies,including energy and industrial shifts,transportation,low-carbon buildings,carbon capture and storage,and power *** fifth chapter outlines atmospheric component dynamics and emission pathways,presenting insights into emission drivers and future *** sixth chapter assesses he

关键词： Synergetic roadmap Carbon neutrality Clean air

来源：评论

学校读者我要写书评

暂无评论

Compensating Verdet constant of optical fibers based on faraday rotating mirror measurement system

Compensating Verdet constant of optical fibers based on fara...

引用

2021 Asia Communications and Photonics Conference, ACP 2021

作者： Zeng, Jiawei Wen, Jianxiang Shi, Hao Wu, Yan Ye, Le Dong, Yanhua Huang, Yi Wang, Tingyun Key Lab of Specialty Fiber Optics and Optical Access Networks Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication Shanghai Institute for Advanced Communication and Data Science School of Communication and Information Engineering Shanghai University 99 Shangda Road Shanghai200444 China

Established Verdet constant test system based on Faraday rotating mirror (FRM). It is found that FRM eliminates the influence of linear birefringence, indicating that the introduction of FRM can compensate for the Ver... 详细信息

ISBN: (纸本)9781957171005

关键词： Optical fibers

来源：评论

学校读者我要写书评

暂无评论

Image Manipulation Detection by Multi-View Multi-Scale Supervision

Image Manipulation Detection by Multi-View Multi-Scale Super...

引用

International Conference on Computer Vision (ICCV)

作者： Xinru Chen Chengbo Dong Jiaqi Ji Juan Cao Xirong Li MoE Key Lab of Data Engineering and Knowledge Engineering Renmin University of China AIMC Lab School of Information Renmin University of China Institute of Computing Technology Chinese Academy of Sciences State Key Laboratory of Media Convergence Production Technology and Systems

ISBN: (纸本)9781665428132

The key challenge of image manipulation detection is how to learn generalizable features that are sensitive to manipulations in novel data, whilst specific to prevent false alarms on authentic images. Current research emphasizes the sensitivity, with the specificity overlooked. In this paper we address both aspects by multi-view feature learning and multi-scale supervision. By exploiting noise distribution and boundary artifact surrounding tampered regions, the former aims to learn semantic-agnostic and thus more generalizable features. The latter allows us to learn from authentic images which are nontrivial to be taken into account by current semantic segmentation network based methods. Our thoughts are realized by a new network which we term MVSS-Net. Extensive experiments on five benchmark sets justify the viability of MVSS-Net for both pixel-level and image-level manipulation detection.

关键词： Representation learning Image segmentation Computer vision Sensitivity Costs Image edge detection Semantics

来源：评论

学校读者我要写书评

暂无评论

Low-Latency Layer-Aware Proactive and Passive Container Migration in Meta Computing

arXiv

引用

arXiv 2024年

作者： Liu, Mengjie Li, Yihua Mou, Fangyi Tang, Zhiqing Lou, Jiong Guo, Jianxiong Jia, Weijia Institute of Artificial Intelligence and Future Networks Beijing Normal University China Faculty of Arts and Sciences Beijing Normal University China Guangdong Key Lab of AI and Multi-Modal Data Processing BNU-HKBU United International College China Department of Computer Science and Engineering Shanghai Jiao Tong University China Department of Informatics University of Zurich Zurich Switzerland

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

Enhanced Attention-Based Pedestrian Trajectory Prediction Model: Integration of Dynamic Social Relationships and Spatial Correlations

SSRN

引用

SSRN 2024年

作者： Lu, Xu Li, Zhize Gao, Xiang de Albuquerque, Victor Hugo C. Liu, Jun School of Computer Science Guangdong Polytechnic Normal University Guangzhou510665 China Guangdong Provincial Key Laboratory of Intellectual Property & Big Data Guangzhou510665 China Pazhou Lab Guangzhou510330 China Department of Teleinformatics Engineering Federal University of Ceará Fortaleza60020-181 Brazil School of automation Guangdong Polytechnic Normal University Guangzhou510665 China

Existing pedestrian trajectory prediction models inadequately consider the impact of evolving dynamic social relationships among pedestrians on roadways and insufficiently address spatial correlation relationships. This paper introduces an attention-enhanced pedestrian trajectory prediction model. It aims to address limitations in traditional models regarding dynamic pedestrian social information and spatial positional correlations. To begin with, it incorporates a dynamic social relationship module based on attention mechanisms. This module captures the dynamic features within pedestrian social relationships effectively, thereby enhancing the modeling capabilities for social interactions. Additionally, to address the issue of insufficient spatial positional correlation, the model introduces dynamic correlation modeling for historical trajectories. This enables a more comprehensive understanding of the internal connections among positional points. Experimental results demonstrate significant performance improvements compared to traditional methods on both the SDD dataset and the inD dataset under the TrajNet benchmark. The model achieves average displacement errors of 7.15 and 11.33, and final displacement errors of 12.51 and 21.21 respectively. © 2024, The Authors. All rights reserved.

关键词： Dynamics

来源：评论

学校读者我要写书评

暂无评论

Image manipulation detection by multi-view multi-scale supervision

arXiv

引用

arXiv 2021年

作者： Chen, Xinru Dong, Chengbo Ji, Jiaqi Cao, Juan Li, Xirong MoE Key Lab of Data Engineering and Knowledge Engineering Renmin University of China AIMC Lab School of Information Renmin University of China Institute of Computing Technology Chinese Academy of Sciences State Key Laboratory of Media Convergence Production Technology and Systems

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Predicting the Risk of Incident Cardiovascular Disease Using Retinal Vessel Caliber Measured by Artificial Intelligence in a Chinese Community-Based Population

SSRN

引用

SSRN 2025年

作者： Luo, Xingyu Yang, Guangzhengao Fan, Fangfang Jiang, Yimeng Jia, Jia Zhao, Jie Chen, Zifan Yan, Shenshen She, Haicheng Zheng, Bo Zhang, Li Zhang, Yan Department of Cardiology Peking University First Hospital Beijing China Institute of Cardiovascular Disease Peking University First Hospital Beijing China Center for Data Science Peking University Beijing China National Engineering Laboratory for Big Data Analysis and Applications Peking University Beijing China Peking University Changsha Institute for Computing and Digital Economy Beijing China Beijing Tongren Eye Center Beijing Tongren Hospital Capital Medical University Beijing Ophthalmology and Visual Science Key Lab Beijing China

Background: The predictive value of retinal vessel caliber, measured through artificial intelligence (AI), for incident cardiovascular disease (CVD) risk remains to be explored. Our study aimed to investigate the association between AI-measured retinal vessel caliber and the risk of incident CVD in a Chinese community-based population. Methods: We conducted a prospective cohort study on subjects from a Beijing community in China who were free of prevalent stroke or myocardial infarction and underwent retinal photography at baseline. By deep-learning algorithm, retinal vessel caliber measurements, including central retinal arteriolar equivalent (CRAE), central retinal venular equivalent (CRVE), and arteriolar-to-venular ratio (AVR), were obtained from 0.5 to 1 disc diameter from the optic disc margin. The primary endpoint was an incident major adverse cardiovascular event (MACE), defined as a composite of first non-fatal stroke, first non-fatal acute myocardial infarction (AMI), and cardiovascular death. The secondary endpoints included first stroke, first AMI, and cardiovascular death. Findings: A total of 3,585 participants were included. The mean age was 56.49 ± 8.94 years, and 2335 (65.1%) were female. Prevalence of prior hypertension and diabetes was 1594 (44.5%) and 676 (18.9%), respectively. The mean values for CRAE, CRVE, and AVR were 190.83 ± 29.92 μm, 278.26 ± 36.34 μm, and 0.69 ± 0.08, respectively. During the follow-up (median, 7.53 years), there were 293 cases of incident MACE (8.2%), 226 strokes (6.3%), 57 AMIs (1.6%), and 44 cardiovascular deaths (1.2%). The Kaplan–Meier curves showed significant differences in cumulative hazards of the primary endpoint among tertiles of CRAE, CRVE, and AVR. In Cox proportional-hazards models adjusting for covariates, CRAE was negatively associated with the risk of incident MACE (per 10 μm increase, hazard ratio [HR] = 0.95, 95% confidence interval [CI]: 0.92-0.99, P = 0.009) and the risk of incident stroke (per 10 μm

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Class-Imbalanced Semi-Supervised Learning for Large-Scale Point Cloud Semantic Segmentation Via Decoupling Optimization

SSRN

引用

SSRN 2023年

作者： Li, Mengtian Lin, Shaohui Wang, Zihan Shen, Yunhang Zhang, Baochang Ma, Lizhuang Visual Media Intelligent Processing Research Group Department of Film and Television Engineering Shanghai University Shanghai200072 China School of Computer Science and Technology East China Normal University Shanghai200062 China Key Laboratory of Advanced Theory and Application in Statistics and Data Science Ministry of Education China School of Automation Science and Electrical Engineering Beihang University Beijing100191 China Youtu Lab Tencent China

Semi-supervised learning (SSL), thanks to the significant reduction of data annotation costs, has been an active research topic for large-scale 3D scene understanding. However, the existing SSL-based methods suffer from severe training bias, mainly due to class imbalance and long-tail distributions of the point cloud data. As a result, they lead to a biased prediction for the tail class segmentation. In this paper, we introduce a new decoupling optimization framework, which disentangles feature representation learning and classifier in an alternative optimization manner to shift the bias decision boundary effectively. In particular, we first employ two-round pseudo-label generation to select unlabeled points across head-to-tail classes. We further introduce multi-class imbalanced focus loss to adaptively pay more attention to feature learning across head-to-tail classes. We fix the backbone parameters after feature learning and retrain the classifier using ground-truth points to update its parameters. Ex-✩Fully documented templates are available in the elsarticle package on CTAN. © 2023, The Authors. All rights reserved.

关键词： Semantic Segmentation

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：