检索结果-内蒙古大学图书馆

Learning from context： a mutual reinforcement model for Chinese microblog opinion retrieval

Frontiers of Computer Science 2018年第4期12卷 714-724页

作者： Jingjing WEI Xiangwen LIAO Houdong ZHENG Guolong CHEN Xueqi CHENG College of Mathematics and Computer Science Fuzhou University Fuzhou 350108 China College of Electronics and Information Science Fujian Jiangxia University Fuzhou 350108 China Fujian Provincial Key Laboratory of Network Computing and Intelligence Processing Fuzhou University Fuzhou 350108 China Institute of Computing Technology Chinese Academic of Sciences Beijing 100190 China

This study addresses the problem of Chinese microblog opinion retrieval, which aims to retrieve opinionated Chinese microblog posts relevant to a target specified by a user query. Existing studies have shown that lexicon-based approaches employed online public sentiment resources to rank sentiment words relying on the document features. However, this approach could not be effectively applied to mi- croblogs that have typical user-generated content with valu- able contextual information：＂user-user＂ interpersonal interactions and ＂user-post/comment＂ intrapersonal interactions. This contextual information is very helpful in estimating the strength of sentiment words more accurately. In this study, we integrate the social contextual relationships among users, posts/comments, and sentiment words into a mutual reinforcement model and propose a unified three-layer heterogeneous graph, on which a random walk sentiment word weighting algorithm is presented to measure the strength of opinion of the sentiment words. Furthermore, the weights of sentiment words are incorporated into a lexicon-based model for Chinese microblog opinion retrieval. Comparative experiments are conducted on a Chinese microblog corpus, and the results show that our proposed mutual reinforcement model achieves significant improvement over previous methods.

关键词： opinion retrieval sentiment words lexiconweighting mutual reinforcement model

来源：评论

学校读者我要写书评

暂无评论

DSRGAN: Explicitly learning disentangled representation of underlying structure and rendering for image generation without tuple supervision

arXiv

引用

arXiv 2019年

作者： Hao, Guang-Yuan Yu, Hong-Xing Zheng, Wei-Shi School of Data and Computer Science Sun Yat-sen University Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Collaborative Innovation Center of High Performance Computing Nudt Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou

We focus on explicitly learning disentangled representation for natural image generation, where the underlying spatial structure and the rendering on the structure can be independently controlled respectively, yet using no tuple supervision. The setting is significant since tuple supervision is costly and sometimes even unavailable. However, the task is highly unconstrained and thus ill-posed. To address this problem, we propose to introduce an auxiliary domain which shares a common underlying-structure space with the target domain, and we make a partially shared latent space assumption. The key idea is to encourage the partially shared latent variable to represent the similar underlying spatial structures in both domains, while the two domain-specific latent variables will be unavoidably arranged to present renderings of two domains respectively. This is achieved by designing two parallel generative networks with a common Progressive Rendering Architecture (PRA), which constrains both generative networks' behaviors to model shared underlying structure and to model spatially dependent relation between rendering and underlying structure. Thus, we propose DSRGAN (GANs for Disentangling Underlying Structure and Rendering) to instantiate our method. We also propose a quantitative criterion (the Normalized Disentanglability) to quantify disentanglability. Comparison to the state-of-The-Art methods shows that DSRGAN can significantly outperform them in disentanglability. Copyright © 2019, The Authors. All rights reserved.

关键词： Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

A New Free-Standing Aqueous Zinc-Ion Capacitor Based on MnO2–CNTs Cathode and MXene Anode

引用

Nano-Micro Letters 2019年第4期11卷 227-238页

作者： Siliang Wang Qiang Wang Wei Zeng Min Wang Limin Ruan Yanan Ma Key Laboratory of Intelligent Computing and Signal Processing Ministry of EducationAnhui UniversityNo.3 Feixi RoadHefei 230039Anhui ProvincePeople’s Republic of China National Engineering Research Center for Agro-Ecological Big Data Analysis and Application School of Electronics and Information EngineeringAnhui UniversityNo.111 Jiulong RoadHefei 230601Anhui ProvincePeople’s Republic of China School of Sciences Hubei University of Automotive TechnologyNo.167 Checheng West RoadShiyan 442002Hubei ProvincePeople’s Republic of China

Restricted by their energy storage mechanism,current energy storage devices have certain drawbacks,such as low power density for batteries and low energy density for ***,the nearest ion capacitors,such as lithium-ion and sodium-ion capacitors containing battery-type and capacitor-type electrodes,may allow achieving both high energy and power *** the inspiration,a new zinc-ion capacitor(ZIC)has been designed and realized by assembling the free-standing manganese dioxide-carbon nanotubes(MnO2-CNTs)battery-type cathode and MXene(Ti3C2Tx)capacitortype anode in an aqueous *** ZIC can avoid the insecurity issues that frequently occurred in lithium-ion and sodium-ion capacitors in organic *** expected,the ZIC in an aqueous liquid electrolyte exhibits excellent electrochemical performance(based on the total weight of cathode and anode),such as a high specific capacitance of 115.1 F g?1(1 mV s?1),high energy density of 98.6 Wh kg?1(77.5 W kg?1),high power density of 2480.6 W kg?1(29.7 Wh kg?1),and high capacitance retention of^83.6%of its initial capacitance(15,000 cycles).Even in an aqueous gel electrolyte,the ZIC also exhibits excellent *** work provides an essential strategy for designing next-generation high-performance energy storage devices.

关键词： Energy storage Zinc-ion capacitor Battery-type and capacitor-type electrodes MXene Electrochemical performance

来源：评论

学校读者我要写书评

暂无评论

Ensemble Margin Based Semi-Supervised Random Forest for the Classification of Hyperspectral Image with Limited Training Data

Ensemble Margin Based Semi-Supervised Random Forest for the ...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Wei Feng Wenjiang Huang Gabriel Dauphin Junshi Xia Yinghui Quan Huichun Ye Yingying Dong Key laboratory of Digital Earth Science Chinese Academy of Sciences Beijing China Laboratory of Information Processing and Transmission University Paris XIII France Geoinformatics Unit RIKEN Center for Advanced Intelligence Project Tokyo Japan Key Laboratory for Radar Signal Processing Xidian University Shaanxi China

In this paper, we propose a novel ensemble margin based semi-supervised random forest (EMRF) algorithm for the classification of the hyperspectral image with limited training data. The proposed method tries to improve the effectiveness of the ensemble model via adaptively labeling the unlabeled instances with high classification probability then adding them into the training set. The classification probability of a training instance is reflected by the unsupervised margin value of this instance. The higher ensemble margin of an instance, the higher probability the instance being classified correctly and added into to the training set in the next iteration.

关键词： Training Radio frequency Hyperspectral imaging Training data

来源：评论

学校读者我要写书评

暂无评论

Automated Selection of Evolutionary Multi-objective Optimization Algorithms

Automated Selection of Evolutionary Multi-objective Optimiza...

引用

IEEE Symposium Series on Computational intelligence (SSCI)

作者： Ye Tian Shichen Peng Tobias Rodemann Xingyi Zhang Yaochu Jin Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Institutes of Physical Science and Information Technology Anhui University Hefei China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei China Honda Research Institute Europe Offenbach/Main Germany Department of Computer Science University of Surrey Guildford Surrey United Kingdom

ISBN: (数字)9781728124858

ISBN: (纸本)9781728124865

In the last two decades, many evolutionary algorithms have shown promising performance in solving a variety of multi-objective optimization problems (MOPs). Since there does not exist an evolutionary algorithm having the best performance on all the MOPs, it is unreasonable to use a single evolutionary algorithm to tackle all the MOPs. Since many real-world MOPs are computationally expensive, selecting the best evolutionary algorithm from multiple candidates via empirical comparisons is also impractical. To address the above issues, this paper proposes an automated algorithm selection method for choosing the most suitable evolutionary algorithm for a given MOP. The proposed method establishes a predictor based on the performance of a set of candidate evolutionary algorithms on multiple benchmark MOPs, where the inputs of the predictor are the explicit and implicit features of an MOP, and the output is the index of the evolutionary algorithm having the best performance on the MOP. Experimental results indicate that the evolutionary algorithm suggested by the proposed method is highly competitive among all the candidate evolutionary algorithms, demonstrating the practical value of the proposed method for engineers to select an evolutionary algorithm for their applications.

关键词： Evolutionary computation Benchmark testing Feature extraction Optimization Prediction algorithms Convergence Linear programming

来源：评论

学校读者我要写书评

暂无评论

Preface

Lecture Notes in Electrical Engineering

引用

Lecture Notes in Electrical Engineering 2022年 808 LNEE卷 v页

作者： Liu, Qi Liu, Xiaodong Chen, Bo Zhang, Yiming Peng, Jiansheng School of Computer and Software Nanjing University of Information Science and Technology Nanjing Jiangsu China School of Computing Edinburgh Napier University Edinburgh United Kingdom State Key Laboratory of Radar Signal Processing Xidian University Xi’an Shaanxi China School of Civil Engineering and Transportation Hebei University of Technology Tianjin Tianjin China Hechi Universtiy Guangxi Hechi China

来源：评论

学校读者我要写书评

暂无评论

Bilingual Word Embedding with Sentence Combination CNN for 1-to-N Sentence Alignment 20

Bilingual Word Embedding with Sentence Combination CNN for 1...

引用

Proceedings of the 4th International Conference on Natural Language processing and Information Retrieval

作者： Xinyuan Ren Xiangling Fu Xuesi Zhou Chunsheng Liu Songfeng Gao Lei Peng School of Software Engineering Beijing University of Posts and Telecommunications Beijing China and Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education Beijing University of Posts and Telecommunications Beijing China Department of Electronic Engineering Tsinghua University Hai Dian Beijing China and Multimedia Signal and Intelligent Information Processing Lab Tsinghua University Hai Dian Beijing China BUPT and Huarong Joint lab of Smart Finance Beijing P. R. China and HuaRong RongTong (Beijing) Technology Co. Ltd Beijing P. R. China

ISBN: (纸本)9781450377607

Sentence alignment, as one of the most active and fundamental tasks in the field of natural language processing (NLP), is usually realized in two categories of methods. One is traditional methods which are firstly proposed, the other, which are adopted later, is based on the Neural Network method. Presently, under the limitation that the existing mainstream data corpora are mostly in the form of 1-to-1, the alignment models with relatively good performance mainly apply to the cases of 1-to-1 sentence alignment. However, under the circumstance that a sentence contains too much information, 1-to-N sentence alignment can actually have a better effect on sentence translation tasks, compared with the 1-to-1 form, since it is more flexible and can reduce the complexity of the original sentence. As a result, we attempt to exploit neural networks with relatively good performance in the cases of 1-to-1 to fit in the cases of 1-to-N. In this paper, a novel 1-N Bilingual word Embedding with Sentence Combination CNN Improved Framework (1-NBESCC) is proposed in order to align 1-to-N sentences more precisely. Experiments show that our proposed model performs as good as the traditional methods such as BLEUALIGN in 1-to-1 situation, but much better in 1-to-N situation.

关键词： Convolutional Neural Network

来源：评论

学校读者我要写书评

暂无评论

Localization of Deep Inpainting Using High-Pass Fully Convolutional Network

Localization of Deep Inpainting Using High-Pass Fully Convol...

引用

International Conference on Computer Vision (ICCV)

作者： Haodong Li Jiwu Huang Guangdong Key Laboratory of Intelligent Information Processing and Shenzhen Key Laboratory of Media Security National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society China

ISBN: (数字)9781728148038

ISBN: (纸本)9781728148045

Image inpainting has been substantially improved with deep learning in the past years. Deep inpainting can fill image regions with plausible contents, which are not visually apparent. Although inpainting is originally designed to repair images, it can even be used for malicious manipulations, e.g., removal of specific objects. Therefore, it is necessary to identify the presence of inpainting in an image. This paper presents a method to locate the regions manipulated by deep inpainting. The proposed method employs a fully convolutional network that is based on high-pass filtered image residuals. Firstly, we analyze and observe that the inpainted regions are more distinguishable from the untouched ones in the residual domain. Hence, a high-pass pre-filtering module is designed to get image residuals for enhancing inpainting traces. Then, a feature extraction module, which learns discriminative features from image residuals, is built with four concatenated ResNet blocks. The learned feature maps are finally enlarged by an up-sampling module, so that a pixel-wise inpainting localization map is obtained. The whole network is trained end-to-end with a loss addressing the class imbalance. Extensive experimental results evaluated on both synthetic and realistic images subjected to deep inpainting have shown the effectiveness of the proposed method.

关键词： Forensics Feature extraction Convolution Kernel Machine learning Computer vision Probability

来源：评论

学校读者我要写书评

暂无评论

A Localization Method of High Energy Transients for All-Sky Gamma-Ray Monitor

arXiv

引用

arXiv 2022年

作者： Zhao, Yi Xue, Wangchen Xiong, Shaolin Luo, Qi Wang, Yuanhao Liu, Jiacong Yu, Heng Zhao, Xiaoyun Huang, Yue Liao, Jinyuan Sun, Jianchao Li, Xiaobo Yi, Qibin Cai, Ce Xiao, Shuo Xie, Shenglun Zheng, Chao Zhang, Yanqiu Wang, Chenwei Tan, Wenjun Guo, Zhiwei Li, Chaoyang An, Zhenghua Chen, Gang Du, Yanqi Gao, Min Gong, Ke Guo, Dongya He, Jiang He, Jianjian Li, Bing Li, Gang Li, Xinqiao Liang, Jing Liang, Xiaohua Liu, Yaqing Ma, Xiang Qiao, Rui Song, Liming Song, Xinying Sun, Xilei Wang, Jin Wang, Ping Wen, Xiangyang Wu, Hong Xu, Yanbing Yang, Sheng Zhang, Dali Zhang, Fan Zhang, Hongmei Zhang, Peng Zhang, Shu Zhang, Zhen Zheng, Shijie Zhang, Keke Han, Xingbo Wu, Haiyan Hu, Tai Geng, Hao Lu, Gaopeng Xu, Wei Lyu, Fanchao Zhang, Hongbo Lu, Fangjun Zhang, Shuangnan Department of Astronomy Beijing Normal University Beijing100875 China Key Laboratory of Particle Astrophysics Institute of High Energy Physics Chinese Academy of Sciences Beijing100049 China University of Chinese Academy of Sciences Beijing100049 China School of Physics and Optoelectronics Xiangtan University Hunan Xiangtan411105 China College of Physics Hebei Normal University Shijiazhuang050024 China Guizhou Provincial Key Laboratory of Radio Astronomy and Data Processing Guizhou Normal University Guiyang550001 China School of Physics and Electronic Science Guizhou Normal University Guiyang550001 China Institute of Astrophysics Central China Normal University Wuhan430079 China College of physics Sciences Technology Hebei University Baoding071002 China Physics and Space Science College China West Normal University Nanchong637002 China School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu611756 China College of Electronic and information Engineering Tongji University Shanghai201804 China Innovation Academy for Microsatellites of Chinese Academy of Sciences Shanghai201304 China National Space Science Center Chinese Academy of Sciences Beijing100190 China School of Earth and Space Sciences University of Science and Technology of China Hefei230026 China Electronic Information School Wuhan University Hubei Wuhan430072 China Key Laboratory of Transportation Meteorology of China Meteorological Administration Nanjing Joint China Key Laboratory of Middle Atmosphere and Global Environment Observation Institute of Atmospheric Physics Chinese Academy of Sciences Beijing100029 China

Fast and reliable localization of high-energy transients is crucial for characterizing the burst properties and guiding the follow-up observations. Localization based on the relative counts of different detectors has been widely used for all-sky gamma-ray monitors. There are two major methods for this counts distribution localization: χ2 minimization method and the Bayesian method. Here we propose a modified Bayesian method that could take advantage of both the accuracy of the Bayesian method and the simplicity of the χ2 method. With comprehensive simulations, we find that our Bayesian method with Poisson likelihood is generally more applicable for various bursts than χ2 method, especially for weak bursts. We further proposed a location-spectrum iteration approach based on the Bayesian inference, which could alleviate the problems caused by the spectral difference between the burst and location templates. Our method is very suitable for scenarios with limited computation resources or time-sensitive applications, such as in-flight localization software, and low-latency localization for rapid follow-up observations. Copyright © 2022, The Authors. All rights reserved.

关键词： Gamma rays

来源：评论

学校读者我要写书评

暂无评论

DeePMD-kit v3: A Multiple-Backend Framework for Machine Learning Potentials

arXiv

引用

arXiv 2025年

作者： Zeng, Jinzhe Zhang, Duo Peng, Anyang Zhang, Xiangyu He, Sensen Wang, Yan Liu, Xinzijian Bi, Hangrui Li, Yifan Cai, Chun Zhang, Chengqian Du, Yiming Zhu, Jia-Xin Mo, Pinghui Huang, Zhengtao Zeng, Qiyu Shi, Shaochen Qin, Xuejian Yu, Zhaoxi Luo, Chenxing Ding, Ye Liu, Yun-Pei Shi, Ruosong Wang, Zhenyu Bore, Sigbjørn Løland Chang, Junhan Deng, Zhe Ding, Zhaohan Han, Siyuan Jiang, Wanrun Ke, Guolin Liu, Zhaoqing Lu, Denghui Muraoka, Koki Oliaei, Hananeh Singh, Anurag Kumar Que, Haohui Xu, Weihong Xu, Zhangmancang Zhuang, Yong-Bin Dai, Jiayu Giese, Timothy J. Jia, Weile Xu, Ben York, Darrin M. Zhang, Linfeng Wang, Han School of Artificial Intelligence and Data Science Unversity of Science and Technology of China Hefei China AI for Science Institute Beijing100080 China DP Technology Beijing100080 China Academy for Advanced Interdisciplinary Studies Peking University Beijing100871 China State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences Beijing100871 China University of Chinese Academy of Sciences Beijing China Baidu Inc. Beijing China Department of Computer Science University of Toronto TorontoON Canada Department of Chemistry Princeton University PrincetonNJ08540 United States University of Chinese Academy of Sciences Beijing100871 China State Key Laboratory of Physical Chemistry of Solid Surfaces iChEM College of Chemistry and Chemical Engineering Xiamen University Xiamen361005 China College of Integrated Circuits Hunan University Changsha410082 China State Key Laboratory of Advanced Technology for Materials Synthesis and Processing Center for Smart Materials and Device Integration School of Material Science and Engineering Wuhan University of Technology Wuhan430070 China College of Science National University of Defense Technology Changsha410073 China Hunan Key Laboratory of Extreme Matter and Applications National University of Defense Technology Changsha410073 China ByteDance Research Beijing100098 China Ningbo Institute of Materials Technology and Engineering Chinese Academy of Sciences Ningbo315201 China College of Materials Science and Opto-Electronic Technology University of Chinese Academy of Sciences Beijing100049 China Key Laboratory of Theoretical and Computational Photochemistry of Ministry of Education College of Chemistry Beijing Normal University Beijing100875 China Department of Geosciences Princeton University PrincetonNJ08544 United States Department of Applied Physics and Applied Mathematics Columbia University New YorkNY10027 United States IKKEM Fujian Xiamen361005 China Graduate

In recent years, machine learning potentials (MLPs) have become indispensable tools in physics, chemistry, and materials science, driving the development of software packages for molecular dynamics (MD) simulations and related applications. These packages, typically built on specific machine learning frameworks such as TensorFlow, PyTorch, or JAX, face integration challenges when advanced applications demand communication across different frameworks. The previous TensorFlow-based implementation of DeePMD-kit exemplified these limitations. In this work, we introduce DeePMD-kit version 3, a significant update featuring a multi-backend framework that supports TensorFlow, PyTorch, JAX, and PaddlePaddle backends, and demonstrate the versatility of this architecture through the integration of other MLPs packages and of Differentiable Molecular Force Field. This architecture allows seamless backend switching with minimal modifications, enabling users and developers to integrate DeePMD-kit with other packages using different machine learning frameworks. This innovation facilitates the development of more complex and interoperable workflows, paving the way for broader applications of MLPs in scientific research. Copyright © 2025, The Authors. All rights reserved.

关键词： Molecular dynamics

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：